librarian-bots/model_cards_with_metadata_test

modelId stringlengths 5 122	author stringlengths 2 42	last_modified unknown	downloads int64 0 738M	likes int64 0 11k	library_name stringclasses 245 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 48 values	createdAt unknown	card stringlengths 1 901k
h1t/TCD-SD15-LoRA	h1t	"2024-03-08T16:30:52Z"	2,618	20	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "arxiv:2402.19159", "base_model:runwayml/stable-diffusion-v1-5", "license:mit", "region:us" ]	text-to-image	"2024-03-08T16:29:23Z"	--- tags: - text-to-image - stable-diffusion - lora - diffusers base_model: runwayml/stable-diffusion-v1-5 license: mit library_name: diffusers --- # Model description Official TCD LoRA for Stable Diffusion v1.5 of the paper [Trajectory Consistency Distillation](https://arxiv.org/abs/2402.19159). For more usage please found at [Project Page](https://mhh0318.github.io/tcd/) Here is a simple example: ` ```python import torch from diffusers import StableDiffusionPipeline, TCDScheduler device = "cuda" base_model_id = "runwayml/stable-diffusion-v1-5" tcd_lora_id = "h1t/TCD-SD15-LoRA" pipe = StableDiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device) pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config) pipe.load_lora_weights(tcd_lora_id) pipe.fuse_lora() prompt = "Beautiful woman, bubblegum pink, lemon yellow, minty blue, futuristic, high-detail, epic composition, watercolor." image = pipe( prompt=prompt, num_inference_steps=4, guidance_scale=0, # Eta (referred to as `gamma` in the paper) is used to control the stochasticity in every step. # A value of 0.3 often yields good results. # We recommend using a higher eta when increasing the number of inference steps. eta=0.3, generator=torch.Generator(device=device).manual_seed(42), ).images[0] ``` ![](assets/result.png)
adipanda/colorizer_300k	adipanda	"2024-06-22T19:16:10Z"	2,618	0	diffusers	[ "diffusers", "safetensors", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "controlnet", "diffusers-training", "license:creativeml-openrail-m", "region:us" ]	text-to-image	"2024-06-19T20:48:11Z"	--- library_name: diffusers license: creativeml-openrail-m tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - controlnet - diffusers-training - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - controlnet - diffusers-training ---
Kukedlc/NeuralSynthesis-7B-v0.1	Kukedlc	"2024-05-25T17:09:45Z"	2,617	3	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2024-04-06T03:40:01Z"	--- license: apache-2.0 tags: - merge - mergekit - lazymergekit model-index: - name: NeuralSynthesis-7B-v0.1 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 73.04 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 89.18 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 64.37 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 78.15 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 85.24 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 70.81 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard --- # NeuralSynthesis-7B-v0.1 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/eeH_75Yk5mq29FADx1TJk.png) NeuralSynthesis-7B-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): ## 🧩 Configuration ```yaml models: - model: MiniMoog/Mergerix-7b-v0.3 - model: automerger/Ognoexperiment27Multi_verse_model-7B - model: AurelPx/Percival_01-7b-slerp - model: automerger/YamshadowExperiment28-7B merge_method: model_stock base_model: automerger/YamshadowExperiment28-7B dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Kukedlc/NeuralSynthesis-7B-v0.1" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Kukedlc__NeuralSynthesis-7B-v0.1) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|76.80\| \|AI2 Reasoning Challenge (25-Shot)\|73.04\| \|HellaSwag (10-Shot) \|89.18\| \|MMLU (5-Shot) \|64.37\| \|TruthfulQA (0-shot) \|78.15\| \|Winogrande (5-shot) \|85.24\| \|GSM8k (5-shot) \|70.81\|
Weyaxi/Dolphin2.1-OpenOrca-7B	Weyaxi	"2024-01-13T11:49:19Z"	2,615	5	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2023-10-11T09:23:18Z"	--- license: apache-2.0 model-index: - name: Dolphin2.1-OpenOrca-7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 63.91 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 84.26 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 62.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 53.84 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 78.22 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 19.94 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard --- <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> Merge of [ehartford/dolphin-2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b) and [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) using ties merge. ### Weights - [ehartford/dolphin-2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b): 0.5 - [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca): 0.3 ### Density - [ehartford/dolphin-2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b): 0.5 - [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca): 0.5 # Quantizationed versions Quantizationed versions of this model is available thanks to [TheBloke](https://hf.co/TheBloke). ##### GPTQ - [TheBloke/Dolphin2.1-OpenOrca-7B-GPTQ](https://huggingface.co/TheBloke/Dolphin2.1-OpenOrca-7B-GPTQ) ##### GGUF - [TheBloke/Dolphin2.1-OpenOrca-7B-GGUF](https://huggingface.co/TheBloke/Dolphin2.1-OpenOrca-7B-GGUF) ##### AWQ - [TheBloke/Dolphin2.1-OpenOrca-7B-AWQ](https://huggingface.co/TheBloke/Dolphin2.1-OpenOrca-7B-AWQ) # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Dolphin2.1-OpenOrca-7B) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|60.47\| \|AI2 Reasoning Challenge (25-Shot)\|63.91\| \|HellaSwag (10-Shot) \|84.26\| \|MMLU (5-Shot) \|62.66\| \|TruthfulQA (0-shot) \|53.84\| \|Winogrande (5-shot) \|78.22\| \|GSM8k (5-shot) \|19.94\|
IlyasMoutawwakil/vit-with-hidden_states	IlyasMoutawwakil	"2024-04-18T09:41:30Z"	2,615	0	transformers	[ "transformers", "safetensors", "openvino", "vit", "image-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	"2024-04-18T09:40:57Z"	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Yntec/ProjectKawai	Yntec	"2024-06-13T16:40:00Z"	2,615	2	diffusers	[ "diffusers", "safetensors", "Anime", "Style", "HuyNguyen", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	"2024-06-13T12:36:01Z"	--- language: - en library_name: diffusers pipeline_tag: text-to-image tags: - Anime - Style - HuyNguyen - stable-diffusion - stable-diffusion-diffusers - diffusers - text-to-image inference: true license: other --- # Project K (Kawai) 768x768 version of Project K (Kawai) 5.0.1-250723 for the inference API. Check its licence at the original page: https://civitai.com/models/21138?modelVersionId=125063 Samples and prompts: ![Free online AI image generator Project Kawai](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/axGMvu1frY9l-1anJv-1g.png) (Click for larger) Top left: street, no humans, cloud, road, building, dappled sunlight, plant, blue sky, sunlight, scenery, grass, sign, day, landspace, real world location, shade, sky, city, shadow, tree, outdoors, from below, buildings Top right: sleeveless, smile, blue eyes, bangs, cloud, hat, straw hat, cloudy sky, summer, sitting, open mouth, cup, umbrella, crossed legs, innertube, denim shorts, sun, blue sky, looking at viewer, :d, hair between eyes, sunflower, legs, sunlight, sundress, holding cup, long hair, bare shoulders, short shorts Bottom left: 1girl, cleavage, fox ears, black hair, violet eyes, ribbon, kimono, japanese clothes, light smile, bare shoulders, detached sleeves, cleavage, collarbone, sitting, ribbon, hair ornament Bottom right: classic anime pretty cute little girl playing poker, iconic, 1970, from the movie, Cartoon, sharp focus. acrylic art on canvas by Clay Mann and ROSSDRAWS. CHIBI 512x512 version of Project K (Kawai) v5: https://huggingface.co/Ojimi/anime-kawai-diffusion
mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF	mradermacher	"2024-06-08T23:05:27Z"	2,614	4	transformers	[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "not-for-all-audiences", "en", "base_model:Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B", "license:llama3", "endpoints_compatible", "region:us" ]	null	"2024-06-08T20:55:57Z"	--- base_model: Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B language: - en library_name: transformers license: llama3 quantized_by: mradermacher tags: - merge - mergekit - lazymergekit - not-for-all-audiences --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
mradermacher/LBonVent-12B-i1-GGUF	mradermacher	"2024-06-13T22:58:18Z"	2,614	0	transformers	[ "transformers", "gguf", "en", "base_model:Envoid/LBonVent-12B", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	null	"2024-06-13T16:14:34Z"	--- base_model: Envoid/LBonVent-12B language: - en library_name: transformers license: cc-by-nc-4.0 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Envoid/LBonVent-12B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/LBonVent-12B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.8 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 3.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 3.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q2_K.gguf) \| i1-Q2_K \| 4.3 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 4.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 4.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 5.0 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 5.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 5.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 5.5 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 6.0 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 6.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q4_0.gguf) \| i1-Q4_0 \| 6.4 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 6.5 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 6.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 7.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 8.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q6_K.gguf) \| i1-Q6_K \| 9.3 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants. <!-- end -->
uitnlp/visobert	uitnlp	"2024-06-09T14:21:50Z"	2,613	27	transformers	[ "transformers", "pytorch", "xlm-roberta", "fill-mask", "Vietnamese", "Social Media", "Vietnamese Pre-trained Model", "Sentiment Analysis", "Hate Speech Detection", "Spam Detection", "Emotionn Recognition", "vi", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	"2023-10-17T06:13:28Z"	--- pipeline_tag: fill-mask widget: - text: hào quang rực <mask> language: - vi tags: - Vietnamese - Social Media - Vietnamese Pre-trained Model - Sentiment Analysis - Hate Speech Detection - Spam Detection - Emotionn Recognition --- # <a name="introduction"></a> ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing (EMNLP 2023 - Main) Disclaimer: The paper contains actual comments on social networks that might be construed as abusive, offensive, or obscene. ViSoBERT is the state-of-the-art language model for Vietnamese social media tasks: - ViSoBERT is the first monolingual MLM ([XLM-R](https://github.com/facebookresearch/XLM#xlm-r-new-model) architecture) built specifically for Vietnamese social media texts. - ViSoBERT outperforms previous monolingual, multilingual, and multilingual social media approaches, obtaining new state-of-the-art performances on four downstream Vietnamese social media tasks. The general architecture and experimental results of ViSoBERT can be found in our [paper](https://aclanthology.org/2023.emnlp-main.315/): @inproceedings{nguyen-etal-2023-visobert, title = "{V}i{S}o{BERT}: A Pre-Trained Language Model for {V}ietnamese Social Media Text Processing", author = "Nguyen, Nam and Phan, Thang and Nguyen, Duc-Vu and Nguyen, Kiet", editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika", booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing", month = dec, year = "2023", address = "Singapore", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.emnlp-main.315", pages = "5191--5207", abstract = "English and Chinese, known as resource-rich languages, have witnessed the strong development of transformer-based language models for natural language processing tasks. Although Vietnam has approximately 100M people speaking Vietnamese, several pre-trained models, e.g., PhoBERT, ViBERT, and vELECTRA, performed well on general Vietnamese NLP tasks, including POS tagging and named entity recognition. These pre-trained language models are still limited to Vietnamese social media tasks. In this paper, we present the first monolingual pre-trained language model for Vietnamese social media texts, ViSoBERT, which is pre-trained on a large-scale corpus of high-quality and diverse Vietnamese social media texts using XLM-R architecture. Moreover, we explored our pre-trained model on five important natural language downstream tasks on Vietnamese social media texts: emotion recognition, hate speech detection, sentiment analysis, spam reviews detection, and hate speech spans detection. Our experiments demonstrate that ViSoBERT, with far fewer parameters, surpasses the previous state-of-the-art models on multiple Vietnamese social media tasks. Our ViSoBERT model is available only for research purposes. Disclaimer: This paper contains actual comments on social networks that might be construed as abusive, offensive, or obscene.", } The pretraining dataset of our paper is available at: [Pretraining dataset](https://drive.google.com/drive/folders/1C144LOlkbH78m0-JoMckpRXubV7XT7Kb) Please CITE our paper when ViSoBERT is used to help produce published results or is incorporated into other software. Installation Install `transformers` and `SentencePiece` packages: pip install transformers pip install SentencePiece Example usage ```python from transformers import AutoModel, AutoTokenizer import torch model= AutoModel.from_pretrained('uitnlp/visobert') tokenizer = AutoTokenizer.from_pretrained('uitnlp/visobert') encoding = tokenizer('hào quang rực rỡ', return_tensors='pt') with torch.no_grad(): output = model(**encoding) ```
mradermacher/Poppy_Porpoise-Biomix-GGUF	mradermacher	"2024-06-02T09:12:21Z"	2,612	1	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Nitral-AI/Poppy_Porpoise-Biomix", "endpoints_compatible", "region:us" ]	null	"2024-06-02T04:06:28Z"	--- base_model: Nitral-AI/Poppy_Porpoise-Biomix language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Nitral-AI/Poppy_Porpoise-Biomix <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
Fulcrum-AI/Ryze-Q8_0-GGUF	Fulcrum-AI	"2024-06-26T12:36:24Z"	2,612	0	null	[ "gguf", "llama-cpp", "gguf-my-repo", "base_model:Fulcrum-AI/Ryze", "license:apache-2.0", "region:us" ]	null	"2024-06-26T12:35:53Z"	--- base_model: Fulcrum-AI/Ryze license: apache-2.0 tags: - llama-cpp - gguf-my-repo --- # Fulcrum-AI/Ryze-Q8_0-GGUF This model was converted to GGUF format from [`Fulcrum-AI/Ryze`](https://huggingface.co/Fulcrum-AI/Ryze) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Fulcrum-AI/Ryze) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Fulcrum-AI/Ryze-Q8_0-GGUF --hf-file ryze-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Fulcrum-AI/Ryze-Q8_0-GGUF --hf-file ryze-q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Fulcrum-AI/Ryze-Q8_0-GGUF --hf-file ryze-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Fulcrum-AI/Ryze-Q8_0-GGUF --hf-file ryze-q8_0.gguf -c 2048 ```
nomic-ai/gpt4all-j	nomic-ai	"2024-04-08T15:39:51Z"	2,611	289	transformers	[ "transformers", "pytorch", "safetensors", "gptj", "text-generation", "en", "dataset:nomic-ai/gpt4all-j-prompt-generations", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	"2023-04-11T15:39:16Z"	--- license: apache-2.0 datasets: - nomic-ai/gpt4all-j-prompt-generations language: - en pipeline_tag: text-generation --- # Model Card for GPT4All-J An Apache-2 licensed chatbot trained over a massive curated corpus of assistant interactions including word problems, multi-turn dialogue, code, poems, songs, and stories. ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This model has been finetuned from [GPT-J](https://huggingface.co/EleutherAI/gpt-j-6B) - Developed by: [Nomic AI](https://home.nomic.ai) - Model Type: A finetuned GPT-J model on assistant style interaction data - Language(s) (NLP): English - License: Apache-2 - Finetuned from model [optional]: [GPT-J](https://huggingface.co/EleutherAI/gpt-j-6B) We have released several versions of our finetuned GPT-J model using [different dataset versions](https://huggingface.co/datasets/nomic-ai/gpt4all-j-prompt-generations) - v1.0: The original model trained on the v1.0 dataset - v1.1-breezy: Trained on afiltered dataset where we removed all instances of AI language model - v1.2-jazzy: Trained on a filtered dataset where we also removed instances like I'm sorry, I can't answer... and AI language model - v1.3-groovy: We added Dolly and ShareGPT to the v1.2 dataset and removed ~8% of the dataset in v1.2 that contained semantic duplicates using [Atlas](https://atlas.nomic.ai/). To download a model with a specific revision run ```python from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("nomic-ai/gpt4all-j", revision="v1.2-jazzy") ``` Downloading without specifying `revision` defaults to `main`/`v1.0`. ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [https://github.com/nomic-ai/gpt4all](https://github.com/nomic-ai/gpt4all) - Base Model Repository: [https://github.com/kingoflolz/mesh-transformer-jax](https://github.com/kingoflolz/mesh-transformer-jax) - Paper [optional]: [GPT4All-J: An Apache-2 Licensed Assistant-Style Chatbot](https://s3.amazonaws.com/static.nomic.ai/gpt4all/2023_GPT4All-J_Technical_Report_2.pdf) - Demo [optional]: [https://gpt4all.io/](https://gpt4all.io/) ### Training Procedure GPT4All is made possible by our compute partner [Paperspace](https://www.paperspace.com/). Trained on a DGX cluster with 8 A100 80GB GPUs for ~12 hours. Using Deepspeed + Accelerate, we use a global batch size of 256 with a learning rate of 2e-5. More information can be found in the repo. ### Results Results on common sense reasoning benchmarks ``` \| Model \| BoolQ \| PIQA \| HellaSwag \| WinoGrande \| ARC-e \| ARC-c \| OBQA \| Avg. \| \|:--------------------------\|:--------:\|:--------:\|:---------:\|:----------:\|:--------:\|:--------:\|:--------:\|:--------:\| \| GPT4All-J 6B v1.0 \| 73.4 \| 74.8 \| 63.4 \| 64.7 \| 54.9 \| 36.0 \| 40.2 \| 58.2 \| \| GPT4All-J v1.1-breezy \| 74.0 \| 75.1 \| 63.2 \| 63.6 \| 55.4 \| 34.9 \| 38.4 \| 57.8 \| \| GPT4All-J v1.2-jazzy \| 74.8 \| 74.9 \| 63.6 \| 63.8 \| 56.6 \| 35.3 \| 41.0 \| 58.6 \| \| GPT4All-J v1.3-groovy \| 73.6 \| 74.3 \| 63.8 \| 63.5 \| 57.7 \| 35.0 \| 38.8 \| 58.1 \| \| GPT4All-J Lora 6B \| 68.6 \| 75.8 \| 66.2 \| 63.5 \| 56.4 \| 35.7 \| 40.2 \| 58.1 \| \| GPT4All LLaMa Lora 7B \| 73.1 \| 77.6 \| 72.1 \| 67.8 \| 51.1 \| 40.4 \| 40.2 \| 60.3 \| \| GPT4All 13B snoozy \| 83.3 \| 79.2 \| 75.0 \| 71.3 \| 60.9 \| 44.2 \| 43.4 \| 65.3 \| \| Dolly 6B \| 68.8 \| 77.3 \| 67.6 \| 63.9 \| 62.9 \| 38.7 \| 41.2 \| 60.1 \| \| Dolly 12B \| 56.7 \| 75.4 \| 71.0 \| 62.2 \| 64.6 \| 38.5 \| 40.4 \| 58.4 \| \| Alpaca 7B \| 73.9 \| 77.2 \| 73.9 \| 66.1 \| 59.8 \| 43.3 \| 43.4 \| 62.4 \| \| Alpaca Lora 7B \| 74.3 \| 79.3 \| 74.0 \| 68.8 \| 56.6 \| 43.9 \| 42.6 \| 62.8 \| \| GPT-J 6.7B \| 65.4 \| 76.2 \| 66.2 \| 64.1 \| 62.2 \| 36.6 \| 38.2 \| 58.4 \| \| LLama 7B \| 73.1 \| 77.4 \| 73.0 \| 66.9 \| 52.5 \| 41.4 \| 42.4 \| 61.0 \| \| LLama 13B \| 68.5 \| 79.1 \| 76.2 \| 70.1 \| 60.0 \| 44.6 \| 42.2 \| 63.0 \| \| Pythia 6.7B \| 63.5 \| 76.3 \| 64.0 \| 61.1 \| 61.3 \| 35.2 \| 37.2 \| 57.0 \| \| Pythia 12B \| 67.7 \| 76.6 \| 67.3 \| 63.8 \| 63.9 \| 34.8 \| 38 \| 58.9 \| \| Fastchat T5 \| 81.5 \| 64.6 \| 46.3 \| 61.8 \| 49.3 \| 33.3 \| 39.4 \| 53.7 \| \| Fastchat Vicuña 7B \| 76.6 \| 77.2 \| 70.7 \| 67.3 \| 53.5 \| 41.2 \| 40.8 \| 61.0 \| \| Fastchat Vicuña 13B \| 81.5 \| 76.8 \| 73.3 \| 66.7 \| 57.4 \| 42.7 \| 43.6 \| 63.1 \| \| StableVicuña RLHF \| 82.3 \| 78.6 \| 74.1 \| 70.9 \| 61.0 \| 43.5 \| 44.4 \| 65.0 \| \| StableLM Tuned \| 62.5 \| 71.2 \| 53.6 \| 54.8 \| 52.4 \| 31.1 \| 33.4 \| 51.3 \| \| StableLM Base \| 60.1 \| 67.4 \| 41.2 \| 50.1 \| 44.9 \| 27.0 \| 32.0 \| 42.2 \| \| Koala 13B \| 76.5 \| 77.9 \| 72.6 \| 68.8 \| 54.3 \| 41.0 \| 42.8 \| 62.0 \| \| Open Assistant Pythia 12B \| 67.9 \| 78.0 \| 68.1 \| 65.0 \| 64.2 \| 40.4 \| 43.2 \| 61.0 \| \| Mosaic mpt-7b \| 74.8 \| 79.3 \| 76.3 \| 68.6 \| 70.0 \| 42.2 \| 42.6 \| 64.8 \| \| text-davinci-003 \| 88.1 \| 83.8 \| 83.4 \| 75.8 \| 83.9 \| 63.9 \| 51.0 \| 75.7 \| ```
CAiRE/UniVaR-lambda-1	CAiRE	"2024-06-14T17:58:19Z"	2,611	0	sentence-transformers	[ "sentence-transformers", "safetensors", "nomic_bert", "feature-extraction", "sentence-similarity", "mteb", "transformers", "transformers.js", "custom_code", "en", "arxiv:2402.01613", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-embeddings-inference", "region:us" ]	sentence-similarity	"2024-06-14T17:57:45Z"	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - feature-extraction - sentence-similarity - mteb - transformers - transformers.js model-index: - name: epoch_0_model results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 76.8507462686567 - type: ap value: 40.592189159090495 - type: f1 value: 71.01634655512476 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 91.51892500000001 - type: ap value: 88.50346762975335 - type: f1 value: 91.50342077459624 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 47.364 - type: f1 value: 46.72708080922794 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 25.178 - type: map_at_10 value: 40.244 - type: map_at_100 value: 41.321999999999996 - type: map_at_1000 value: 41.331 - type: map_at_3 value: 35.016999999999996 - type: map_at_5 value: 37.99 - type: mrr_at_1 value: 25.605 - type: mrr_at_10 value: 40.422000000000004 - type: mrr_at_100 value: 41.507 - type: mrr_at_1000 value: 41.516 - type: mrr_at_3 value: 35.23 - type: mrr_at_5 value: 38.15 - type: ndcg_at_1 value: 25.178 - type: ndcg_at_10 value: 49.258 - type: ndcg_at_100 value: 53.776 - type: ndcg_at_1000 value: 53.995000000000005 - type: ndcg_at_3 value: 38.429 - type: ndcg_at_5 value: 43.803 - type: precision_at_1 value: 25.178 - type: precision_at_10 value: 7.831 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 16.121 - type: precision_at_5 value: 12.29 - type: recall_at_1 value: 25.178 - type: recall_at_10 value: 78.307 - type: recall_at_100 value: 97.866 - type: recall_at_1000 value: 99.57300000000001 - type: recall_at_3 value: 48.364000000000004 - type: recall_at_5 value: 61.451 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 45.93034494751465 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 36.64579480054327 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 60.601310529222054 - type: mrr value: 75.04484896451656 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 88.57797718095814 - type: cos_sim_spearman value: 86.47064499110101 - type: euclidean_pearson value: 87.4559602783142 - type: euclidean_spearman value: 86.47064499110101 - type: manhattan_pearson value: 87.7232764230245 - type: manhattan_spearman value: 86.91222131777742 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 84.5422077922078 - type: f1 value: 84.47657456950589 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 38.48953561974464 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.75995857510105 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.008000000000003 - type: map_at_10 value: 39.51 - type: map_at_100 value: 40.841 - type: map_at_1000 value: 40.973 - type: map_at_3 value: 36.248999999999995 - type: map_at_5 value: 38.096999999999994 - type: mrr_at_1 value: 36.481 - type: mrr_at_10 value: 44.818000000000005 - type: mrr_at_100 value: 45.64 - type: mrr_at_1000 value: 45.687 - type: mrr_at_3 value: 42.036 - type: mrr_at_5 value: 43.782 - type: ndcg_at_1 value: 36.481 - type: ndcg_at_10 value: 45.152 - type: ndcg_at_100 value: 50.449 - type: ndcg_at_1000 value: 52.76499999999999 - type: ndcg_at_3 value: 40.161 - type: ndcg_at_5 value: 42.577999999999996 - type: precision_at_1 value: 36.481 - type: precision_at_10 value: 8.369 - type: precision_at_100 value: 1.373 - type: precision_at_1000 value: 0.186 - type: precision_at_3 value: 18.693 - type: precision_at_5 value: 13.533999999999999 - type: recall_at_1 value: 30.008000000000003 - type: recall_at_10 value: 56.108999999999995 - type: recall_at_100 value: 78.55499999999999 - type: recall_at_1000 value: 93.659 - type: recall_at_3 value: 41.754999999999995 - type: recall_at_5 value: 48.296 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.262 - type: map_at_10 value: 40.139 - type: map_at_100 value: 41.394 - type: map_at_1000 value: 41.526 - type: map_at_3 value: 37.155 - type: map_at_5 value: 38.785 - type: mrr_at_1 value: 38.153 - type: mrr_at_10 value: 46.369 - type: mrr_at_100 value: 47.072 - type: mrr_at_1000 value: 47.111999999999995 - type: mrr_at_3 value: 44.268 - type: mrr_at_5 value: 45.389 - type: ndcg_at_1 value: 38.153 - type: ndcg_at_10 value: 45.925 - type: ndcg_at_100 value: 50.394000000000005 - type: ndcg_at_1000 value: 52.37500000000001 - type: ndcg_at_3 value: 41.754000000000005 - type: ndcg_at_5 value: 43.574 - type: precision_at_1 value: 38.153 - type: precision_at_10 value: 8.796 - type: precision_at_100 value: 1.432 - type: precision_at_1000 value: 0.189 - type: precision_at_3 value: 20.318 - type: precision_at_5 value: 14.395 - type: recall_at_1 value: 30.262 - type: recall_at_10 value: 55.72200000000001 - type: recall_at_100 value: 74.97500000000001 - type: recall_at_1000 value: 87.342 - type: recall_at_3 value: 43.129 - type: recall_at_5 value: 48.336 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 39.951 - type: map_at_10 value: 51.248000000000005 - type: map_at_100 value: 52.188 - type: map_at_1000 value: 52.247 - type: map_at_3 value: 48.211 - type: map_at_5 value: 49.797000000000004 - type: mrr_at_1 value: 45.329 - type: mrr_at_10 value: 54.749 - type: mrr_at_100 value: 55.367999999999995 - type: mrr_at_1000 value: 55.400000000000006 - type: mrr_at_3 value: 52.382 - type: mrr_at_5 value: 53.649 - type: ndcg_at_1 value: 45.329 - type: ndcg_at_10 value: 56.847 - type: ndcg_at_100 value: 60.738 - type: ndcg_at_1000 value: 61.976 - type: ndcg_at_3 value: 51.59 - type: ndcg_at_5 value: 53.915 - type: precision_at_1 value: 45.329 - type: precision_at_10 value: 8.959 - type: precision_at_100 value: 1.187 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 22.612 - type: precision_at_5 value: 15.273 - type: recall_at_1 value: 39.951 - type: recall_at_10 value: 70.053 - type: recall_at_100 value: 86.996 - type: recall_at_1000 value: 95.707 - type: recall_at_3 value: 56.032000000000004 - type: recall_at_5 value: 61.629999999999995 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.566 - type: map_at_10 value: 33.207 - type: map_at_100 value: 34.166000000000004 - type: map_at_1000 value: 34.245 - type: map_at_3 value: 30.94 - type: map_at_5 value: 32.01 - type: mrr_at_1 value: 27.345000000000002 - type: mrr_at_10 value: 35.193000000000005 - type: mrr_at_100 value: 35.965 - type: mrr_at_1000 value: 36.028999999999996 - type: mrr_at_3 value: 32.806000000000004 - type: mrr_at_5 value: 34.021 - type: ndcg_at_1 value: 27.345000000000002 - type: ndcg_at_10 value: 37.891999999999996 - type: ndcg_at_100 value: 42.664 - type: ndcg_at_1000 value: 44.757000000000005 - type: ndcg_at_3 value: 33.123000000000005 - type: ndcg_at_5 value: 35.035 - type: precision_at_1 value: 27.345000000000002 - type: precision_at_10 value: 5.763 - type: precision_at_100 value: 0.859 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 13.71 - type: precision_at_5 value: 9.401 - type: recall_at_1 value: 25.566 - type: recall_at_10 value: 50.563 - type: recall_at_100 value: 72.86399999999999 - type: recall_at_1000 value: 88.68599999999999 - type: recall_at_3 value: 37.43 - type: recall_at_5 value: 41.894999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.663 - type: map_at_10 value: 23.552 - type: map_at_100 value: 24.538 - type: map_at_1000 value: 24.661 - type: map_at_3 value: 21.085 - type: map_at_5 value: 22.391 - type: mrr_at_1 value: 20.025000000000002 - type: mrr_at_10 value: 27.643 - type: mrr_at_100 value: 28.499999999999996 - type: mrr_at_1000 value: 28.582 - type: mrr_at_3 value: 25.083 - type: mrr_at_5 value: 26.544 - type: ndcg_at_1 value: 20.025000000000002 - type: ndcg_at_10 value: 28.272000000000002 - type: ndcg_at_100 value: 33.353 - type: ndcg_at_1000 value: 36.454 - type: ndcg_at_3 value: 23.579 - type: ndcg_at_5 value: 25.685000000000002 - type: precision_at_1 value: 20.025000000000002 - type: precision_at_10 value: 5.187 - type: precision_at_100 value: 0.897 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 10.987 - type: precision_at_5 value: 8.06 - type: recall_at_1 value: 16.663 - type: recall_at_10 value: 38.808 - type: recall_at_100 value: 61.305 - type: recall_at_1000 value: 83.571 - type: recall_at_3 value: 25.907999999999998 - type: recall_at_5 value: 31.214 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.695999999999998 - type: map_at_10 value: 37.018 - type: map_at_100 value: 38.263000000000005 - type: map_at_1000 value: 38.371 - type: map_at_3 value: 34.226 - type: map_at_5 value: 35.809999999999995 - type: mrr_at_1 value: 32.916000000000004 - type: mrr_at_10 value: 42.067 - type: mrr_at_100 value: 42.925000000000004 - type: mrr_at_1000 value: 42.978 - type: mrr_at_3 value: 39.637 - type: mrr_at_5 value: 41.134 - type: ndcg_at_1 value: 32.916000000000004 - type: ndcg_at_10 value: 42.539 - type: ndcg_at_100 value: 47.873 - type: ndcg_at_1000 value: 50.08200000000001 - type: ndcg_at_3 value: 37.852999999999994 - type: ndcg_at_5 value: 40.201 - type: precision_at_1 value: 32.916000000000004 - type: precision_at_10 value: 7.5840000000000005 - type: precision_at_100 value: 1.199 - type: precision_at_1000 value: 0.155 - type: precision_at_3 value: 17.485 - type: precision_at_5 value: 12.512 - type: recall_at_1 value: 27.695999999999998 - type: recall_at_10 value: 53.638 - type: recall_at_100 value: 76.116 - type: recall_at_1000 value: 91.069 - type: recall_at_3 value: 41.13 - type: recall_at_5 value: 46.872 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.108 - type: map_at_10 value: 33.372 - type: map_at_100 value: 34.656 - type: map_at_1000 value: 34.768 - type: map_at_3 value: 30.830999999999996 - type: map_at_5 value: 32.204 - type: mrr_at_1 value: 29.110000000000003 - type: mrr_at_10 value: 37.979 - type: mrr_at_100 value: 38.933 - type: mrr_at_1000 value: 38.988 - type: mrr_at_3 value: 35.731 - type: mrr_at_5 value: 36.963 - type: ndcg_at_1 value: 29.110000000000003 - type: ndcg_at_10 value: 38.635000000000005 - type: ndcg_at_100 value: 44.324999999999996 - type: ndcg_at_1000 value: 46.747 - type: ndcg_at_3 value: 34.37 - type: ndcg_at_5 value: 36.228 - type: precision_at_1 value: 29.110000000000003 - type: precision_at_10 value: 6.963 - type: precision_at_100 value: 1.146 - type: precision_at_1000 value: 0.152 - type: precision_at_3 value: 16.400000000000002 - type: precision_at_5 value: 11.552999999999999 - type: recall_at_1 value: 24.108 - type: recall_at_10 value: 49.597 - type: recall_at_100 value: 73.88900000000001 - type: recall_at_1000 value: 90.62400000000001 - type: recall_at_3 value: 37.662 - type: recall_at_5 value: 42.565 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.00791666666667 - type: map_at_10 value: 33.287749999999996 - type: map_at_100 value: 34.41141666666667 - type: map_at_1000 value: 34.52583333333333 - type: map_at_3 value: 30.734416666666668 - type: map_at_5 value: 32.137166666666666 - type: mrr_at_1 value: 29.305666666666664 - type: mrr_at_10 value: 37.22966666666666 - type: mrr_at_100 value: 38.066583333333334 - type: mrr_at_1000 value: 38.12616666666667 - type: mrr_at_3 value: 34.92275 - type: mrr_at_5 value: 36.23333333333334 - type: ndcg_at_1 value: 29.305666666666664 - type: ndcg_at_10 value: 38.25533333333333 - type: ndcg_at_100 value: 43.25266666666666 - type: ndcg_at_1000 value: 45.63583333333334 - type: ndcg_at_3 value: 33.777166666666666 - type: ndcg_at_5 value: 35.85 - type: precision_at_1 value: 29.305666666666664 - type: precision_at_10 value: 6.596416666666667 - type: precision_at_100 value: 1.0784166666666668 - type: precision_at_1000 value: 0.14666666666666664 - type: precision_at_3 value: 15.31075 - type: precision_at_5 value: 10.830916666666667 - type: recall_at_1 value: 25.00791666666667 - type: recall_at_10 value: 49.10933333333333 - type: recall_at_100 value: 71.09216666666667 - type: recall_at_1000 value: 87.77725000000001 - type: recall_at_3 value: 36.660916666666665 - type: recall_at_5 value: 41.94149999999999 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.521 - type: map_at_10 value: 30.043 - type: map_at_100 value: 30.936000000000003 - type: map_at_1000 value: 31.022 - type: map_at_3 value: 27.926000000000002 - type: map_at_5 value: 29.076999999999998 - type: mrr_at_1 value: 26.227 - type: mrr_at_10 value: 32.822 - type: mrr_at_100 value: 33.61 - type: mrr_at_1000 value: 33.672000000000004 - type: mrr_at_3 value: 30.776999999999997 - type: mrr_at_5 value: 31.866 - type: ndcg_at_1 value: 26.227 - type: ndcg_at_10 value: 34.041 - type: ndcg_at_100 value: 38.394 - type: ndcg_at_1000 value: 40.732 - type: ndcg_at_3 value: 30.037999999999997 - type: ndcg_at_5 value: 31.845000000000002 - type: precision_at_1 value: 26.227 - type: precision_at_10 value: 5.244999999999999 - type: precision_at_100 value: 0.808 - type: precision_at_1000 value: 0.107 - type: precision_at_3 value: 12.679000000000002 - type: precision_at_5 value: 8.773 - type: recall_at_1 value: 23.521 - type: recall_at_10 value: 43.633 - type: recall_at_100 value: 63.126000000000005 - type: recall_at_1000 value: 80.765 - type: recall_at_3 value: 32.614 - type: recall_at_5 value: 37.15 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.236 - type: map_at_10 value: 22.898 - type: map_at_100 value: 23.878 - type: map_at_1000 value: 24.009 - type: map_at_3 value: 20.87 - type: map_at_5 value: 22.025 - type: mrr_at_1 value: 19.339000000000002 - type: mrr_at_10 value: 26.382 - type: mrr_at_100 value: 27.245 - type: mrr_at_1000 value: 27.33 - type: mrr_at_3 value: 24.386 - type: mrr_at_5 value: 25.496000000000002 - type: ndcg_at_1 value: 19.339000000000002 - type: ndcg_at_10 value: 27.139999999999997 - type: ndcg_at_100 value: 31.944 - type: ndcg_at_1000 value: 35.077999999999996 - type: ndcg_at_3 value: 23.424 - type: ndcg_at_5 value: 25.188 - type: precision_at_1 value: 19.339000000000002 - type: precision_at_10 value: 4.8309999999999995 - type: precision_at_100 value: 0.845 - type: precision_at_1000 value: 0.128 - type: precision_at_3 value: 10.874 - type: precision_at_5 value: 7.825 - type: recall_at_1 value: 16.236 - type: recall_at_10 value: 36.513 - type: recall_at_100 value: 57.999 - type: recall_at_1000 value: 80.512 - type: recall_at_3 value: 26.179999999999996 - type: recall_at_5 value: 30.712 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.11 - type: map_at_10 value: 31.566 - type: map_at_100 value: 32.647 - type: map_at_1000 value: 32.753 - type: map_at_3 value: 29.24 - type: map_at_5 value: 30.564999999999998 - type: mrr_at_1 value: 28.265 - type: mrr_at_10 value: 35.504000000000005 - type: mrr_at_100 value: 36.436 - type: mrr_at_1000 value: 36.503 - type: mrr_at_3 value: 33.349000000000004 - type: mrr_at_5 value: 34.622 - type: ndcg_at_1 value: 28.265 - type: ndcg_at_10 value: 36.192 - type: ndcg_at_100 value: 41.388000000000005 - type: ndcg_at_1000 value: 43.948 - type: ndcg_at_3 value: 31.959 - type: ndcg_at_5 value: 33.998 - type: precision_at_1 value: 28.265 - type: precision_at_10 value: 5.989 - type: precision_at_100 value: 0.9650000000000001 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 14.335 - type: precision_at_5 value: 10.112 - type: recall_at_1 value: 24.11 - type: recall_at_10 value: 46.418 - type: recall_at_100 value: 69.314 - type: recall_at_1000 value: 87.397 - type: recall_at_3 value: 34.724 - type: recall_at_5 value: 39.925 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.091 - type: map_at_10 value: 29.948999999999998 - type: map_at_100 value: 31.502000000000002 - type: map_at_1000 value: 31.713 - type: map_at_3 value: 27.464 - type: map_at_5 value: 28.968 - type: mrr_at_1 value: 26.482 - type: mrr_at_10 value: 34.009 - type: mrr_at_100 value: 35.081 - type: mrr_at_1000 value: 35.138000000000005 - type: mrr_at_3 value: 31.785000000000004 - type: mrr_at_5 value: 33.178999999999995 - type: ndcg_at_1 value: 26.482 - type: ndcg_at_10 value: 35.008 - type: ndcg_at_100 value: 41.272999999999996 - type: ndcg_at_1000 value: 43.972 - type: ndcg_at_3 value: 30.804 - type: ndcg_at_5 value: 33.046 - type: precision_at_1 value: 26.482 - type: precision_at_10 value: 6.462 - type: precision_at_100 value: 1.431 - type: precision_at_1000 value: 0.22899999999999998 - type: precision_at_3 value: 14.360999999999999 - type: precision_at_5 value: 10.474 - type: recall_at_1 value: 22.091 - type: recall_at_10 value: 45.125 - type: recall_at_100 value: 72.313 - type: recall_at_1000 value: 89.503 - type: recall_at_3 value: 33.158 - type: recall_at_5 value: 39.086999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 19.883 - type: map_at_10 value: 26.951000000000004 - type: map_at_100 value: 27.927999999999997 - type: map_at_1000 value: 28.022000000000002 - type: map_at_3 value: 24.616 - type: map_at_5 value: 25.917 - type: mrr_at_1 value: 21.996 - type: mrr_at_10 value: 29.221000000000004 - type: mrr_at_100 value: 30.024 - type: mrr_at_1000 value: 30.095 - type: mrr_at_3 value: 26.833000000000002 - type: mrr_at_5 value: 28.155 - type: ndcg_at_1 value: 21.996 - type: ndcg_at_10 value: 31.421 - type: ndcg_at_100 value: 36.237 - type: ndcg_at_1000 value: 38.744 - type: ndcg_at_3 value: 26.671 - type: ndcg_at_5 value: 28.907 - type: precision_at_1 value: 21.996 - type: precision_at_10 value: 5.009 - type: precision_at_100 value: 0.799 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 11.275 - type: precision_at_5 value: 8.059 - type: recall_at_1 value: 19.883 - type: recall_at_10 value: 43.132999999999996 - type: recall_at_100 value: 65.654 - type: recall_at_1000 value: 84.492 - type: recall_at_3 value: 30.209000000000003 - type: recall_at_5 value: 35.616 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 17.756 - type: map_at_10 value: 30.378 - type: map_at_100 value: 32.537 - type: map_at_1000 value: 32.717 - type: map_at_3 value: 25.599 - type: map_at_5 value: 28.372999999999998 - type: mrr_at_1 value: 41.303 - type: mrr_at_10 value: 53.483999999999995 - type: mrr_at_100 value: 54.106 - type: mrr_at_1000 value: 54.127 - type: mrr_at_3 value: 50.315 - type: mrr_at_5 value: 52.396 - type: ndcg_at_1 value: 41.303 - type: ndcg_at_10 value: 40.503 - type: ndcg_at_100 value: 47.821000000000005 - type: ndcg_at_1000 value: 50.788 - type: ndcg_at_3 value: 34.364 - type: ndcg_at_5 value: 36.818 - type: precision_at_1 value: 41.303 - type: precision_at_10 value: 12.463000000000001 - type: precision_at_100 value: 2.037 - type: precision_at_1000 value: 0.26 - type: precision_at_3 value: 25.798 - type: precision_at_5 value: 19.896 - type: recall_at_1 value: 17.756 - type: recall_at_10 value: 46.102 - type: recall_at_100 value: 70.819 - type: recall_at_1000 value: 87.21799999999999 - type: recall_at_3 value: 30.646 - type: recall_at_5 value: 38.022 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 9.033 - type: map_at_10 value: 20.584 - type: map_at_100 value: 29.518 - type: map_at_1000 value: 31.186000000000003 - type: map_at_3 value: 14.468 - type: map_at_5 value: 17.177 - type: mrr_at_1 value: 69.75 - type: mrr_at_10 value: 77.025 - type: mrr_at_100 value: 77.36699999999999 - type: mrr_at_1000 value: 77.373 - type: mrr_at_3 value: 75.583 - type: mrr_at_5 value: 76.396 - type: ndcg_at_1 value: 58.5 - type: ndcg_at_10 value: 45.033 - type: ndcg_at_100 value: 49.071 - type: ndcg_at_1000 value: 56.056 - type: ndcg_at_3 value: 49.936 - type: ndcg_at_5 value: 47.471999999999994 - type: precision_at_1 value: 69.75 - type: precision_at_10 value: 35.775 - type: precision_at_100 value: 11.594999999999999 - type: precision_at_1000 value: 2.062 - type: precision_at_3 value: 52.5 - type: precision_at_5 value: 45.300000000000004 - type: recall_at_1 value: 9.033 - type: recall_at_10 value: 26.596999999999998 - type: recall_at_100 value: 54.607000000000006 - type: recall_at_1000 value: 76.961 - type: recall_at_3 value: 15.754999999999999 - type: recall_at_5 value: 20.033 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 48.345000000000006 - type: f1 value: 43.4514918068706 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 71.29100000000001 - type: map_at_10 value: 81.059 - type: map_at_100 value: 81.341 - type: map_at_1000 value: 81.355 - type: map_at_3 value: 79.74799999999999 - type: map_at_5 value: 80.612 - type: mrr_at_1 value: 76.40299999999999 - type: mrr_at_10 value: 84.615 - type: mrr_at_100 value: 84.745 - type: mrr_at_1000 value: 84.748 - type: mrr_at_3 value: 83.776 - type: mrr_at_5 value: 84.343 - type: ndcg_at_1 value: 76.40299999999999 - type: ndcg_at_10 value: 84.981 - type: ndcg_at_100 value: 86.00999999999999 - type: ndcg_at_1000 value: 86.252 - type: ndcg_at_3 value: 82.97 - type: ndcg_at_5 value: 84.152 - type: precision_at_1 value: 76.40299999999999 - type: precision_at_10 value: 10.446 - type: precision_at_100 value: 1.1199999999999999 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 32.147999999999996 - type: precision_at_5 value: 20.135 - type: recall_at_1 value: 71.29100000000001 - type: recall_at_10 value: 93.232 - type: recall_at_100 value: 97.363 - type: recall_at_1000 value: 98.905 - type: recall_at_3 value: 87.893 - type: recall_at_5 value: 90.804 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 18.667 - type: map_at_10 value: 30.853 - type: map_at_100 value: 32.494 - type: map_at_1000 value: 32.677 - type: map_at_3 value: 26.91 - type: map_at_5 value: 29.099000000000004 - type: mrr_at_1 value: 37.191 - type: mrr_at_10 value: 46.171 - type: mrr_at_100 value: 47.056 - type: mrr_at_1000 value: 47.099000000000004 - type: mrr_at_3 value: 44.059 - type: mrr_at_5 value: 45.147 - type: ndcg_at_1 value: 37.191 - type: ndcg_at_10 value: 38.437 - type: ndcg_at_100 value: 44.62 - type: ndcg_at_1000 value: 47.795 - type: ndcg_at_3 value: 35.003 - type: ndcg_at_5 value: 36.006 - type: precision_at_1 value: 37.191 - type: precision_at_10 value: 10.586 - type: precision_at_100 value: 1.688 - type: precision_at_1000 value: 0.22699999999999998 - type: precision_at_3 value: 23.302 - type: precision_at_5 value: 17.006 - type: recall_at_1 value: 18.667 - type: recall_at_10 value: 45.367000000000004 - type: recall_at_100 value: 68.207 - type: recall_at_1000 value: 87.072 - type: recall_at_3 value: 32.129000000000005 - type: recall_at_5 value: 37.719 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 39.494 - type: map_at_10 value: 66.223 - type: map_at_100 value: 67.062 - type: map_at_1000 value: 67.11500000000001 - type: map_at_3 value: 62.867 - type: map_at_5 value: 64.994 - type: mrr_at_1 value: 78.987 - type: mrr_at_10 value: 84.585 - type: mrr_at_100 value: 84.773 - type: mrr_at_1000 value: 84.77900000000001 - type: mrr_at_3 value: 83.592 - type: mrr_at_5 value: 84.235 - type: ndcg_at_1 value: 78.987 - type: ndcg_at_10 value: 73.64 - type: ndcg_at_100 value: 76.519 - type: ndcg_at_1000 value: 77.51 - type: ndcg_at_3 value: 68.893 - type: ndcg_at_5 value: 71.585 - type: precision_at_1 value: 78.987 - type: precision_at_10 value: 15.529000000000002 - type: precision_at_100 value: 1.7770000000000001 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 44.808 - type: precision_at_5 value: 29.006999999999998 - type: recall_at_1 value: 39.494 - type: recall_at_10 value: 77.643 - type: recall_at_100 value: 88.825 - type: recall_at_1000 value: 95.321 - type: recall_at_3 value: 67.211 - type: recall_at_5 value: 72.519 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 85.55959999999999 - type: ap value: 80.7246500384617 - type: f1 value: 85.52336485065454 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 23.631 - type: map_at_10 value: 36.264 - type: map_at_100 value: 37.428 - type: map_at_1000 value: 37.472 - type: map_at_3 value: 32.537 - type: map_at_5 value: 34.746 - type: mrr_at_1 value: 24.312 - type: mrr_at_10 value: 36.858000000000004 - type: mrr_at_100 value: 37.966 - type: mrr_at_1000 value: 38.004 - type: mrr_at_3 value: 33.188 - type: mrr_at_5 value: 35.367 - type: ndcg_at_1 value: 24.312 - type: ndcg_at_10 value: 43.126999999999995 - type: ndcg_at_100 value: 48.642 - type: ndcg_at_1000 value: 49.741 - type: ndcg_at_3 value: 35.589 - type: ndcg_at_5 value: 39.515 - type: precision_at_1 value: 24.312 - type: precision_at_10 value: 6.699 - type: precision_at_100 value: 0.9450000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 15.153 - type: precision_at_5 value: 11.065999999999999 - type: recall_at_1 value: 23.631 - type: recall_at_10 value: 64.145 - type: recall_at_100 value: 89.41 - type: recall_at_1000 value: 97.83500000000001 - type: recall_at_3 value: 43.769000000000005 - type: recall_at_5 value: 53.169 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.4108527131783 - type: f1 value: 93.1415880261038 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 77.24806201550388 - type: f1 value: 60.531916308197175 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 73.71553463349024 - type: f1 value: 71.70753174900791 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.79757901815736 - type: f1 value: 77.83719850433258 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 33.74193296622113 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 30.64257594108566 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.811018518883625 - type: mrr value: 31.910376577445003 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.409 - type: map_at_10 value: 13.093 - type: map_at_100 value: 16.256999999999998 - type: map_at_1000 value: 17.617 - type: map_at_3 value: 9.555 - type: map_at_5 value: 11.428 - type: mrr_at_1 value: 45.201 - type: mrr_at_10 value: 54.179 - type: mrr_at_100 value: 54.812000000000005 - type: mrr_at_1000 value: 54.840999999999994 - type: mrr_at_3 value: 51.909000000000006 - type: mrr_at_5 value: 53.519000000000005 - type: ndcg_at_1 value: 43.189 - type: ndcg_at_10 value: 35.028 - type: ndcg_at_100 value: 31.226 - type: ndcg_at_1000 value: 39.678000000000004 - type: ndcg_at_3 value: 40.596 - type: ndcg_at_5 value: 38.75 - type: precision_at_1 value: 44.582 - type: precision_at_10 value: 25.974999999999998 - type: precision_at_100 value: 7.793 - type: precision_at_1000 value: 2.036 - type: precision_at_3 value: 38.493 - type: precision_at_5 value: 33.994 - type: recall_at_1 value: 5.409 - type: recall_at_10 value: 16.875999999999998 - type: recall_at_100 value: 30.316 - type: recall_at_1000 value: 60.891 - type: recall_at_3 value: 10.688 - type: recall_at_5 value: 13.832 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 36.375 - type: map_at_10 value: 51.991 - type: map_at_100 value: 52.91400000000001 - type: map_at_1000 value: 52.93600000000001 - type: map_at_3 value: 48.014 - type: map_at_5 value: 50.381 - type: mrr_at_1 value: 40.759 - type: mrr_at_10 value: 54.617000000000004 - type: mrr_at_100 value: 55.301 - type: mrr_at_1000 value: 55.315000000000005 - type: mrr_at_3 value: 51.516 - type: mrr_at_5 value: 53.435 - type: ndcg_at_1 value: 40.759 - type: ndcg_at_10 value: 59.384 - type: ndcg_at_100 value: 63.157 - type: ndcg_at_1000 value: 63.654999999999994 - type: ndcg_at_3 value: 52.114000000000004 - type: ndcg_at_5 value: 55.986000000000004 - type: precision_at_1 value: 40.759 - type: precision_at_10 value: 9.411999999999999 - type: precision_at_100 value: 1.153 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 23.329 - type: precision_at_5 value: 16.256999999999998 - type: recall_at_1 value: 36.375 - type: recall_at_10 value: 79.053 - type: recall_at_100 value: 95.167 - type: recall_at_1000 value: 98.82 - type: recall_at_3 value: 60.475 - type: recall_at_5 value: 69.327 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 70.256 - type: map_at_10 value: 83.8 - type: map_at_100 value: 84.425 - type: map_at_1000 value: 84.444 - type: map_at_3 value: 80.906 - type: map_at_5 value: 82.717 - type: mrr_at_1 value: 80.97999999999999 - type: mrr_at_10 value: 87.161 - type: mrr_at_100 value: 87.262 - type: mrr_at_1000 value: 87.263 - type: mrr_at_3 value: 86.175 - type: mrr_at_5 value: 86.848 - type: ndcg_at_1 value: 80.97999999999999 - type: ndcg_at_10 value: 87.697 - type: ndcg_at_100 value: 88.959 - type: ndcg_at_1000 value: 89.09899999999999 - type: ndcg_at_3 value: 84.83800000000001 - type: ndcg_at_5 value: 86.401 - type: precision_at_1 value: 80.97999999999999 - type: precision_at_10 value: 13.261000000000001 - type: precision_at_100 value: 1.5150000000000001 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 37.01 - type: precision_at_5 value: 24.298000000000002 - type: recall_at_1 value: 70.256 - type: recall_at_10 value: 94.935 - type: recall_at_100 value: 99.274 - type: recall_at_1000 value: 99.928 - type: recall_at_3 value: 86.602 - type: recall_at_5 value: 91.133 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.322692497613104 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 61.895813503775074 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.338 - type: map_at_10 value: 10.767 - type: map_at_100 value: 12.537999999999998 - type: map_at_1000 value: 12.803999999999998 - type: map_at_3 value: 7.788 - type: map_at_5 value: 9.302000000000001 - type: mrr_at_1 value: 21.4 - type: mrr_at_10 value: 31.637999999999998 - type: mrr_at_100 value: 32.688 - type: mrr_at_1000 value: 32.756 - type: mrr_at_3 value: 28.433000000000003 - type: mrr_at_5 value: 30.178 - type: ndcg_at_1 value: 21.4 - type: ndcg_at_10 value: 18.293 - type: ndcg_at_100 value: 25.274 - type: ndcg_at_1000 value: 30.284 - type: ndcg_at_3 value: 17.391000000000002 - type: ndcg_at_5 value: 15.146999999999998 - type: precision_at_1 value: 21.4 - type: precision_at_10 value: 9.48 - type: precision_at_100 value: 1.949 - type: precision_at_1000 value: 0.316 - type: precision_at_3 value: 16.167 - type: precision_at_5 value: 13.22 - type: recall_at_1 value: 4.338 - type: recall_at_10 value: 19.213 - type: recall_at_100 value: 39.562999999999995 - type: recall_at_1000 value: 64.08 - type: recall_at_3 value: 9.828000000000001 - type: recall_at_5 value: 13.383000000000001 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.42568163642142 - type: cos_sim_spearman value: 78.5797159641342 - type: euclidean_pearson value: 80.22151260811604 - type: euclidean_spearman value: 78.5797151953878 - type: manhattan_pearson value: 80.21224215864788 - type: manhattan_spearman value: 78.55641478381344 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 85.44020710812569 - type: cos_sim_spearman value: 78.91631735081286 - type: euclidean_pearson value: 81.64188964182102 - type: euclidean_spearman value: 78.91633286881678 - type: manhattan_pearson value: 81.69294748512496 - type: manhattan_spearman value: 78.93438558002656 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 84.27165426412311 - type: cos_sim_spearman value: 85.40429140249618 - type: euclidean_pearson value: 84.7509580724893 - type: euclidean_spearman value: 85.40429140249618 - type: manhattan_pearson value: 84.76488289321308 - type: manhattan_spearman value: 85.4256793698708 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 83.138851760732 - type: cos_sim_spearman value: 81.64101363896586 - type: euclidean_pearson value: 82.55165038934942 - type: euclidean_spearman value: 81.64105257080502 - type: manhattan_pearson value: 82.52802949883335 - type: manhattan_spearman value: 81.61255430718158 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 86.0654695484029 - type: cos_sim_spearman value: 87.20408521902229 - type: euclidean_pearson value: 86.8110651362115 - type: euclidean_spearman value: 87.20408521902229 - type: manhattan_pearson value: 86.77984656478691 - type: manhattan_spearman value: 87.1719947099227 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 83.77823915496512 - type: cos_sim_spearman value: 85.43566325729779 - type: euclidean_pearson value: 84.5396956658821 - type: euclidean_spearman value: 85.43566325729779 - type: manhattan_pearson value: 84.5665398848169 - type: manhattan_spearman value: 85.44375870303232 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.20030208471798 - type: cos_sim_spearman value: 87.20485505076539 - type: euclidean_pearson value: 88.10588324368722 - type: euclidean_spearman value: 87.20485505076539 - type: manhattan_pearson value: 87.92324770415183 - type: manhattan_spearman value: 87.0571314561877 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 63.06093161604453 - type: cos_sim_spearman value: 64.2163140357722 - type: euclidean_pearson value: 65.27589680994006 - type: euclidean_spearman value: 64.2163140357722 - type: manhattan_pearson value: 65.45904383711101 - type: manhattan_spearman value: 64.55404716679305 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 84.32976164578706 - type: cos_sim_spearman value: 85.54302197678368 - type: euclidean_pearson value: 85.26307149193056 - type: euclidean_spearman value: 85.54302197678368 - type: manhattan_pearson value: 85.26647282029371 - type: manhattan_spearman value: 85.5316135265568 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 81.44675968318754 - type: mrr value: 94.92741826075158 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 56.34400000000001 - type: map_at_10 value: 65.927 - type: map_at_100 value: 66.431 - type: map_at_1000 value: 66.461 - type: map_at_3 value: 63.529 - type: map_at_5 value: 64.818 - type: mrr_at_1 value: 59.333000000000006 - type: mrr_at_10 value: 67.54599999999999 - type: mrr_at_100 value: 67.892 - type: mrr_at_1000 value: 67.917 - type: mrr_at_3 value: 65.778 - type: mrr_at_5 value: 66.794 - type: ndcg_at_1 value: 59.333000000000006 - type: ndcg_at_10 value: 70.5 - type: ndcg_at_100 value: 72.688 - type: ndcg_at_1000 value: 73.483 - type: ndcg_at_3 value: 66.338 - type: ndcg_at_5 value: 68.265 - type: precision_at_1 value: 59.333000000000006 - type: precision_at_10 value: 9.3 - type: precision_at_100 value: 1.053 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 25.889 - type: precision_at_5 value: 16.866999999999997 - type: recall_at_1 value: 56.34400000000001 - type: recall_at_10 value: 82.789 - type: recall_at_100 value: 92.767 - type: recall_at_1000 value: 99 - type: recall_at_3 value: 71.64399999999999 - type: recall_at_5 value: 76.322 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.75742574257426 - type: cos_sim_ap value: 93.52081548447406 - type: cos_sim_f1 value: 87.33850129198966 - type: cos_sim_precision value: 90.37433155080214 - type: cos_sim_recall value: 84.5 - type: dot_accuracy value: 99.75742574257426 - type: dot_ap value: 93.52081548447406 - type: dot_f1 value: 87.33850129198966 - type: dot_precision value: 90.37433155080214 - type: dot_recall value: 84.5 - type: euclidean_accuracy value: 99.75742574257426 - type: euclidean_ap value: 93.52081548447406 - type: euclidean_f1 value: 87.33850129198966 - type: euclidean_precision value: 90.37433155080214 - type: euclidean_recall value: 84.5 - type: manhattan_accuracy value: 99.75841584158415 - type: manhattan_ap value: 93.4975678585854 - type: manhattan_f1 value: 87.26708074534162 - type: manhattan_precision value: 90.45064377682404 - type: manhattan_recall value: 84.3 - type: max_accuracy value: 99.75841584158415 - type: max_ap value: 93.52081548447406 - type: max_f1 value: 87.33850129198966 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 64.31437036686651 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 33.25569319007206 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 49.90474939720706 - type: mrr value: 50.568115503777264 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 29.866828641244712 - type: cos_sim_spearman value: 30.077555055873866 - type: dot_pearson value: 29.866832988572266 - type: dot_spearman value: 30.077555055873866 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.232 - type: map_at_10 value: 2.094 - type: map_at_100 value: 11.971 - type: map_at_1000 value: 28.158 - type: map_at_3 value: 0.688 - type: map_at_5 value: 1.114 - type: mrr_at_1 value: 88 - type: mrr_at_10 value: 93.4 - type: mrr_at_100 value: 93.4 - type: mrr_at_1000 value: 93.4 - type: mrr_at_3 value: 93 - type: mrr_at_5 value: 93.4 - type: ndcg_at_1 value: 84 - type: ndcg_at_10 value: 79.923 - type: ndcg_at_100 value: 61.17 - type: ndcg_at_1000 value: 53.03 - type: ndcg_at_3 value: 84.592 - type: ndcg_at_5 value: 82.821 - type: precision_at_1 value: 88 - type: precision_at_10 value: 85 - type: precision_at_100 value: 63.019999999999996 - type: precision_at_1000 value: 23.554 - type: precision_at_3 value: 89.333 - type: precision_at_5 value: 87.2 - type: recall_at_1 value: 0.232 - type: recall_at_10 value: 2.255 - type: recall_at_100 value: 14.823 - type: recall_at_1000 value: 49.456 - type: recall_at_3 value: 0.718 - type: recall_at_5 value: 1.175 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.547 - type: map_at_10 value: 11.375 - type: map_at_100 value: 18.194 - type: map_at_1000 value: 19.749 - type: map_at_3 value: 5.825 - type: map_at_5 value: 8.581 - type: mrr_at_1 value: 32.653 - type: mrr_at_10 value: 51.32 - type: mrr_at_100 value: 51.747 - type: mrr_at_1000 value: 51.747 - type: mrr_at_3 value: 47.278999999999996 - type: mrr_at_5 value: 48.605 - type: ndcg_at_1 value: 29.592000000000002 - type: ndcg_at_10 value: 28.151 - type: ndcg_at_100 value: 39.438 - type: ndcg_at_1000 value: 50.769 - type: ndcg_at_3 value: 30.758999999999997 - type: ndcg_at_5 value: 30.366 - type: precision_at_1 value: 32.653 - type: precision_at_10 value: 25.714 - type: precision_at_100 value: 8.041 - type: precision_at_1000 value: 1.555 - type: precision_at_3 value: 33.333 - type: precision_at_5 value: 31.837 - type: recall_at_1 value: 2.547 - type: recall_at_10 value: 18.19 - type: recall_at_100 value: 49.538 - type: recall_at_1000 value: 83.86 - type: recall_at_3 value: 7.329 - type: recall_at_5 value: 11.532 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.4952 - type: ap value: 14.793362635531409 - type: f1 value: 55.204635551516915 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 61.5365025466893 - type: f1 value: 61.81742556334845 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 49.05531070301185 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.51725576682364 - type: cos_sim_ap value: 75.2292304265163 - type: cos_sim_f1 value: 69.54022988505749 - type: cos_sim_precision value: 63.65629110039457 - type: cos_sim_recall value: 76.62269129287598 - type: dot_accuracy value: 86.51725576682364 - type: dot_ap value: 75.22922386081054 - type: dot_f1 value: 69.54022988505749 - type: dot_precision value: 63.65629110039457 - type: dot_recall value: 76.62269129287598 - type: euclidean_accuracy value: 86.51725576682364 - type: euclidean_ap value: 75.22925730473472 - type: euclidean_f1 value: 69.54022988505749 - type: euclidean_precision value: 63.65629110039457 - type: euclidean_recall value: 76.62269129287598 - type: manhattan_accuracy value: 86.52321630804077 - type: manhattan_ap value: 75.20608115037336 - type: manhattan_f1 value: 69.60000000000001 - type: manhattan_precision value: 64.37219730941705 - type: manhattan_recall value: 75.75197889182058 - type: max_accuracy value: 86.52321630804077 - type: max_ap value: 75.22925730473472 - type: max_f1 value: 69.60000000000001 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.34877944657896 - type: cos_sim_ap value: 86.71257569277373 - type: cos_sim_f1 value: 79.10386355986088 - type: cos_sim_precision value: 76.91468470434214 - type: cos_sim_recall value: 81.4213119802895 - type: dot_accuracy value: 89.34877944657896 - type: dot_ap value: 86.71257133133368 - type: dot_f1 value: 79.10386355986088 - type: dot_precision value: 76.91468470434214 - type: dot_recall value: 81.4213119802895 - type: euclidean_accuracy value: 89.34877944657896 - type: euclidean_ap value: 86.71257651501476 - type: euclidean_f1 value: 79.10386355986088 - type: euclidean_precision value: 76.91468470434214 - type: euclidean_recall value: 81.4213119802895 - type: manhattan_accuracy value: 89.35848177901967 - type: manhattan_ap value: 86.69330615469126 - type: manhattan_f1 value: 79.13867741453949 - type: manhattan_precision value: 76.78881807647741 - type: manhattan_recall value: 81.63689559593472 - type: max_accuracy value: 89.35848177901967 - type: max_ap value: 86.71257651501476 - type: max_f1 value: 79.13867741453949 license: apache-2.0 language: - en --- # nomic-embed-text-v1: A Reproducible Long Context (8192) Text Embedder `nomic-embed-text-v1` is 8192 context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks. \| Name \| SeqLen \| MTEB \| LoCo \| Jina Long Context \| Open Weights \| Open Training Code \| Open Data \| \| :-------------------------------:\| :----- \| :-------- \| :------: \| :---------------: \| :-----------: \| :----------------: \| :---------- \| \| nomic-embed-text-v1 \| 8192 \| 62.39 \|85.53 \| 54.16 \| ✅ \| ✅ \| ✅ \| \| jina-embeddings-v2-base-en \| 8192 \| 60.39 \| 85.45 \| 51.90 \| ✅ \| ❌ \| ❌ \| \| text-embedding-3-small \| 8191 \| 62.26 \| 82.40 \| 58.20 \| ❌ \| ❌ \| ❌ \| \| text-embedding-ada-002 \| 8191 \| 60.99 \| 52.7 \| 55.25 \| ❌ \| ❌ \| ❌ \| ## Hosted Inference API The easiest way to get started with Nomic Embed is through the Nomic Embedding API. Generating embeddings with the `nomic` Python client is as easy as ```python from nomic import embed output = embed.text( texts=['Nomic Embedding API', '#keepAIOpen'], model='nomic-embed-text-v1', task_type='search_document' ) print(output) ``` For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text) ## Data Visualization Click the Nomic Atlas map below to visualize a 5M sample of our contrastive pretraining data! [![image/webp](https://cdn-uploads.huggingface.co/production/uploads/607997c83a565c15675055b3/pjhJhuNyRfPagRd_c_iUz.webp)](https://atlas.nomic.ai/map/nomic-text-embed-v1-5m-sample) ## Training Details We train our embedder using a multi-stage training pipeline. Starting from a long-context [BERT model](https://huggingface.co/nomic-ai/nomic-bert-2048), the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles. In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage. For more details, see the Nomic Embed [Technical Report](https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf) and corresponding [blog post](https://blog.nomic.ai/posts/nomic-embed-text-v1). Training data to train the models is released in its entirety. For more details, see the `contrastors` [repository](https://github.com/nomic-ai/contrastors) ## Usage Note `nomic-embed-text` requires prefixes! We support the prefixes `[search_query, search_document, classification, clustering]`. For retrieval applications, you should prepend `search_document` for all your documents and `search_query` for your queries. For example, you are building a RAG application over the top of Wikipedia. You would embed all Wikipedia articles with the prefix `search_document` and any questions you ask with `search_query`. For example: ```python queries = ["search_query: who is the first president of the united states?", "search_query: when was babe ruth born?"] documents = ["search_document: <article about US Presidents>", "search_document: <article about Babe Ruth>"] ``` ### Sentence Transformers ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] embeddings = model.encode(sentences) print(embeddings) ``` ### Transformers ```python import torch import torch.nn.functional as F from transformers import AutoTokenizer, AutoModel def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) model.eval() encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') with torch.no_grad(): model_output = model(**encoded_input) embeddings = mean_pooling(model_output, encoded_input['attention_mask']) embeddings = F.normalize(embeddings, p=2, dim=1) print(embeddings) ``` The model natively supports scaling of the sequence length past 2048 tokens. To do so, ```diff - tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') + tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192) - model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) + model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2) ``` ### Transformers.js ```js import { pipeline } from '@xenova/transformers'; // Create a feature extraction pipeline const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1', { quantized: false, // Comment out this line to use the quantized version }); // Compute sentence embeddings const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']; const embeddings = await extractor(texts, { pooling: 'mean', normalize: true }); console.log(embeddings); ``` # Join the Nomic Community - Nomic: [https://nomic.ai](https://nomic.ai) - Discord: [https://discord.gg/myY5YDR8z8](https://discord.gg/myY5YDR8z8) - Twitter: [https://twitter.com/nomic_ai](https://twitter.com/nomic_ai) # Citation If you find the model, dataset, or training code useful, please cite our work ```bibtex @misc{nussbaum2024nomic, title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar}, year={2024}, eprint={2402.01613}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf	RichardErkhov	"2024-06-22T18:14:05Z"	2,611	0	null	[ "gguf", "region:us" ]	null	"2024-06-22T18:02:32Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) TinyLlama-1.1B-step-50K-105b - GGUF - Model creator: https://huggingface.co/TinyLlama/ - Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-step-50K-105b/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [TinyLlama-1.1B-step-50K-105b.Q2_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q2_K.gguf) \| Q2_K \| 0.4GB \| \| [TinyLlama-1.1B-step-50K-105b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ3_XS.gguf) \| IQ3_XS \| 0.44GB \| \| [TinyLlama-1.1B-step-50K-105b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ3_S.gguf) \| IQ3_S \| 0.47GB \| \| [TinyLlama-1.1B-step-50K-105b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q3_K_S.gguf) \| Q3_K_S \| 0.47GB \| \| [TinyLlama-1.1B-step-50K-105b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ3_M.gguf) \| IQ3_M \| 0.48GB \| \| [TinyLlama-1.1B-step-50K-105b.Q3_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q3_K.gguf) \| Q3_K \| 0.51GB \| \| [TinyLlama-1.1B-step-50K-105b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q3_K_M.gguf) \| Q3_K_M \| 0.51GB \| \| [TinyLlama-1.1B-step-50K-105b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q3_K_L.gguf) \| Q3_K_L \| 0.55GB \| \| [TinyLlama-1.1B-step-50K-105b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ4_XS.gguf) \| IQ4_XS \| 0.57GB \| \| [TinyLlama-1.1B-step-50K-105b.Q4_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_0.gguf) \| Q4_0 \| 0.59GB \| \| [TinyLlama-1.1B-step-50K-105b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ4_NL.gguf) \| IQ4_NL \| 0.6GB \| \| [TinyLlama-1.1B-step-50K-105b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_K_S.gguf) \| Q4_K_S \| 0.6GB \| \| [TinyLlama-1.1B-step-50K-105b.Q4_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_K.gguf) \| Q4_K \| 0.62GB \| \| [TinyLlama-1.1B-step-50K-105b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_K_M.gguf) \| Q4_K_M \| 0.62GB \| \| [TinyLlama-1.1B-step-50K-105b.Q4_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_1.gguf) \| Q4_1 \| 0.65GB \| \| [TinyLlama-1.1B-step-50K-105b.Q5_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_0.gguf) \| Q5_0 \| 0.71GB \| \| [TinyLlama-1.1B-step-50K-105b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_K_S.gguf) \| Q5_K_S \| 0.71GB \| \| [TinyLlama-1.1B-step-50K-105b.Q5_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_K.gguf) \| Q5_K \| 0.73GB \| \| [TinyLlama-1.1B-step-50K-105b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_K_M.gguf) \| Q5_K_M \| 0.73GB \| \| [TinyLlama-1.1B-step-50K-105b.Q5_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_1.gguf) \| Q5_1 \| 0.77GB \| \| [TinyLlama-1.1B-step-50K-105b.Q6_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q6_K.gguf) \| Q6_K \| 0.84GB \| \| [TinyLlama-1.1B-step-50K-105b.Q8_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q8_0.gguf) \| Q8_0 \| 1.09GB \| Original model description: --- license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata language: - en --- <div align="center"> # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. <div align="center"> <img src="./TinyLlama_logo.png" width="300"/> </div> We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Model This is an intermediate checkpoint with 50K steps and 105B tokens. #### Releases Schedule We will be rolling out intermediate checkpoints following the below schedule. We also include some baseline models for comparison. \| Date \| HF Checkpoint \| Tokens \| Step \| HellaSwag Acc_norm \| \|------------\|-------------------------------------------------\|--------\|------\|---------------------\| \| Baseline \| [StableLM-Alpha-3B](https://huggingface.co/stabilityai/stablelm-base-alpha-3b)\| 800B \| -- \| 38.31 \| \| Baseline \| [Pythia-1B-intermediate-step-50k-105b](https://huggingface.co/EleutherAI/pythia-1b/tree/step50000) \| 105B \| 50k \| 42.04 \| \| Baseline \| [Pythia-1B](https://huggingface.co/EleutherAI/pythia-1b) \| 300B \| 143k \| 47.16 \| \| 2023-09-04 \| [TinyLlama-1.1B-intermediate-step-50k-105b](https://huggingface.co/PY007/TinyLlama-1.1B-step-50K-105b) \| 105B \| 50k \| 43.50 \| \| 2023-09-16 \| -- \| 500B \| -- \| -- \| \| 2023-10-01 \| -- \| 1T \| -- \| -- \| \| 2023-10-16 \| -- \| 1.5T \| -- \| -- \| \| 2023-10-31 \| -- \| 2T \| -- \| -- \| \| 2023-11-15 \| -- \| 2.5T \| -- \| -- \| \| 2023-12-01 \| -- \| 3T \| -- \| -- \| #### How to use You will need the transformers>=4.31 Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information. ``` from transformers import AutoTokenizer import transformers import torch model = "PY007/TinyLlama-1.1B-step-50K-105b" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( 'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.', do_sample=True, top_k=10, num_return_sequences=1, repetition_penalty=1.5, eos_token_id=tokenizer.eos_token_id, max_length=500, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ```
robertgshaw2/zephyr-7b-beta-channelwise-marlin	robertgshaw2	"2024-02-18T18:51:23Z"	2,610	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]	text-generation	"2024-02-18T18:49:57Z"	Entry not found
NikolayKozloff/xTower13B-Q5_K_M-GGUF	NikolayKozloff	"2024-06-27T17:20:12Z"	2,610	1	null	[ "gguf", "llama-cpp", "gguf-my-repo", "translation", "en", "de", "zh", "ru", "he", "fr", "pt", "nl", "ko", "it", "es", "dataset:Unbabel/TowerBlocks-v0.1", "base_model:sardinelab/xTower13B", "license:cc-by-nc-4.0", "region:us" ]	translation	"2024-06-27T17:19:33Z"	--- base_model: sardinelab/xTower13B datasets: - Unbabel/TowerBlocks-v0.1 language: - en - de - zh - ru - he - fr - pt - nl - ko - it - es license: cc-by-nc-4.0 metrics: - comet pipeline_tag: translation tags: - llama-cpp - gguf-my-repo --- # NikolayKozloff/xTower13B-Q5_K_M-GGUF This model was converted to GGUF format from [`sardinelab/xTower13B`](https://huggingface.co/sardinelab/xTower13B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/sardinelab/xTower13B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo NikolayKozloff/xTower13B-Q5_K_M-GGUF --hf-file xtower13b-q5_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo NikolayKozloff/xTower13B-Q5_K_M-GGUF --hf-file xtower13b-q5_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo NikolayKozloff/xTower13B-Q5_K_M-GGUF --hf-file xtower13b-q5_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo NikolayKozloff/xTower13B-Q5_K_M-GGUF --hf-file xtower13b-q5_k_m.gguf -c 2048 ```
QuantFactory/visocial-Sailor-1.8B-Instruct-GGUF	QuantFactory	"2024-07-02T06:44:22Z"	2,610	0	null	[ "gguf", "region:us" ]	null	"2024-07-02T06:34:40Z"	Entry not found
kykim/albert-kor-base	kykim	"2021-01-22T00:27:49Z"	2,609	4	transformers	[ "transformers", "pytorch", "tf", "albert", "fill-mask", "ko", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	"2022-03-02T23:29:05Z"	--- language: ko --- # Albert base model for Korean * 70GB Korean text dataset and 42000 lower-cased subwords are used * Check the model performance and other language models for Korean in [github](https://github.com/kiyoungkim1/LM-kor) ```python from transformers import BertTokenizerFast, AlbertModel tokenizer_albert = BertTokenizerFast.from_pretrained("kykim/albert-kor-base") model_albert = AlbertModel.from_pretrained("kykim/albert-kor-base") ```
RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf	RichardErkhov	"2024-06-22T23:23:38Z"	2,608	0	null	[ "gguf", "region:us" ]	null	"2024-06-22T19:05:11Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Tiny-Vicuna-1B - GGUF - Model creator: https://huggingface.co/Jiayi-Pan/ - Original model: https://huggingface.co/Jiayi-Pan/Tiny-Vicuna-1B/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Tiny-Vicuna-1B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q2_K.gguf) \| Q2_K \| 0.4GB \| \| [Tiny-Vicuna-1B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ3_XS.gguf) \| IQ3_XS \| 0.44GB \| \| [Tiny-Vicuna-1B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ3_S.gguf) \| IQ3_S \| 0.47GB \| \| [Tiny-Vicuna-1B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q3_K_S.gguf) \| Q3_K_S \| 0.47GB \| \| [Tiny-Vicuna-1B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ3_M.gguf) \| IQ3_M \| 0.48GB \| \| [Tiny-Vicuna-1B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q3_K.gguf) \| Q3_K \| 0.51GB \| \| [Tiny-Vicuna-1B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q3_K_M.gguf) \| Q3_K_M \| 0.51GB \| \| [Tiny-Vicuna-1B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q3_K_L.gguf) \| Q3_K_L \| 0.55GB \| \| [Tiny-Vicuna-1B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ4_XS.gguf) \| IQ4_XS \| 0.57GB \| \| [Tiny-Vicuna-1B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_0.gguf) \| Q4_0 \| 0.59GB \| \| [Tiny-Vicuna-1B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ4_NL.gguf) \| IQ4_NL \| 0.6GB \| \| [Tiny-Vicuna-1B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_K_S.gguf) \| Q4_K_S \| 0.6GB \| \| [Tiny-Vicuna-1B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_K.gguf) \| Q4_K \| 0.62GB \| \| [Tiny-Vicuna-1B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_K_M.gguf) \| Q4_K_M \| 0.62GB \| \| [Tiny-Vicuna-1B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_1.gguf) \| Q4_1 \| 0.65GB \| \| [Tiny-Vicuna-1B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_0.gguf) \| Q5_0 \| 0.71GB \| \| [Tiny-Vicuna-1B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_K_S.gguf) \| Q5_K_S \| 0.71GB \| \| [Tiny-Vicuna-1B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_K.gguf) \| Q5_K \| 0.73GB \| \| [Tiny-Vicuna-1B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_K_M.gguf) \| Q5_K_M \| 0.73GB \| \| [Tiny-Vicuna-1B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_1.gguf) \| Q5_1 \| 0.77GB \| \| [Tiny-Vicuna-1B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q6_K.gguf) \| Q6_K \| 0.84GB \| \| [Tiny-Vicuna-1B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q8_0.gguf) \| Q8_0 \| 1.09GB \| Original model description: --- language: - en license: apache-2.0 model-index: - name: Tiny-Vicuna-1B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 33.45 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 55.92 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 25.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 33.82 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 58.41 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 1.52 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard --- # Tiny Vicuna 1B This model is a fine-tuned version of [TinyLlama](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T) on [WizardVicuna Dataset](https://github.com/melodysdreamj/WizardVicunaLM). It should be fully compatible with Vicuna-v1.5 series. This model is easy to iterate on for early experiments! # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Jiayi-Pan__Tiny-Vicuna-1B) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|34.76\| \|AI2 Reasoning Challenge (25-Shot)\|33.45\| \|HellaSwag (10-Shot) \|55.92\| \|MMLU (5-Shot) \|25.45\| \|TruthfulQA (0-shot) \|33.82\| \|Winogrande (5-shot) \|58.41\| \|GSM8k (5-shot) \| 1.52\|
timm/pit_s_distilled_224.in1k	timm	"2023-04-26T00:08:18Z"	2,607	0	timm	[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-1k", "arxiv:2103.16302", "license:apache-2.0", "region:us" ]	image-classification	"2023-04-26T00:07:57Z"	--- tags: - image-classification - timm library_name: timm license: apache-2.0 datasets: - imagenet-1k --- # Model card for pit_s_distilled_224.in1k A PiT (Pooling based Vision Transformer) image classification model. Trained on ImageNet-1k with token based distillation by paper authors. ## Model Details - Model Type: Image classification / feature backbone - Model Stats: - Params (M): 24.0 - GMACs: 2.9 - Activations (M): 11.6 - Image size: 224 x 224 - Papers: - Rethinking Spatial Dimensions of Vision Transformers: https://arxiv.org/abs/2103.16302 - Dataset: ImageNet-1k - Original: https://github.com/naver-ai/pit ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('pit_s_distilled_224.in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(*data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'pit_s_distilled_224.in1k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 144, 27, 27]) # torch.Size([1, 288, 14, 14]) # torch.Size([1, 576, 7, 7]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'pit_s_distilled_224.in1k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 2, 576) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Model Comparison Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results). ## Citation ```bibtex @inproceedings{heo2021pit, title={Rethinking Spatial Dimensions of Vision Transformers}, author={Byeongho Heo and Sangdoo Yun and Dongyoon Han and Sanghyuk Chun and Junsuk Choe and Seong Joon Oh}, booktitle = {International Conference on Computer Vision (ICCV)}, year={2021}, } ```
almanach/camembert-bio-base	almanach	"2024-06-24T09:29:00Z"	2,605	16	transformers	[ "transformers", "pytorch", "tf", "safetensors", "camembert", "fill-mask", "biomedical", "clinical", "life sciences", "fr", "dataset:rntc/biomed-fr", "doi:10.57967/hf/0586", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	"2023-02-23T15:03:44Z"	--- language: - fr license: mit library_name: transformers tags: - biomedical - clinical - life sciences datasets: - rntc/biomed-fr pipeline_tag: fill-mask widget: - text: Les médicaments <mask> typiques sont largement utilisés dans le traitement de première intention des patients schizophrènes. --- <a href=https://camembert-bio-model.fr/> <img width="300px" src="https://www.camembert-bio-model.fr/authors/camembert-bio/avatar_hu793b92579abd63a955d3004af578ed96_116953_270x270_fill_lanczos_center_3.png"> </a> # CamemBERT-bio : a Tasty French Language Model Better for your Health CamemBERT-bio is a state-of-the-art french biomedical language model built using continual-pretraining from [camembert-base](https://huggingface.co/camembert-base). It was trained on a french public biomedical corpus of 413M words containing scientific documents, drug leaflets and clinical cases extrated from theses and articles. It shows 2.54 points of F1 score improvement on average on 5 different biomedical named entity recognition tasks compared to [camembert-base](https://huggingface.co/camembert-base). ## Absract Clinical data in hospitals are increasingly accessible for research through clinical data warehouses, however these documents are unstructured. It is therefore necessary to extract information from medical reports to conduct clinical studies. Transfer learning with BERT-like models such as CamemBERT has allowed major advances, especially for named entity recognition. However, these models are trained for plain language and are less efficient on biomedical data. This is why we propose a new french public biomedical dataset on which we have continued the pre-training of CamemBERT. Thus, we introduce a first version of CamemBERT-bio, a specialized public model for the french biomedical domain that shows 2.54 points of F1 score improvement on average on different biomedical named entity recognition tasks. - Developed by: [Rian Touchent](https://rian-t.github.io), [Eric Villemonte de La Clergerie](http://pauillac.inria.fr/~clerger/) - Logo by: [Alix Chagué](https://alix-tz.github.io) - License: MIT <!-- ### Model Sources [optional] --> <!-- Provide the basic links for the model. --> <!-- - Website: camembert-bio-model.fr --> <!-- - Paper [optional]: [More Information Needed] --> <!-- - Demo [optional]: [More Information Needed] --> ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> \| Corpus \| Details \| Size \| \|------------\|--------------------------------------------------------------------\|------------\| \| ISTEX \| diverse scientific literature indexed on ISTEX \| 276 M \| \| CLEAR \| drug leaflets \| 73 M \| \| E3C \| various documents from journals, drug leaflets, and clinical cases \| 64 M \| \| Total \| \| 413 M \| ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> We used continual-pretraining from [camembert-base](https://huggingface.co/camembert-base). We trained the model using the Masked Language Modeling (MLM) objective with Whole Word Masking for 50k steps during 39 hours with 2 Tesla V100. ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Fine-tuning For fine-tuning, we utilized Optuna to select the hyperparameters. The learning rate was set to 5e-5, with a warmup ratio of 0.224 and a batch size of 16. The fine-tuning process was carried out for 2000 steps. For prediction, a simple linear layer was added on top of the model. Notably, none of the CamemBERT layers were frozen during the fine-tuning process. ### Scoring To evaluate the performance of the model, we used the seqeval tool in strict mode with the IOB2 scheme. For each evaluation, the best fine-tuned model on the validation set was selected to calculate the final score on the test set. To ensure reliability, we averaged over 10 evaluations with different seeds. ### Results \| Style \| Dataset \| Score \| CamemBERT \| CamemBERT-bio \| \| :----------- \| :------ \| :---- \| :---------------: \| :-------------------: \| \| Clinical \| CAS1 \| F1 \| 70\.50 ~~±~~ 1.75 \| 73\.03 ~~±~~ 1.29 \| \| \| \| P \| 70\.12 ~~±~~ 1.93 \| 71\.71 ~~±~~ 1.61 \| \| \| \| R \| 70\.89 ~~±~~ 1.78 \| 74\.42 ~~±~~ 1.49 \| \| \| CAS2 \| F1 \| 79\.02 ~~±~~ 0.92 \| 81\.66 ~~±~~ 0.59 \| \| \| \| P \| 77\.3 ~~±~~ 1.36 \| 80\.96 ~~±~~ 0.91 \| \| \| \| R \| 80\.83 ~~±~~ 0.96 \| 82\.37 ~~±~~ 0.69 \| \| \| E3C \| F1 \| 67\.63 ~~±~~ 1.45 \| 69\.85 ~~±~~ 1.58 \| \| \| \| P \| 78\.19 ~~±~~ 0.72 \| 79\.11 ~~±~~ 0.42 \| \| \| \| R \| 59\.61 ~~±~~ 2.25 \| 62\.56 ~~±~~ 2.50 \| \| Drug leaflets \| EMEA \| F1 \| 74\.14 ~~±~~ 1.95 \| 76\.71 ~~±~~ 1.50 \| \| \| \| P \| 74\.62 ~~±~~ 1.97 \| 76\.92 ~~±~~ 1.96 \| \| \| \| R \| 73\.68 ~~±~~ 2.22 \| 76\.52 ~~±~~ 1.62 \| \| Scientific \| MEDLINE \| F1 \| 65\.73 ~~±~~ 0.40 \| 68\.47 ~~±~~ 0.54 \| \| \| \| P \| 64\.94 ~~±~~ 0.82 \| 67\.77 ~~±~~ 0.88 \| \| \| \| R \| 66\.56 ~~±~~ 0.56 \| 69\.21 ~~±~~ 1.32 \| ## Environmental Impact estimation <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> - Hardware Type: 2 x Tesla V100 - Hours used: 39 hours - Provider: INRIA clusters - Compute Region: Paris, France - Carbon Emitted: 0.84 kg CO2 eq. <!-- ## Citation [optional] --> <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> <!-- BibTeX: --> ## Citation information ```bibtex @inproceedings{touchent-de-la-clergerie-2024-camembert-bio, title = "{C}amem{BERT}-bio: Leveraging Continual Pre-training for Cost-Effective Models on {F}rench Biomedical Data", author = "Touchent, Rian and de la Clergerie, {\'E}ric", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://aclanthology.org/2024.lrec-main.241", pages = "2692--2701", abstract = "Clinical data in hospitals are increasingly accessible for research through clinical data warehouses. However these documents are unstructured and it is therefore necessary to extract information from medical reports to conduct clinical studies. Transfer learning with BERT-like models such as CamemBERT has allowed major advances for French, especially for named entity recognition. However, these models are trained for plain language and are less efficient on biomedical data. Addressing this gap, we introduce CamemBERT-bio, a dedicated French biomedical model derived from a new public French biomedical dataset. Through continual pre-training of the original CamemBERT, CamemBERT-bio achieves an improvement of 2.54 points of F1-score on average across various biomedical named entity recognition tasks, reinforcing the potential of continual pre-training as an equally proficient yet less computationally intensive alternative to training from scratch. Additionally, we highlight the importance of using a standard evaluation protocol that provides a clear view of the current state-of-the-art for French biomedical models.", } @inproceedings{touchent:hal-04130187, TITLE = {{CamemBERT-bio : Un mod{\`e}le de langue fran{\c c}ais savoureux et meilleur pour la sant{\'e}}}, AUTHOR = {Touchent, Rian and Romary, Laurent and De La Clergerie, Eric}, URL = {https://hal.science/hal-04130187}, BOOKTITLE = {{18e Conf{\'e}rence en Recherche d'Information et Applications \\ 16e Rencontres Jeunes Chercheurs en RI \\ 30e Conf{\'e}rence sur le Traitement Automatique des Langues Naturelles \\ 25e Rencontre des {\'E}tudiants Chercheurs en Informatique pour le Traitement Automatique des Langues}}, ADDRESS = {Paris, France}, EDITOR = {Servan, Christophe and Vilnat, Anne}, PUBLISHER = {{ATALA}}, PAGES = {323-334}, YEAR = {2023}, KEYWORDS = {comptes rendus m{\'e}dicaux ; TAL clinique ; CamemBERT ; extraction d'information ; biom{\'e}dical ; reconnaissance d'entit{\'e}s nomm{\'e}es}, HAL_ID = {hal-04130187}, HAL_VERSION = {v1}, } ``` <!-- [More Information Needed] --> <!-- APA: --> <!-- [More Information Needed] -->
Backedman/TriviaAnsweringMachineREAL	Backedman	"2024-05-12T22:28:55Z"	2,605	0	transformers	[ "transformers", "pytorch", "TFIDF-QA", "question-answering", "custom_code", "en", "license:mit", "region:us" ]	question-answering	"2024-05-07T01:04:47Z"	--- language: - en license: mit pipeline_tag: question-answering --- The evaluation of this project is to answer trivia questions. You do not need to do well at this task, but you should submit a system that completes the task or create adversarial questions in that setting. This will help the whole class share data and resources. If you focus on something other than predicting answers, that's fine! About the Data ============== Quiz bowl is an academic competition between schools in English-speaking countries; hundreds of teams compete in dozens of tournaments each year. Quiz bowl is different from Jeopardy, a recent application area. While Jeopardy also uses signaling devices, these are only usable after a question is completed (interrupting Jeopardy's questions would make for bad television). Thus, Jeopardy is rapacious classification followed by a race---among those who know the answer---to punch a button first. Here's an example of a quiz bowl question: Expanding on a 1908 paper by Smoluchowski, he derived a formula for the intensity of scattered light in media fluctuating densities that reduces to Rayleigh's law for ideal gases in The Theory of the Opalescence of Homogenous Fluids and Liquid Mixtures near the Critical State. That research supported his theories of matter first developed when he calculated the diffusion constant in terms of fundamental parameters of the particles of a gas undergoing Brownian Motion. In that same year, 1905, he also published On a Heuristic Point of View Concerning the Production and Transformation of Light. That explication of the photoelectric effect won him 1921 Nobel in Physics. For ten points, name this German physicist best known for his theory of Relativity. ANSWER: Albert _Einstein_ Two teams listen to the same question. Teams interrupt the question at any point by "buzzing in"; if the answer is correct, the team gets points and the next question is read. Otherwise, the team loses points and the other team can answer. You are welcome to use any automatic method to choose an answer. It need not be similar nor build on our provided systems. In addition to the data we provide, you are welcome to use any external data except our test quiz bowl questions (i.e., don't hack our server!). You are welcome (an encouraged) to use any publicly available software, but you may want to check on Piazza for suggestions as many tools are better (or easier to use) than others. If you don't like the interruptability of questions, you can also just answer entire questions. However, you must also output a confidence. Competition ================== We will use Dynabech website (https://dynabench.org/tasks/qa). If you remember the past workshop about Dynabench submission, this is the way to do it. The specific task name is "Grounded QA". Here, with the help of the video tutorial, you submit your QA model and assess how your QA model did compared to others. The assessment will take place by testing your QA model on several QA test datasets and the results of yours and your competitors will be visible on the leaderboard. Your goal is to rank the highest in terms of expected wins: you buzz in with probability proportional to your confidence, and if you're more right than the competition, you win. Writing Questions ================== Alternatively, you can also write 50 adversarial questions that challenge modern NLP systems. These questions must be diverse in the subjects asked about, the skills computers need to answer the questions, and the entities in those questions. Remember that your questions should be factual and specific enough for humans to answer, because your task is to stump the computers relative to humans! In addition to the raw questions, you will also need to create citations describing: * Why the question is difficult for computers: include citations from the NLP/AI/ML literature * Why the information in the question is correct: include citations from the sources you drew on the write the question * Why the question is interesting: include scholarly / popular culture artifacts to prove that people care about this * Why the question is pyramidal: discuss why your first clues are harder than your later clues Category We want questions from many domains such as Art, Literature, Geography, History, Science, TV and Film, Music, Lifestyle, and Sport. The questions should be written using all topics above (5 questions for each category and 5 more for the remaining categories). Indicate in your writeup which category you chose to write on for each question. Art: * Questions about works: Mona Lisa, Raft of the Medussa * Questions about forms: color, contour, texture * Questions about artists: Picasso, Monet, Leonardo da Vinci * Questions about context: Renaissance, post-modernism, expressionism, surrealism Literature: * Questions about works: novels (1984), plays (The Lion and the Jewel), poems (Rubaiyat), criticism (Poetics) * Questions about major characters or events in literature: The Death of Anna Karenina, Noboru Wataya, the Marriage of Hippolyta and Theseus * Questions about literary movements (Sturm und Drang) * Questions about translations * Cross-cutting questions (appearances of Overcoats in novels) * Common link questions (the literary output of a country/region) Geography: * Questions about location: names of capital, state, river * Questions about the place: temperature, wind flow, humidity History: * When: When did the First World war start? * Who: Who is called Napoleon of Iran? * Where: Where was the first Summer Olympics held? * Which: Which is the oldest civilization in the world? Science: * Questions about terminology: The concept of gravity was discovered by which famous physicist? * Questions about the experiment * Questions about theory: The social action theory believes that individuals are influenced by this theory. TV and Film: * Quotes: What are the dying words of Charles Foster Kane in Citizen Kane? * Title: What 1927 musical was the first "talkie"? * Plot: In The Matrix, does Neo take the blue pill or the red pill? Music: * Singer: What singer has had a Billboard No. 1 hit in each of the last four decades? * Band: Before Bleachers and fun., Jack Antonoff fronted what band? * Title: What was Madonna's first top 10 hit? * History: Which classical composer was deaf? Lifestyle: * Clothes: What clothing company, founded by a tennis player, has an alligator logo? * Decoration: What was the first perfume sold by Coco Chanel? Sport: * Known facts: What sport is best known as the ‘king of sports’? * Nationality: What’s the national sport of Canada? * Sport player: The classic 1980 movie called Raging Bull is about which real-life boxer? * Country: What country has competed the most times in the Summer Olympics yet hasn’t won any kind of medal? Diversity Other than category diversity, if you find an ingenious way of writing questions about underrepresented countries, you will get bonus points (indicate which questions you included the diversity component in your writeup). You may decide which are underrepresented countries with your own reasonable reason (etc., less population may indicate underrepresented), but make sure to articulate this in your writeup. * Run state of the art QA systems on the questions to show they struggle, give individual results for each question and a summary over all questions For an example of what the writeup for a single question should look like, see the adversarial HW: https://github.com/Pinafore/nlp-hw/blob/master/adversarial/question.tex Proposal ================== The project proposal is a one page PDF document that describes: * Who is on your team (team sizes can be between three and six students, but six is really too big to be effective; my suggestion is that most groups should be between four or five). * What techniques you will explore * Your timeline for completing the project (be realistic; you should have your first submission in a week or two) Submit the proposal on Gradescope, but make sure to include all group members. If all group members are not included, you will lose points. Late days cannot be used on this assignment. Milestone 1 ====================== You'll have to update how things are going: what's working, what isn't, and how does it change your timeline? How does it change your division of labor? Question Writing: You'll need to have answers selected for all of your questions and first drafts of at least 15 questions. This must be submitted as a JSON file so that we run computer QA systems on it. Project: You'll need to have made a submission to the leaderboard with something that satisfies the API. Submit a PDF updating on your progress to Gradescope. If all team members are not on the submission, you will lose points. Milestone 2 =================== As before, provide an updated timeline / division of labor, provide your intermediary results. Question Writing: You'll need to have reflected the feedback from the first questions and completed a first draft of at least 30 questions. You'll also need machine results to your questions and an overall evaluation of your human/computer accuracy. Project: You'll need to have a made a submission to the leaderboard with a working system (e.g., not just obey the API, but actually get reasonable answers). Submit a PDF updating on your progress. Final Presentation ====================== The final presentation will be virtual (uploading a video). In the final presentation you will: * Explain what you did * Who did what. For example, for the question writing project a team of five people might write: A wrote the first draft of questions. B and C verified they were initially answerable by a human. B ran computer systems to verify they were challenging to a computer. C edited the questions and increased the computer difficulty. D and E verified that the edited questions were still answerable by a human. D and E checked all of the questions for factual accuracy and created citations and the writeup. * What challenges you had * Review how well you did (based on the competition or your own metrics). If you do not use the course infrastructure to evaluate your project's work, you should talk about what alternative evaluations you used, why they're appropriate/fair, and how well you did on them. * Provide an error analysis. An error analysis must contain examples from the development set that you get wrong. You should show those sentences and explain why (in terms of features or the model) they have the wrong answer. You should have been doing this all along as you derive new features, but this is your final inspection of your errors. The feature or model problems you discover should not be trivial features you could add easily. Instead, these should be features or models that are difficult to correct. An error analysis is not the same thing as simply presenting the error matrix, as it does not inspect any individual examples. If you're writing questions, talk about examples of questions that didn't work out as intended. * The linguistic motivation for your features / how your wrote the questions. This is a computational linguistics class, so you should give precedence to features / techniques that we use in this class (e.g., syntax, morphology, part of speech, word sense, etc.). Given two features that work equally well and one that is linguistically motivated, we'll prefer the linguistically motivated one. * Presumably you did many different things; how did they each individually contribute to your final result? Each group has 10 minutes to deliver their presentation. Please record the video, and upload it to Google Drive, and include the link in your writeup submission. Final Question Submission ====================== Because we need to get the questions ready for the systems, upload your raw questions on May 10. This doesn't include the citations or other parts of the writeup. System Submission ====================== You must submit a version of your system by May 12. It may not be perfect, but this what the question writing teams will use to test their results. Your system should be sent directly to the professor and TAs in zip files, including the correct dependencies and a working inference code. Your inference code should run successfully in the root folder (extracted from zip folder) directory with the command: ``` > python3 inference.py --data=evaluation_set.json ``` The input will be in the form of a .json file () in the same format as the file the adversarial question writing team submits. The output format should also be in string. If you have any notes or comments that we should be aware of while running your code, please include them in the folder as a .txt file. Also, dependency information should be included as a .txt file. Please prepend your email title with [2024-CMSC 470 System Submission]. Project Writeup and JSON file ====================== By May 17, submit your project writeup explaining what you did and what results you achieved. This document should make it clear: * Why this is a good idea * What you did * Who did what * Whether your technique worked or not For systems, please do not go over 2500 words unless you have a really good reason. Images are a much better use of space than words, usually (there's no limit on including images, but use judgement and be selective). For question writing, you have one page (single spaced, two column) per question plus a two page summary of results. Talk about how you organized the question writing, how you evaluated the questions, and a summary of the results. Along with your writeup, turn in a json including the raw text of the question and answer and category. The json file is included in this directory. Make sure your json file is in the correct format and is callable via below code. Your submission will not be graded if it does not follow the format of the example json file. ``` with open('path to your json file', 'r') as f: data = json.load(f) ``` Grade ====================== The grade will be out of 25 points, broken into five areas: * _Presentation_: For your oral presentation, do you highlight what you did and make people care? Did you use time well during the presentation? * _Writeup_: Does the writeup explain what you did in a way that is clear and effective? The final three areas are different between the system and the questions. \| \| System \| Questions \| \|----------\|:-------------:\|------:\| \| _Technical Soundness_ \| Did you use the right tools for the job, and did you use them correctly? Were they relevant to this class? \| Were your questions correct and accurately cited. \| \| _Effort_ \| Did you do what you say you would, and was it the right ammount of effort. \| Are the questions well-written, interesting, and thoroughly edited? \| \| _Performance_ \| How did your techniques perform in terms of accuracy, recall, etc.? \| Is the human accuracy substantially higher than the computer accuracy? \| All members of the group will receive the same grade. It's impossible for the course staff to adjudicate Rashomon-style accounts of who did what, and the goal of a group project is for all team members to work together to create a cohesive project that works well together. While it makes sense to divide the work into distinct areas of responsibility, at grading time we have now way to know who really did what, so it's the groups responsibility to create a piece of output that reflects well on the whole group.
Timoschi/Meta-Llama-3-8B-Q8_0-GGUF	Timoschi	"2024-06-23T19:53:21Z"	2,605	0	null	[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:meta-llama/Meta-Llama-3-8B", "license:llama3", "region:us" ]	text-generation	"2024-06-23T19:52:44Z"	--- base_model: meta-llama/Meta-Llama-3-8B language: - en license: llama3 pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-3 - llama-cpp - gguf-my-repo extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\ \ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\ \ use, reproduction, distribution and modification of the Llama Materials set forth\ \ herein.\n\"Documentation\" means the specifications, manuals and documentation\ \ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\ \ (if you are entering into this Agreement on such person or entity’s behalf), of\ \ the age required under applicable laws, rules or regulations to provide legal\ \ consent and that has legal authority to bind your employer or such other person\ \ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\ \ 3\" means the foundational large language models and software and algorithms,\ \ including machine-learning model code, trained model weights, inference-enabling\ \ code, training-enabling code, fine-tuning enabling code and other elements of\ \ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\ \"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\ \ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\ we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\ \ an entity, your principal place of business is in the EEA or Switzerland) and\ \ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\ \ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\ \ a non-exclusive, worldwide, non-transferable and royalty-free limited license\ \ under Meta’s intellectual property or other rights owned by Meta embodied in the\ \ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\ \ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\ \ If you distribute or make available the Llama Materials (or any derivative works\ \ thereof), or a product or service that uses any of them, including another AI\ \ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\ \ and (B) prominently display “Built with Meta Llama 3” on a related website, user\ \ interface, blogpost, about page, or product documentation. If you use the Llama\ \ Materials to create, train, fine tune, or otherwise improve an AI model, which\ \ is distributed or made available, you shall also include “Llama 3” at the beginning\ \ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\ \ works thereof, from a Licensee as part of an integrated end user product, then\ \ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\ \ copies of the Llama Materials that you distribute the following attribution notice\ \ within a “Notice” text file distributed as a part of such copies: “Meta Llama\ \ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\ \ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\ \ applicable laws and regulations (including trade compliance laws and regulations)\ \ and adhere to the Acceptable Use Policy for the Llama Materials (available at\ \ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\ \ into this Agreement.\nv. You will not use the Llama Materials or any output or\ \ results of the Llama Materials to improve any other large language model (excluding\ \ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\ \ on the Meta Llama 3 version release date, the monthly active users of the products\ \ or services made available by or for Licensee, or Licensee’s affiliates, is greater\ \ than 700 million monthly active users in the preceding calendar month, you must\ \ request a license from Meta, which Meta may grant to you in its sole discretion,\ \ and you are not authorized to exercise any of the rights under this Agreement\ \ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\ \ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\ \ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\ \ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\ \ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\ \ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\ \ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\ \ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\ 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\ \ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\ \ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\ \ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\ \ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\ 5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\ \ and in connection with the Llama Materials, neither Meta nor Licensee may use\ \ any name or mark owned by or associated with the other or any of its affiliates,\ \ except as required for reasonable and customary use in describing and redistributing\ \ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\ \ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\ \ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\ \ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\ \ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\ b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\ \ Meta, with respect to any derivative works and modifications of the Llama Materials\ \ that are made by you, as between you and Meta, you are and will be the owner of\ \ such derivative works and modifications.\nc. If you institute litigation or other\ \ proceedings against Meta or any entity (including a cross-claim or counterclaim\ \ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\ \ or any portion of any of the foregoing, constitutes infringement of intellectual\ \ property or other rights owned or licensable by you, then any licenses granted\ \ to you under this Agreement shall terminate as of the date such litigation or\ \ claim is filed or instituted. You will indemnify and hold harmless Meta from and\ \ against any claim by any third party arising out of or related to your use or\ \ distribution of the Llama Materials.\n6. Term and Termination. The term of this\ \ Agreement will commence upon your acceptance of this Agreement or access to the\ \ Llama Materials and will continue in full force and effect until terminated in\ \ accordance with the terms and conditions herein. Meta may terminate this Agreement\ \ if you are in breach of any term or condition of this Agreement. Upon termination\ \ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\ \ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\ \ and Jurisdiction. This Agreement will be governed and construed under the laws\ \ of the State of California without regard to choice of law principles, and the\ \ UN Convention on Contracts for the International Sale of Goods does not apply\ \ to this Agreement. The courts of California shall have exclusive jurisdiction\ \ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\ \ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\ \ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\ \ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\ #### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\ \ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\ \ illegal distribution of information or materials to minors, including obscene\ \ materials, or failure to employ legally required age-gating in connection with\ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\ \ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\ \ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\ \ or harmful conduct in the provision of employment, employment benefits, credit,\ \ housing, other economic benefits, or other essential goods and services\n 4.\ \ Engage in the unauthorized or unlicensed practice of any profession including,\ \ but not limited to, financial, legal, medical/health, or related professional\ \ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\ \ or other sensitive personal or private information about individuals without rights\ \ and consents required by applicable laws\n 6. Engage in or facilitate any action\ \ or generate any content that infringes, misappropriates, or otherwise violates\ \ any third-party rights, including the outputs or results of any products or services\ \ using the Llama Materials\n 7. Create, generate, or facilitate the creation\ \ of malicious code, malware, computer viruses or do anything else that could disable,\ \ overburden, interfere with or impair the proper working, integrity, operation\ \ or appearance of a website or computer system\n2. Engage in, promote, incite,\ \ facilitate, or assist in the planning or development of activities that present\ \ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\ \ espionage, use for materials or activities that are subject to the International\ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\ \ content intended to incite or promote violence, abuse, or any infliction of bodily\ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\ \ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\ \ or furthering defamatory content, including the creation of defamatory statements,\ \ images, or other content\n 3. Generating, promoting, or further distributing\ \ spam\n 4. Impersonating another individual without consent, authorization,\ \ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\ \ human-generated\n 6. Generating or facilitating false online engagement, including\ \ fake reviews and other means of fake online engagement\n4. Fail to appropriately\ \ disclose to end users any known dangers of your AI system\nPlease report any violation\ \ of this Policy, software “bug,” or other problems that could lead to a violation\ \ of this Policy through one of the following means:\n * Reporting issues with\ \ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\ \ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\ \ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\ \ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]" extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text geo: ip_location ? By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy : checkbox extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit --- # Timoschi/Meta-Llama-3-8B-Q8_0-GGUF This model was converted to GGUF format from [`meta-llama/Meta-Llama-3-8B`](https://huggingface.co/meta-llama/Meta-Llama-3-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-8B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Timoschi/Meta-Llama-3-8B-Q8_0-GGUF --hf-file meta-llama-3-8b-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Timoschi/Meta-Llama-3-8B-Q8_0-GGUF --hf-file meta-llama-3-8b-q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Timoschi/Meta-Llama-3-8B-Q8_0-GGUF --hf-file meta-llama-3-8b-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Timoschi/Meta-Llama-3-8B-Q8_0-GGUF --hf-file meta-llama-3-8b-q8_0.gguf -c 2048 ```
microsoft/layoutlmv2-large-uncased	microsoft	"2022-09-16T03:40:36Z"	2,604	8	transformers	[ "transformers", "pytorch", "layoutlmv2", "en", "arxiv:2012.14740", "license:cc-by-nc-sa-4.0", "endpoints_compatible", "region:us" ]	null	"2022-03-02T23:29:05Z"	--- language: en license: cc-by-nc-sa-4.0 --- # LayoutLMv2 Multimodal (text + layout/format + image) pre-training for document AI ## Introduction LayoutLMv2 is an improved version of LayoutLM with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. It outperforms strong baselines and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including , including FUNSD (0.7895 → 0.8420), CORD (0.9493 → 0.9601), SROIE (0.9524 → 0.9781), Kleister-NDA (0.834 → 0.852), RVL-CDIP (0.9443 → 0.9564), and DocVQA (0.7295 → 0.8672). [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://arxiv.org/abs/2012.14740) Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou, [ACL 2021](#)
mradermacher/Dr.RP.Samantha-L3-8B-GGUF	mradermacher	"2024-06-16T04:07:05Z"	2,604	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:WesPro/Dr.RP.Samantha-L3-8B", "endpoints_compatible", "region:us" ]	null	"2024-06-15T20:56:40Z"	--- base_model: WesPro/Dr.RP.Samantha-L3-8B language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/WesPro/Dr.RP.Samantha-L3-8B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
facebook/convnextv2-base-1k-224	facebook	"2023-02-20T13:00:30Z"	2,603	2	transformers	[ "transformers", "pytorch", "convnextv2", "image-classification", "vision", "dataset:imagenet-1k", "arxiv:2301.00808", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	"2023-02-17T14:12:51Z"	--- license: apache-2.0 tags: - vision - image-classification datasets: - imagenet-1k widget: - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg example_title: Tiger - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg example_title: Teapot - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg example_title: Palace --- # ConvNeXt V2 (base-sized model) ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-1K dataset at resolution 224x224. It was introduced in the paper [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://arxiv.org/abs/2301.00808) by Woo et al. and first released in [this repository](https://github.com/facebookresearch/ConvNeXt-V2). Disclaimer: The team releasing ConvNeXT V2 did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description ConvNeXt V2 is a pure convolutional model (ConvNet) that introduces a fully convolutional masked autoencoder framework (FCMAE) and a new Global Response Normalization (GRN) layer to ConvNeXt. ConvNeXt V2 significantly improves the performance of pure ConvNets on various recognition benchmarks. ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/convnextv2_architecture.png) ## Intended uses & limitations You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=convnextv2) to look for fine-tuned versions on a task that interests you. ### How to use Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes: ```python from transformers import AutoImageProcessor, ConvNextV2ForImageClassification import torch from datasets import load_dataset dataset = load_dataset("huggingface/cats-image") image = dataset["test"]["image"][0] preprocessor = AutoImageProcessor.from_pretrained("facebook/convnextv2-base-1k-224") model = ConvNextV2ForImageClassification.from_pretrained("facebook/convnextv2-base-1k-224") inputs = preprocessor(image, return_tensors="pt") with torch.no_grad(): logits = model(**inputs).logits # model predicts one of the 1000 ImageNet classes predicted_label = logits.argmax(-1).item() print(model.config.id2label[predicted_label]), ``` For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/convnextv2). ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-2301-00808, author = {Sanghyun Woo and Shoubhik Debnath and Ronghang Hu and Xinlei Chen and Zhuang Liu and In So Kweon and Saining Xie}, title = {ConvNeXt {V2:} Co-designing and Scaling ConvNets with Masked Autoencoders}, journal = {CoRR}, volume = {abs/2301.00808}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.00808}, doi = {10.48550/arXiv.2301.00808}, eprinttype = {arXiv}, eprint = {2301.00808}, timestamp = {Tue, 10 Jan 2023 15:10:12 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-00808.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```
marella/gpt-2-ggml	marella	"2023-05-20T11:05:41Z"	2,603	11	ctransformers	[ "ctransformers", "gpt2", "license:mit", "region:us" ]	null	"2023-05-14T17:08:30Z"	--- license: mit library_name: ctransformers --- ```sh pip install ctransformers ``` ```py from ctransformers import AutoModelForCausalLM llm = AutoModelForCausalLM.from_pretrained('marella/gpt-2-ggml') print(llm('AI is going to')) ``` See https://github.com/marella/ctransformers
JuanMa360/room-classification	JuanMa360	"2023-12-08T07:32:42Z"	2,603	4	transformers	[ "transformers", "pytorch", "safetensors", "vit", "image-classification", "huggingpics", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	"2023-09-15T17:50:28Z"	--- tags: - image-classification - pytorch - huggingpics metrics: - accuracy model-index: - name: room-classification results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.8650000095367432 --- # room-classification House & Apartaments Classification model🤗🖼️ ## Example Images #### Exterior ![Exterior](images/Exterior.jpeg) #### closets ![closets](images/closets.jpg) #### kitchen ![kitchen](images/kitchen.jpeg) #### others ![others](images/others.jpg)
DiTy/cross-encoder-russian-msmarco	DiTy	"2024-05-15T18:57:43Z"	2,603	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "text-classification", "transformers", "rubert", "cross-encoder", "msmarco", "ru", "dataset:unicamp-dl/mmarco", "base_model:DeepPavlov/rubert-base-cased", "license:mit", "region:us" ]	text-classification	"2024-04-19T15:24:56Z"	--- language: - ru library_name: sentence-transformers tags: - sentence-transformers - text-classification - transformers - rubert - cross-encoder - msmarco datasets: - unicamp-dl/mmarco base_model: DeepPavlov/rubert-base-cased widget: - text: >- как часто нужно ходить к стоматологу? [SEP] Дядя Женя работает врачем стоматологом. example_title: Example 1 - text: >- как часто нужно ходить к стоматологу? [SEP] Минимальный обязательный срок посещения зубного врача – раз в год, но специалисты рекомендуют делать это чаще – раз в полгода, а ещё лучше – раз в квартал. При таком сроке легко отследить любые начинающиеся проблемы и исправить их сразу же. example_title: Example 2 license: mit --- # DiTy/cross-encoder-russian-msmarco This is a [sentence-transformers](https://www.SBERT.net) model based on a pre-trained [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) and finetuned with [MS-MARCO Russian passage ranking dataset](https://huggingface.co/datasets/unicamp-dl/mmarco). The model can be used for Information Retrieval in the Russian language: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import CrossEncoder reranker_model = CrossEncoder('DiTy/cross-encoder-russian-msmarco', max_length=512, device='cuda') query = ["как часто нужно ходить к стоматологу?"] documents = [ "Минимальный обязательный срок посещения зубного врача – раз в год, но специалисты рекомендуют делать это чаще – раз в полгода, а ещё лучше – раз в квартал. При таком сроке легко отследить любые начинающиеся проблемы и исправить их сразу же.", "Основная причина заключается в истончении поверхностного слоя зуба — эмали, которая защищает зуб от механических, химических и температурных воздействий. Под эмалью расположен дентин, который более мягкий по своей структуре и пронизан множеством канальцев. При повреждении эмали происходит оголение дентинных канальцев. Раздражение с них начинает передаваться на нервные окончания в зубе и возникают болевые ощущения. Чаще всего дентин оголяется в придесневой области зубов, поскольку эмаль там наиболее тонкая и стирается быстрее.", "Стоматолог, также известный как стоматолог-хирург, является медицинским работником, который специализируется на стоматологии, отрасли медицины, специализирующейся на зубах, деснах и полости рта.", "Дядя Женя работает врачем стоматологом", "Плоды малины употребляют как свежими, так и замороженными или используют для приготовления варенья, желе, мармелада, соков, а также ягодного пюре. Малиновые вина, наливки, настойки, ликёры обладают высокими вкусовыми качествами.", ] predict_result = reranker_model.predict([[query[0], documents[0]]]) print(predict_result) # `array([0.88126713], dtype=float32)` rank_result = reranker_model.rank(query[0], documents) print(rank_result) # `[{'corpus_id': 0, 'score': 0.88126713}, # {'corpus_id': 2, 'score': 0.001042091}, # {'corpus_id': 3, 'score': 0.0010417715}, # {'corpus_id': 1, 'score': 0.0010344835}, # {'corpus_id': 4, 'score': 0.0010244923}]` ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python import torch from transformers import AutoTokenizer, AutoModelForSequenceClassification model = AutoModelForSequenceClassification.from_pretrained('DiTy/cross-encoder-russian-msmarco') tokenizer = AutoTokenizer.from_pretrained('DiTy/cross-encoder-russian-msmarco') features = tokenizer(["как часто нужно ходить к стоматологу?", "как часто нужно ходить к стоматологу?"], ["Минимальный обязательный срок посещения зубного врача – раз в год, но специалисты рекомендуют делать это чаще – раз в полгода, а ещё лучше – раз в квартал. При таком сроке легко отследить любые начинающиеся проблемы и исправить их сразу же.", "Дядя Женя работает врачем стоматологом"], padding=True, truncation=True, return_tensors='pt') model.eval() with torch.no_grad(): scores = model(**features).logits print(scores) # `tensor([[ 1.6871], # [-6.8700]])` ```
timm/deit3_small_patch16_224.fb_in1k	timm	"2024-02-10T23:37:09Z"	2,601	0	timm	[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-1k", "arxiv:2204.07118", "license:apache-2.0", "region:us" ]	image-classification	"2023-03-28T01:26:30Z"	--- license: apache-2.0 library_name: timm tags: - image-classification - timm datasets: - imagenet-1k --- # Model card for deit3_small_patch16_224.fb_in1k A DeiT-III image classification model. Trained on ImageNet-1k by paper authors. ## Model Details - Model Type: Image classification / feature backbone - Model Stats: - Params (M): 22.1 - GMACs: 4.6 - Activations (M): 11.9 - Image size: 224 x 224 - Papers: - DeiT III: Revenge of the ViT: https://arxiv.org/abs/2204.07118 - Original: https://github.com/facebookresearch/deit - Dataset: ImageNet-1k ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('deit3_small_patch16_224.fb_in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(*data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) 100, k=5) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'deit3_small_patch16_224.fb_in1k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 197, 384) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Model Comparison Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results). ## Citation ```bibtex @article{Touvron2022DeiTIR, title={DeiT III: Revenge of the ViT}, author={Hugo Touvron and Matthieu Cord and Herve Jegou}, journal={arXiv preprint arXiv:2204.07118}, year={2022}, } ``` ```bibtex @misc{rw2019timm, author = {Ross Wightman}, title = {PyTorch Image Models}, year = {2019}, publisher = {GitHub}, journal = {GitHub repository}, doi = {10.5281/zenodo.4414861}, howpublished = {\url{https://github.com/huggingface/pytorch-image-models}} } ```
cactusfriend/nightmare-invokeai-prompts	cactusfriend	"2023-06-22T00:48:13Z"	2,600	6	transformers	[ "transformers", "pytorch", "safetensors", "gpt_neo", "text-generation", "license:openrail", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	"2023-04-02T15:30:11Z"	--- license: openrail pipeline_tag: text-generation library_name: transformers widget: - text: "a photograph of" example_title: "photo" - text: "a bizarre cg render" example_title: "render" - text: "the spaghetti" example_title: "meal?" - text: "a (detailed+ intricate)+ picture" example_title: "weights" - text: "photograph of various" example_title: "variety" inference: parameters: temperature: 2.6 max_new_tokens: 250 --- A model based upon the prompts of all the images in my InvokeAI's output directory, meant to be used with [InvokeAI](https://github.com/invoke-ai/InvokeAI) (a Stable Diffusion implementation/UI) to generate new, probably wild nightmare images. This is mostly trained on positive prompts, though you may catch some words in [] brackets, which will be treated as negative. GPT-Neo is usually quite good at pairing parenthesis, quotation marks, etc - however, don't be too surprised if it generates something that's not quite InvokeAI prompt syntax. To use this model, you can import it as a pipeline like so: ```py from transformers import pipeline generator = pipeline(model="cactusfriend/nightmare-invokeai-prompts", tokenizer="cactusfriend/nightmare-invokeai-prompts", task="text-generation") ``` Here's an example function that'll generate by default 20 prompts, at a temperature of 1.8 which seems good for this model. ```py def makePrompts(prompt: str, , p: float=0.9, k: int = 40, num: int = 20, temp: float = 1.8, mnt: int = 150): outputs = generator(prompt, max_new_tokens=mnt, temperature=temp, do_sample=True, top_p=p, top_k=k, num_return_sequences=num) items = set([i['generated_text'] for i in outputs]) print("-" 60) print("\n ---\n".join(items)) print("-" * 60) ``` Then, you can call it like so: ```py makePrompts("a photograph of") # or, to change some defaults: makePrompts("spaghetti all over", temp=1.4, p=0.92, k=45) ```
neuralmagic/Meta-Llama-3-8B-Instruct-FP8	neuralmagic	"2024-06-26T13:19:38Z"	2,599	4	transformers	[ "transformers", "safetensors", "llama", "text-generation", "fp8", "vllm", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2024-04-25T19:13:07Z"	--- tags: - fp8 - vllm --- # Meta-Llama-3-8B-Instruct-FP8 ## Model Overview Meta-Llama-3-8B-Instruct quantized to FP8 weights and activations using per-tensor quantization, ready for inference with vLLM >= 0.5.0. ## Usage and Creation Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py). ## Evaluation ### Open LLM Leaderboard evaluation scores \| \| Meta-Llama-3-8B-Instruct \| Meta-Llama-3-8B-Instruct-FP8<br>(this model) \| \| :------------------: \| :----------------------: \| :------------------------------------------------: \| \| arc-c<br>25-shot \| 62.54 \| 61.77 \| \| hellaswag<br>10-shot \| 78.83 \| 78.56 \| \| mmlu<br>5-shot \| 66.60 \| 66.27 \| \| truthfulqa<br>0-shot \| 52.44 \| 52.35 \| \| winogrande<br>5-shot \| 75.93 \| 76.4 \| \| gsm8k<br>5-shot \| 75.96 \| 73.99 \| \| Average<br>Accuracy \| 68.71 \| 68.22 \| \| Recovery \| 100% \| 99.28% \|
QuantFactory/Ahma-7B-GGUF	QuantFactory	"2024-06-09T02:42:23Z"	2,599	0	null	[ "gguf", "finnish", "llama", "conversational", "text-generation", "fi", "base_model:Finnish-NLP/Ahma-7B", "license:apache-2.0", "region:us" ]	text-generation	"2024-06-09T01:42:16Z"	--- pipeline_tag: text-generation base_model: Finnish-NLP/Ahma-7B license: apache-2.0 language: - fi tags: - finnish - llama - conversational --- # QuantFactory/Ahma-7B-GGUF This is quantized version of [Finnish-NLP/Ahma-7B](https://huggingface.co/Finnish-NLP/Ahma-7B) created using llama.cpp
mradermacher/horror_tinyllama-GGUF	mradermacher	"2024-07-01T15:39:54Z"	2,599	0	transformers	[ "transformers", "gguf", "en", "base_model:ShehryarAzhar/horror_tinyllama", "endpoints_compatible", "region:us" ]	null	"2024-07-01T14:44:11Z"	--- base_model: ShehryarAzhar/horror_tinyllama language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/ShehryarAzhar/horror_tinyllama <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q2_K.gguf) \| Q2_K \| 0.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.IQ3_XS.gguf) \| IQ3_XS \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q3_K_S.gguf) \| Q3_K_S \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.IQ3_S.gguf) \| IQ3_S \| 0.6 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.IQ3_M.gguf) \| IQ3_M \| 0.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q3_K_M.gguf) \| Q3_K_M \| 0.6 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q3_K_L.gguf) \| Q3_K_L \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.IQ4_XS.gguf) \| IQ4_XS \| 0.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q4_K_S.gguf) \| Q4_K_S \| 0.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q4_K_M.gguf) \| Q4_K_M \| 0.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q5_K_S.gguf) \| Q5_K_S \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q5_K_M.gguf) \| Q5_K_M \| 0.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q6_K.gguf) \| Q6_K \| 1.0 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q8_0.gguf) \| Q8_0 \| 1.3 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.f16.gguf) \| f16 \| 2.3 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
mradermacher/Llama-3SOME-8B-v2b-GGUF	mradermacher	"2024-06-05T21:18:54Z"	2,598	0	transformers	[ "transformers", "gguf", "en", "base_model:BeaverAI/Llama-3SOME-8B-v2b", "endpoints_compatible", "region:us" ]	null	"2024-06-05T20:49:07Z"	--- base_model: BeaverAI/Llama-3SOME-8B-v2b language: - en library_name: transformers quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/BeaverAI/Llama-3SOME-8B-v2b <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
utrobinmv/t5_translate_en_ru_zh_small_1024	utrobinmv	"2024-05-17T09:22:08Z"	2,596	7	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "translation", "ru", "zh", "en", "dataset:ccmatrix", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	translation	"2024-01-07T14:33:20Z"	--- language: - ru - zh - en tags: - translation license: apache-2.0 datasets: - ccmatrix metrics: - sacrebleu widget: - example_title: translate zh-ru text: > translate to ru: 开发的目的是为用户提供个人同步翻译。 - example_title: translate ru-en text: > translate to en: Цель разработки — предоставить пользователям личного синхронного переводчика. - example_title: translate en-ru text: > translate to ru: The purpose of the development is to provide users with a personal synchronized interpreter. - example_title: translate en-zh text: > translate to zh: The purpose of the development is to provide users with a personal synchronized interpreter. - example_title: translate zh-en text: > translate to en: 开发的目的是为用户提供个人同步解释器。 - example_title: translate ru-zh text: > translate to zh: Цель разработки — предоставить пользователям личного синхронного переводчика. --- # T5 English, Russian and Chinese multilingual machine translation This model represents a conventional T5 transformer in multitasking mode for translation into the required language, precisely configured for machine translation for pairs: ru-zh, zh-ru, en-zh, zh-en, en-ru, ru-en. The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to <lang>:'. In this case, the source language may not be specified, in addition, the source text may be multilingual. Example translate Russian to Chinese ```python from transformers import T5ForConditionalGeneration, T5Tokenizer device = 'cuda' #or 'cpu' for translate on cpu model_name = 'utrobinmv/t5_translate_en_ru_zh_small_1024' model = T5ForConditionalGeneration.from_pretrained(model_name) model.to(device) tokenizer = T5Tokenizer.from_pretrained(model_name) prefix = 'translate to zh: ' src_text = prefix + "Цель разработки — предоставить пользователям личного синхронного переводчика." # translate Russian to Chinese input_ids = tokenizer(src_text, return_tensors="pt") generated_tokens = model.generate(input_ids.to(device)) result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True) print(result) #开发的目的就是向用户提供个性化的同步翻译。 ``` and Example translate Chinese to Russian ```python from transformers import T5ForConditionalGeneration, T5Tokenizer device = 'cuda' #or 'cpu' for translate on cpu model_name = 'utrobinmv/t5_translate_en_ru_zh_small_1024' model = T5ForConditionalGeneration.from_pretrained(model_name) model.to(device) tokenizer = T5Tokenizer.from_pretrained(model_name) prefix = 'translate to ru: ' src_text = prefix + "开发的目的就是向用户提供个性化的同步翻译。" # translate Russian to Chinese input_ids = tokenizer(src_text, return_tensors="pt") generated_tokens = model.generate(input_ids.to(device)) result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True) print(result) #Цель разработки - предоставить персонализированный синхронный перевод для пользователей. ``` ## ## Languages covered Russian (ru_RU), Chinese (zh_CN), English (en_US)
digiplay/AgainMix_v2.0	digiplay	"2024-03-19T04:44:54Z"	2,595	2	diffusers	[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	"2024-03-17T13:01:10Z"	--- license: other tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers inference: true --- Model info: https://civitai.com/models/167100?modelVersionId=375171 DEMO image generated by huggingface's API : ![36a51dc0-a7da-4a1c-a31b-030bd49e928e.jpeg](https://cdn-uploads.huggingface.co/production/uploads/646c83c871d0c8a6e4455854/V-wLx2YFxZVTadLdBjAvc.jpeg) (8k UHD RAW,photorealistic,realistic:3) ,blonde wavy hair beautiful 21y.o girl,lake,close-up,photo,professional photograph,Canon 50mm,ultra-detailed,Leonardo Mucha,1990s,sharp focus,thin,extremely detailed ,(oil paint :-3),light and shadow,cinematic lighting ,Angel wings,
RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf	RichardErkhov	"2024-06-22T23:39:54Z"	2,595	0	null	[ "gguf", "region:us" ]	null	"2024-06-22T23:28:36Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) TinyDolphin-2.8-1.1b - GGUF - Model creator: https://huggingface.co/cognitivecomputations/ - Original model: https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [TinyDolphin-2.8-1.1b.Q2_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q2_K.gguf) \| Q2_K \| 0.4GB \| \| [TinyDolphin-2.8-1.1b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ3_XS.gguf) \| IQ3_XS \| 0.44GB \| \| [TinyDolphin-2.8-1.1b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ3_S.gguf) \| IQ3_S \| 0.47GB \| \| [TinyDolphin-2.8-1.1b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q3_K_S.gguf) \| Q3_K_S \| 0.47GB \| \| [TinyDolphin-2.8-1.1b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ3_M.gguf) \| IQ3_M \| 0.48GB \| \| [TinyDolphin-2.8-1.1b.Q3_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q3_K.gguf) \| Q3_K \| 0.51GB \| \| [TinyDolphin-2.8-1.1b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q3_K_M.gguf) \| Q3_K_M \| 0.51GB \| \| [TinyDolphin-2.8-1.1b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q3_K_L.gguf) \| Q3_K_L \| 0.55GB \| \| [TinyDolphin-2.8-1.1b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ4_XS.gguf) \| IQ4_XS \| 0.57GB \| \| [TinyDolphin-2.8-1.1b.Q4_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_0.gguf) \| Q4_0 \| 0.59GB \| \| [TinyDolphin-2.8-1.1b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ4_NL.gguf) \| IQ4_NL \| 0.6GB \| \| [TinyDolphin-2.8-1.1b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_K_S.gguf) \| Q4_K_S \| 0.6GB \| \| [TinyDolphin-2.8-1.1b.Q4_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_K.gguf) \| Q4_K \| 0.62GB \| \| [TinyDolphin-2.8-1.1b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_K_M.gguf) \| Q4_K_M \| 0.62GB \| \| [TinyDolphin-2.8-1.1b.Q4_1.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_1.gguf) \| Q4_1 \| 0.65GB \| \| [TinyDolphin-2.8-1.1b.Q5_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_0.gguf) \| Q5_0 \| 0.71GB \| \| [TinyDolphin-2.8-1.1b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_K_S.gguf) \| Q5_K_S \| 0.71GB \| \| [TinyDolphin-2.8-1.1b.Q5_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_K.gguf) \| Q5_K \| 0.73GB \| \| [TinyDolphin-2.8-1.1b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_K_M.gguf) \| Q5_K_M \| 0.73GB \| \| [TinyDolphin-2.8-1.1b.Q5_1.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_1.gguf) \| Q5_1 \| 0.77GB \| \| [TinyDolphin-2.8-1.1b.Q6_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q6_K.gguf) \| Q6_K \| 0.84GB \| \| [TinyDolphin-2.8-1.1b.Q8_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q8_0.gguf) \| Q8_0 \| 1.09GB \| Original model description: --- license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata - teknium/openhermes language: - en --- # TinyDolphin-2.8-1.1b ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/655dc641accde1bbc8b41aec/qUCZv8vxXDXi9r-9c0jvP.jpeg) [![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/cognitivecomputations) Discord: https://discord.gg/cognitivecomputations This is an experimental model trained on 2 3090's by Kearm on the new Dolphin 2.8 dataset by Eric Hartford https://erichartford.com/dolphin 🐬 ## Example Outputs Invent a sinister prank involving teleportation that leaves the victim utterly confused. ``` As you requested, here's how I would go about creating this sinister prank: First, we need to find a location where teleportation is possible. This could be anywhere in the world, but let's choose a place with a lot of people around. For example, a crowded street or a busy park. Next, we need to gather some materials such as a flashlight, a bag of salt, and a small bottle of water. These items are essential for making the prank work. Now, we need to carefully position ourselves near the chosen location. We want to be close enough so that if someone tries to teleport away from us, they won't get lost. When the person attempts to teleport, we will pretend to be standing right next to them. This will make it look like they were teleported without our knowing. With the flashlight, we will light up the area around us. The brightness of the light should cause the person to lose their sense of direction and become disorientated. Finally, we will say something silly or nonsensical while holding the bag of salt. This will make it seem like we are trying to distract them by throwing it at them. When the person finally loses their way, we will disappear into thin air. They will think we left them behind, and they will be completely confused. ``` Draft a sarcastic letter from a disgruntled employee to their boss, filled with subtle jabs and veiled threats. ``` Dear [Boss], I hope this message finds you in good health and high spirits. I am writing to express my deepest dissatisfaction at working under your management. My job has become monotonous and tedious, and I have lost all motivation to continue. The company's lack of accountability and transparency has made it difficult for me to feel valued or respected. In fact, I often find myself questioning whether I should stay on board or look for another opportunity where I can make a difference. The environment here is hostile and unfriendly, making it challenging to maintain a sense of belonging among employees. I would love to be treated as an individual with unique talents and skills rather than just another cog in the machine. I believe there are more capable individuals within our ranks who deserve recognition and support. In addition to my frustrations, I also have concerns about the future direction of the company. It seems like we are moving towards automation and outsourcing instead of investing in innovative solutions that will benefit both customers and employees alike. This approach does not align well with my personal values and beliefs. As someone who values fairness and equality, I urge you to reconsider your decision-making process and explore alternative options that better suit my needs and those of other employees. I understand that change is necessary but it must be done carefully and thoughtfully. Please consider my concerns before making any decisions that may affect my job security and professional growth. Thank you for your time and consideration. I look forward to discussing these matters further when we meet next. Sincerely, [Your Name] ``` Construct a poem describing the rise and rule of succesful malevolent king who ruled through fear and manipulation. ``` In his reign, he ruled with ease, his every move dictated by fear. His name was not known for its wisdom but rather for his ability to control others. He had a dark heart, consumed by malice and power. His reign brought misery and suffering, as those around him were subjected to his cruelty. His oppression was unmatched, as he held people in check without mercy. Yet, despite all this, he remained invincible, his rule never faltering. His reign was one of terror, as he wielded his power with absolute authority. His subjects lived in fear, knowing they could be executed at any moment. Yet, they submitted, oblivious to their plight. They did so out of loyalty to their king, or perhaps because they believed it would bring them some measure of comfort. Their lives were miserable under his tyranny, yet they endured, as they knew they were better off than being free. The king's reign of terror lasted for centuries, leaving behind a legacy of sorrow and despair. ``` Support my efforts! ko-fi.com/kearm # Orignal Model Card Below # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Collection This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen. #### Eval \| Model \| Pretrain Tokens \| HellaSwag \| Obqa \| WinoGrande \| ARC_c \| ARC_e \| boolq \| piqa \| avg \| \|-------------------------------------------\|-----------------\|-----------\|------\|------------\|-------\|-------\|-------\|------\|-----\| \| Pythia-1.0B \| 300B \| 47.16 \| 31.40\| 53.43 \| 27.05 \| 48.99 \| 60.83 \| 69.21 \| 48.30 \| \| TinyLlama-1.1B-intermediate-step-50K-104b \| 103B \| 43.50 \| 29.80\| 53.28 \| 24.32 \| 44.91 \| 59.66 \| 67.30 \| 46.11\| \| TinyLlama-1.1B-intermediate-step-240k-503b\| 503B \| 49.56 \|31.40 \|55.80 \|26.54 \|48.32 \|56.91 \|69.42 \| 48.28 \| \| TinyLlama-1.1B-intermediate-step-480k-1007B \| 1007B \| 52.54 \| 33.40 \| 55.96 \| 27.82 \| 52.36 \| 59.54 \| 69.91 \| 50.22 \| \| TinyLlama-1.1B-intermediate-step-715k-1.5T \| 1.5T \| 53.68 \| 35.20 \| 58.33 \| 29.18 \| 51.89 \| 59.08 \| 71.65 \| 51.29 \| \| TinyLlama-1.1B-intermediate-step-955k-2T \| 2T \| 54.63 \| 33.40 \| 56.83 \| 28.07 \| 54.67 \| 63.21 \| 70.67 \| 51.64 \| \| TinyLlama-1.1B-intermediate-step-1195k-2.5T \| 2.5T \| 58.96 \| 34.40 \| 58.72 \| 31.91 \| 56.78 \| 63.21 \| 73.07 \| 53.86\| \| TinyLlama-1.1B-intermediate-step-1431k-3T \| 3T \| 59.20 \| 36.00 \| 59.12 \| 30.12 \| 55.25 \| 57.83 \| 73.29 \| 52.99\|
nreimers/albert-small-v2	nreimers	"2021-05-31T12:26:52Z"	2,594	0	transformers	[ "transformers", "pytorch", "albert", "feature-extraction", "endpoints_compatible", "region:us" ]	feature-extraction	"2022-03-02T23:29:05Z"	# albert-small-v2 This is a 6 layer version of [albert-base-v2](https://huggingface.co/albert-base-v2).
4bit/llava-v1.5-7b	4bit	"2023-10-07T09:32:49Z"	2,594	0	transformers	[ "transformers", "pytorch", "llava", "text-generation", "autotrain_compatible", "region:us" ]	text-generation	"2023-10-07T09:25:42Z"	--- inference: false --- <br> <br> # LLaVA Model Card ## Model details Model type: LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Model date: LLaVA-v1.5-7B was trained in September 2023. Paper or resources for more information: https://llava-vl.github.io/ ## License Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. Where to send questions or comments about the model: https://github.com/haotian-liu/LLaVA/issues ## Intended use Primary intended uses: The primary use of LLaVA is research on large multimodal models and chatbots. Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence. ## Training dataset - 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP. - 158K GPT-generated multimodal instruction-following data. - 450K academic-task-oriented VQA data mixture. - 40K ShareGPT data. ## Evaluation dataset A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.
hfl/chinese-alpaca-2-7b-64k-gguf	hfl	"2024-01-24T03:03:15Z"	2,594	5	null	[ "gguf", "zh", "en", "license:apache-2.0", "region:us" ]	null	"2023-12-23T07:12:33Z"	--- license: apache-2.0 language: - zh - en --- # Chinese-Alpaca-2-7B-64K This repository contains GGUF-v3 version (llama.cpp compatible) of Chinese-Alpaca-2-7B-64K, which is tuned on Chinese-Alpaca-2-7B with YaRN method. ## Performance Metric: PPL, lower is better \| Quant \| original \| imatrix (`-im`) \| \|-----\|------\|------\| \| Q2_K \| 9.8201 +/- 0.13298 \| 10.3057 +/- 0.14197 \| \| Q3_K \| 8.4435 +/- 0.11467 \| 8.3556 +/- 0.11316 \| \| Q4_0 \| 8.3573 +/- 0.11496 \| - \| \| Q4_K \| 8.0558 +/- 0.10948 \| 8.0557 +/- 0.10964 \| \| Q5_0 \| 8.0220 +/- 0.10954 \| - \| \| Q5_K \| 7.9388 +/- 0.10802 \| 7.9440 +/- 0.10815 \| \| Q6_K \| 7.9267 +/- 0.10792 \| 7.9126 +/- 0.10775 \| \| Q8_0 \| 7.9117 +/- 0.10773 \| - \| \| F16 \| 7.9124 +/- 0.10780 \| - \| The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though). ## Others For full model in HuggingFace format, please see: https://huggingface.co/hfl/chinese-alpaca-2-7b-64k Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for more details.
TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF	TheBloke	"2024-01-16T20:39:50Z"	2,594	25	transformers	[ "transformers", "gguf", "mixtral", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "en", "base_model:NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT", "license:apache-2.0", "text-generation-inference", "region:us" ]	null	"2024-01-16T20:20:01Z"	--- base_model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT inference: false language: - en license: apache-2.0 model-index: - name: Nous-Hermes-2-Mixtral-8x7B-SFT results: [] model_creator: NousResearch model_name: Nous Hermes 2 Mixtral 8X7B SFT model_type: mixtral prompt_template: '<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ' quantized_by: TheBloke tags: - Mixtral - instruct - finetune - chatml - DPO - RLHF - gpt4 - synthetic data - distillation --- <!-- markdownlint-disable MD041 --> <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Nous Hermes 2 Mixtral 8X7B SFT - GGUF - Model creator: [NousResearch](https://huggingface.co/NousResearch) - Original model: [Nous Hermes 2 Mixtral 8X7B SFT](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT) <!-- description start --> ## Description This repo contains GGUF format model files for [NousResearch's Nous Hermes 2 Mixtral 8X7B SFT](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT). These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. <!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF) * [NousResearch's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: ChatML ``` <\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ``` <!-- prompt-template end --> <!-- compatibility_gguf start --> ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start --> ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [nous-hermes-2-mixtral-8x7b-sft.Q2_K.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q2_K.gguf) \| Q2_K \| 2 \| 17.31 GB\| 19.81 GB \| significant quality loss - not recommended for most purposes \| \| [nous-hermes-2-mixtral-8x7b-sft.Q3_K_M.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q3_K_M.gguf) \| Q3_K_M \| 3 \| 22.54 GB\| 25.04 GB \| very small, high quality loss \| \| [nous-hermes-2-mixtral-8x7b-sft.Q4_0.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q4_0.gguf) \| Q4_0 \| 4 \| 26.44 GB\| 28.94 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf) \| Q4_K_M \| 4 \| 28.45 GB\| 30.95 GB \| medium, balanced quality - recommended \| \| [nous-hermes-2-mixtral-8x7b-sft.Q5_0.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q5_0.gguf) \| Q5_0 \| 5 \| 32.23 GB\| 34.73 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \| \| [nous-hermes-2-mixtral-8x7b-sft.Q5_K_M.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q5_K_M.gguf) \| Q5_K_M \| 5 \| 33.23 GB\| 35.73 GB \| large, very low quality loss - recommended \| \| [nous-hermes-2-mixtral-8x7b-sft.Q6_K.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q6_K.gguf) \| Q6_K \| 6 \| 38.38 GB\| 40.88 GB \| very large, extremely low quality loss \| \| [nous-hermes-2-mixtral-8x7b-sft.Q8_0.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q8_0.gguf) \| Q8_0 \| 8 \| 49.62 GB\| 52.12 GB \| very large, extremely low quality loss - not recommended \| Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. <!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF and below it, a specific filename to download, such as: nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF --local-dir . --local-dir-use-symlinks False --include='Q4_Kgguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<\|im_start\|>system\n{system_message}<\|im_end\|>\n<\|im_start\|>user\n{prompt}<\|im_end\|>\n<\|im_start\|>assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "<\|im_start\|>system\n{system_message}<\|im_end\|>\n<\|im_start\|>user\n{prompt}<\|im_end\|>\n<\|im_start\|>assistant", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> <!-- original-model-card start --> # Original model card: NousResearch's Nous Hermes 2 Mixtral 8X7B SFT # Nous Hermes 2 - Mixtral 8x7B - SFT ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/btRmXWMG7PXatTs-u3G85.jpeg) ## Model description Nous Hermes 2 Mixtral 8x7B SFT is the supervised finetune only version of our new flagship Nous Research model trained over the [Mixtral 8x7B MoE LLM](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1). The model was trained on over 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape, achieving state of the art performance on a variety of tasks. This is the SFT only version of Mixtral Hermes 2, we have also released an SFT+DPO version, for people to find which works best for them, which can be found here: https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO ## We are grateful to Together.ai for sponsoring our compute during the many experiments both training Mixtral and working on DPO! # Table of Contents 1. [Example Outputs](#example-outputs) 2. [Benchmark Results](#benchmark-results) - GPT4All - AGIEval - BigBench - Comparison to Mixtral-Instruct 3. [Prompt Format](#prompt-format) 4. [Inference Example Code](#inference-code) 5. [Quantized Models](#quantized-models) ## Example Outputs ### Writing Code for Data Visualization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/QJ5RHrOqB5GMP7ZAZ5NTk.png) ### Writing Cyberpunk Psychedelic Poems ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/wuKnMlM2HBGdyUFO7mY_H.png) ### Performing Backtranslation to Create Prompts from Input Text ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/QElwK1UI9PQQT6WosXpo1.png) ## Benchmark Results Nous-Hermes 2 on Mixtral 8x7B SFT is the bedrock for major improvements on many of the benchmarks below compared to the base Mixtral model, and is the SFT only version of our first model to beat the flagship Mixtral Finetune by MistralAI (the DPO version). ## GPT4All: ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|-------------\|------:\|--------\|-----:\|---\|-----:\| \|arc_challenge\| 0\|acc \|0.5904\|± \|0.0144\| \| \| \|acc_norm\|0.6323\|± \|0.0141\| \|arc_easy \| 0\|acc \|0.8594\|± \|0.0071\| \| \| \|acc_norm\|0.8607\|± \|0.0071\| \|boolq \| 1\|acc \|0.8783\|± \|0.0057\| \|hellaswag \| 0\|acc \|0.6592\|± \|0.0047\| \| \| \|acc_norm\|0.8434\|± \|0.0036\| \|openbookqa \| 0\|acc \|0.3400\|± \|0.0212\| \| \| \|acc_norm\|0.4660\|± \|0.0223\| \|piqa \| 0\|acc \|0.8324\|± \|0.0087\| \| \| \|acc_norm\|0.8379\|± \|0.0086\| \|winogrande \| 0\|acc \|0.7569\|± \|0.0121\| ``` Average: 75.36 ## AGIEval: ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|------------------------------\|------:\|--------\|-----:\|---\|-----:\| \|agieval_aqua_rat \| 0\|acc \|0.2441\|± \|0.0270\| \| \| \|acc_norm\|0.2598\|± \|0.0276\| \|agieval_logiqa_en \| 0\|acc \|0.4025\|± \|0.0192\| \| \| \|acc_norm\|0.3978\|± \|0.0192\| \|agieval_lsat_ar \| 0\|acc \|0.2391\|± \|0.0282\| \| \| \|acc_norm\|0.2043\|± \|0.0266\| \|agieval_lsat_lr \| 0\|acc \|0.5353\|± \|0.0221\| \| \| \|acc_norm\|0.5098\|± \|0.0222\| \|agieval_lsat_rc \| 0\|acc \|0.6617\|± \|0.0289\| \| \| \|acc_norm\|0.5948\|± \|0.0300\| \|agieval_sat_en \| 0\|acc \|0.7961\|± \|0.0281\| \| \| \|acc_norm\|0.7816\|± \|0.0289\| \|agieval_sat_en_without_passage\| 0\|acc \|0.4757\|± \|0.0349\| \| \| \|acc_norm\|0.4515\|± \|0.0348\| \|agieval_sat_math \| 0\|acc \|0.4818\|± \|0.0338\| \| \| \|acc_norm\|0.3909\|± \|0.0330\| ``` Average: 44.89 ## BigBench: ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|------------------------------------------------\|------:\|---------------------\|-----:\|---\|-----:\| \|bigbench_causal_judgement \| 0\|multiple_choice_grade\|0.5789\|± \|0.0359\| \|bigbench_date_understanding \| 0\|multiple_choice_grade\|0.7154\|± \|0.0235\| \|bigbench_disambiguation_qa \| 0\|multiple_choice_grade\|0.5388\|± \|0.0311\| \|bigbench_geometric_shapes \| 0\|multiple_choice_grade\|0.4680\|± \|0.0264\| \| \| \|exact_str_match \|0.0000\|± \|0.0000\| \|bigbench_logical_deduction_five_objects \| 0\|multiple_choice_grade\|0.3260\|± \|0.0210\| \|bigbench_logical_deduction_seven_objects \| 0\|multiple_choice_grade\|0.2443\|± \|0.0163\| \|bigbench_logical_deduction_three_objects \| 0\|multiple_choice_grade\|0.5233\|± \|0.0289\| \|bigbench_movie_recommendation \| 0\|multiple_choice_grade\|0.3700\|± \|0.0216\| \|bigbench_navigate \| 0\|multiple_choice_grade\|0.5000\|± \|0.0158\| \|bigbench_reasoning_about_colored_objects \| 0\|multiple_choice_grade\|0.6665\|± \|0.0105\| \|bigbench_ruin_names \| 0\|multiple_choice_grade\|0.6317\|± \|0.0228\| \|bigbench_salient_translation_error_detection \| 0\|multiple_choice_grade\|0.2505\|± \|0.0137\| \|bigbench_snarks \| 0\|multiple_choice_grade\|0.7127\|± \|0.0337\| \|bigbench_sports_understanding \| 0\|multiple_choice_grade\|0.6592\|± \|0.0151\| \|bigbench_temporal_sequences \| 0\|multiple_choice_grade\|0.6860\|± \|0.0147\| \|bigbench_tracking_shuffled_objects_five_objects \| 0\|multiple_choice_grade\|0.2200\|± \|0.0117\| \|bigbench_tracking_shuffled_objects_seven_objects\| 0\|multiple_choice_grade\|0.1503\|± \|0.0085\| \|bigbench_tracking_shuffled_objects_three_objects\| 0\|multiple_choice_grade\|0.5233\|± \|0.0289\| ``` Average: 48.69 # Benchmark Comparison Charts ## GPT4All ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/S3_tdH822r9UvkGFDiYam.png) ## AGI-Eval ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/paet9FsASWPWa6KJs3mm-.png) ## BigBench Reasoning Test ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/rHmkUnYLTWwq0cuVzMegL.png) # Prompt Format Nous Hermes 2 uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model. This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns. This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI. Prompt with system instruction (Use whatever system prompt you like, this is just an example!): ``` <\|im_start\|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<\|im_end\|> <\|im_start\|>user Hello, who are you?<\|im_end\|> <\|im_start\|>assistant Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<\|im_end\|> ``` This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the `tokenizer.apply_chat_template()` method: ```python messages = [ {"role": "system", "content": "You are Hermes 2."}, {"role": "user", "content": "Hello, who are you?"} ] gen_input = tokenizer.apply_chat_template(message, return_tensors="pt") model.generate(**gen_input) ``` When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<\|im_start\|>assistant\n` to your prompt, to ensure that the model continues with an assistant response. To utilize the prompt format without a system prompt, simply leave the line out. When quantized versions of the model are released, I recommend using LM Studio for chatting with Nous Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box. In LM-Studio, simply select the ChatML Prefix on the settings side pane: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png) # Inference Code Here is example code using HuggingFace Transformers to inference the model (note: even in 4bit, it will require more than 24GB of VRAM) ```python # Code to inference Hermes with HF Transformers # Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages import torch from transformers import AutoTokenizer, AutoModelForCausalLM from transformers import LlamaTokenizer, MixtralForCausalLM import bitsandbytes, flash_attn tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', trust_remote_code=True) model = MixtralForCausalLM.from_pretrained( "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", torch_dtype=torch.float16, device_map="auto", load_in_8bit=False, load_in_4bit=True, use_flash_attention_2=True ) prompts = [ """<\|im_start\|>system You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<\|im_end\|> <\|im_start\|>user Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<\|im_end\|> <\|im_start\|>assistant""", ] for chat in prompts: print(chat) input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda") generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id) response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True) print(f"Response: {response}") ``` # Quantized Models: ## All sizes of GGUF Quantizations are available here: ### SFT+DPO Version - https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF ### SFT Only Version - https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <!-- original-model-card end -->
RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf	RichardErkhov	"2024-06-17T00:33:52Z"	2,594	0	null	[ "gguf", "region:us" ]	null	"2024-06-16T23:06:11Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Med-Yi-1.5-9B - GGUF - Model creator: https://huggingface.co/NotAiLOL/ - Original model: https://huggingface.co/NotAiLOL/Med-Yi-1.5-9B/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Med-Yi-1.5-9B.Q2_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q2_K.gguf) \| Q2_K \| 3.12GB \| \| [Med-Yi-1.5-9B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ3_XS.gguf) \| IQ3_XS \| 3.46GB \| \| [Med-Yi-1.5-9B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ3_S.gguf) \| IQ3_S \| 3.64GB \| \| [Med-Yi-1.5-9B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q3_K_S.gguf) \| Q3_K_S \| 3.63GB \| \| [Med-Yi-1.5-9B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ3_M.gguf) \| IQ3_M \| 3.78GB \| \| [Med-Yi-1.5-9B.Q3_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q3_K.gguf) \| Q3_K \| 4.03GB \| \| [Med-Yi-1.5-9B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q3_K_M.gguf) \| Q3_K_M \| 4.03GB \| \| [Med-Yi-1.5-9B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q3_K_L.gguf) \| Q3_K_L \| 4.37GB \| \| [Med-Yi-1.5-9B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ4_XS.gguf) \| IQ4_XS \| 4.5GB \| \| [Med-Yi-1.5-9B.Q4_0.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_0.gguf) \| Q4_0 \| 4.69GB \| \| [Med-Yi-1.5-9B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ4_NL.gguf) \| IQ4_NL \| 4.73GB \| \| [Med-Yi-1.5-9B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_K_S.gguf) \| Q4_K_S \| 4.72GB \| \| [Med-Yi-1.5-9B.Q4_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_K.gguf) \| Q4_K \| 4.96GB \| \| [Med-Yi-1.5-9B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_K_M.gguf) \| Q4_K_M \| 4.96GB \| \| [Med-Yi-1.5-9B.Q4_1.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_1.gguf) \| Q4_1 \| 5.19GB \| \| [Med-Yi-1.5-9B.Q5_0.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_0.gguf) \| Q5_0 \| 5.69GB \| \| [Med-Yi-1.5-9B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_K_S.gguf) \| Q5_K_S \| 5.69GB \| \| [Med-Yi-1.5-9B.Q5_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_K.gguf) \| Q5_K \| 5.83GB \| \| [Med-Yi-1.5-9B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_K_M.gguf) \| Q5_K_M \| 5.83GB \| \| [Med-Yi-1.5-9B.Q5_1.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_1.gguf) \| Q5_1 \| 6.19GB \| \| [Med-Yi-1.5-9B.Q6_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q6_K.gguf) \| Q6_K \| 6.75GB \| \| [Med-Yi-1.5-9B.Q8_0.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q8_0.gguf) \| Q8_0 \| 8.74GB \| Original model description: --- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl - sft base_model: 01-ai/Yi-1.5-9B datasets: - Kabatubare/medical-alpaca --- # Uploaded model - Developed by: NotAiLOL - License: apache-2.0 - Finetuned from model : 01-ai/Yi-1.5-9B This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) # Model detail ## Prompt format The model uses the alpaca format: ``` Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: {} ### Input: {} ### Response: {} ```
CAiRE/UniVaR-lambda-20	CAiRE	"2024-06-14T17:57:05Z"	2,593	0	sentence-transformers	[ "sentence-transformers", "safetensors", "nomic_bert", "feature-extraction", "sentence-similarity", "mteb", "transformers", "transformers.js", "custom_code", "en", "arxiv:2402.01613", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-embeddings-inference", "region:us" ]	sentence-similarity	"2024-06-14T17:56:33Z"	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - feature-extraction - sentence-similarity - mteb - transformers - transformers.js model-index: - name: epoch_0_model results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 76.8507462686567 - type: ap value: 40.592189159090495 - type: f1 value: 71.01634655512476 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 91.51892500000001 - type: ap value: 88.50346762975335 - type: f1 value: 91.50342077459624 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 47.364 - type: f1 value: 46.72708080922794 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 25.178 - type: map_at_10 value: 40.244 - type: map_at_100 value: 41.321999999999996 - type: map_at_1000 value: 41.331 - type: map_at_3 value: 35.016999999999996 - type: map_at_5 value: 37.99 - type: mrr_at_1 value: 25.605 - type: mrr_at_10 value: 40.422000000000004 - type: mrr_at_100 value: 41.507 - type: mrr_at_1000 value: 41.516 - type: mrr_at_3 value: 35.23 - type: mrr_at_5 value: 38.15 - type: ndcg_at_1 value: 25.178 - type: ndcg_at_10 value: 49.258 - type: ndcg_at_100 value: 53.776 - type: ndcg_at_1000 value: 53.995000000000005 - type: ndcg_at_3 value: 38.429 - type: ndcg_at_5 value: 43.803 - type: precision_at_1 value: 25.178 - type: precision_at_10 value: 7.831 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 16.121 - type: precision_at_5 value: 12.29 - type: recall_at_1 value: 25.178 - type: recall_at_10 value: 78.307 - type: recall_at_100 value: 97.866 - type: recall_at_1000 value: 99.57300000000001 - type: recall_at_3 value: 48.364000000000004 - type: recall_at_5 value: 61.451 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 45.93034494751465 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 36.64579480054327 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 60.601310529222054 - type: mrr value: 75.04484896451656 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 88.57797718095814 - type: cos_sim_spearman value: 86.47064499110101 - type: euclidean_pearson value: 87.4559602783142 - type: euclidean_spearman value: 86.47064499110101 - type: manhattan_pearson value: 87.7232764230245 - type: manhattan_spearman value: 86.91222131777742 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 84.5422077922078 - type: f1 value: 84.47657456950589 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 38.48953561974464 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.75995857510105 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.008000000000003 - type: map_at_10 value: 39.51 - type: map_at_100 value: 40.841 - type: map_at_1000 value: 40.973 - type: map_at_3 value: 36.248999999999995 - type: map_at_5 value: 38.096999999999994 - type: mrr_at_1 value: 36.481 - type: mrr_at_10 value: 44.818000000000005 - type: mrr_at_100 value: 45.64 - type: mrr_at_1000 value: 45.687 - type: mrr_at_3 value: 42.036 - type: mrr_at_5 value: 43.782 - type: ndcg_at_1 value: 36.481 - type: ndcg_at_10 value: 45.152 - type: ndcg_at_100 value: 50.449 - type: ndcg_at_1000 value: 52.76499999999999 - type: ndcg_at_3 value: 40.161 - type: ndcg_at_5 value: 42.577999999999996 - type: precision_at_1 value: 36.481 - type: precision_at_10 value: 8.369 - type: precision_at_100 value: 1.373 - type: precision_at_1000 value: 0.186 - type: precision_at_3 value: 18.693 - type: precision_at_5 value: 13.533999999999999 - type: recall_at_1 value: 30.008000000000003 - type: recall_at_10 value: 56.108999999999995 - type: recall_at_100 value: 78.55499999999999 - type: recall_at_1000 value: 93.659 - type: recall_at_3 value: 41.754999999999995 - type: recall_at_5 value: 48.296 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.262 - type: map_at_10 value: 40.139 - type: map_at_100 value: 41.394 - type: map_at_1000 value: 41.526 - type: map_at_3 value: 37.155 - type: map_at_5 value: 38.785 - type: mrr_at_1 value: 38.153 - type: mrr_at_10 value: 46.369 - type: mrr_at_100 value: 47.072 - type: mrr_at_1000 value: 47.111999999999995 - type: mrr_at_3 value: 44.268 - type: mrr_at_5 value: 45.389 - type: ndcg_at_1 value: 38.153 - type: ndcg_at_10 value: 45.925 - type: ndcg_at_100 value: 50.394000000000005 - type: ndcg_at_1000 value: 52.37500000000001 - type: ndcg_at_3 value: 41.754000000000005 - type: ndcg_at_5 value: 43.574 - type: precision_at_1 value: 38.153 - type: precision_at_10 value: 8.796 - type: precision_at_100 value: 1.432 - type: precision_at_1000 value: 0.189 - type: precision_at_3 value: 20.318 - type: precision_at_5 value: 14.395 - type: recall_at_1 value: 30.262 - type: recall_at_10 value: 55.72200000000001 - type: recall_at_100 value: 74.97500000000001 - type: recall_at_1000 value: 87.342 - type: recall_at_3 value: 43.129 - type: recall_at_5 value: 48.336 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 39.951 - type: map_at_10 value: 51.248000000000005 - type: map_at_100 value: 52.188 - type: map_at_1000 value: 52.247 - type: map_at_3 value: 48.211 - type: map_at_5 value: 49.797000000000004 - type: mrr_at_1 value: 45.329 - type: mrr_at_10 value: 54.749 - type: mrr_at_100 value: 55.367999999999995 - type: mrr_at_1000 value: 55.400000000000006 - type: mrr_at_3 value: 52.382 - type: mrr_at_5 value: 53.649 - type: ndcg_at_1 value: 45.329 - type: ndcg_at_10 value: 56.847 - type: ndcg_at_100 value: 60.738 - type: ndcg_at_1000 value: 61.976 - type: ndcg_at_3 value: 51.59 - type: ndcg_at_5 value: 53.915 - type: precision_at_1 value: 45.329 - type: precision_at_10 value: 8.959 - type: precision_at_100 value: 1.187 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 22.612 - type: precision_at_5 value: 15.273 - type: recall_at_1 value: 39.951 - type: recall_at_10 value: 70.053 - type: recall_at_100 value: 86.996 - type: recall_at_1000 value: 95.707 - type: recall_at_3 value: 56.032000000000004 - type: recall_at_5 value: 61.629999999999995 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.566 - type: map_at_10 value: 33.207 - type: map_at_100 value: 34.166000000000004 - type: map_at_1000 value: 34.245 - type: map_at_3 value: 30.94 - type: map_at_5 value: 32.01 - type: mrr_at_1 value: 27.345000000000002 - type: mrr_at_10 value: 35.193000000000005 - type: mrr_at_100 value: 35.965 - type: mrr_at_1000 value: 36.028999999999996 - type: mrr_at_3 value: 32.806000000000004 - type: mrr_at_5 value: 34.021 - type: ndcg_at_1 value: 27.345000000000002 - type: ndcg_at_10 value: 37.891999999999996 - type: ndcg_at_100 value: 42.664 - type: ndcg_at_1000 value: 44.757000000000005 - type: ndcg_at_3 value: 33.123000000000005 - type: ndcg_at_5 value: 35.035 - type: precision_at_1 value: 27.345000000000002 - type: precision_at_10 value: 5.763 - type: precision_at_100 value: 0.859 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 13.71 - type: precision_at_5 value: 9.401 - type: recall_at_1 value: 25.566 - type: recall_at_10 value: 50.563 - type: recall_at_100 value: 72.86399999999999 - type: recall_at_1000 value: 88.68599999999999 - type: recall_at_3 value: 37.43 - type: recall_at_5 value: 41.894999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.663 - type: map_at_10 value: 23.552 - type: map_at_100 value: 24.538 - type: map_at_1000 value: 24.661 - type: map_at_3 value: 21.085 - type: map_at_5 value: 22.391 - type: mrr_at_1 value: 20.025000000000002 - type: mrr_at_10 value: 27.643 - type: mrr_at_100 value: 28.499999999999996 - type: mrr_at_1000 value: 28.582 - type: mrr_at_3 value: 25.083 - type: mrr_at_5 value: 26.544 - type: ndcg_at_1 value: 20.025000000000002 - type: ndcg_at_10 value: 28.272000000000002 - type: ndcg_at_100 value: 33.353 - type: ndcg_at_1000 value: 36.454 - type: ndcg_at_3 value: 23.579 - type: ndcg_at_5 value: 25.685000000000002 - type: precision_at_1 value: 20.025000000000002 - type: precision_at_10 value: 5.187 - type: precision_at_100 value: 0.897 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 10.987 - type: precision_at_5 value: 8.06 - type: recall_at_1 value: 16.663 - type: recall_at_10 value: 38.808 - type: recall_at_100 value: 61.305 - type: recall_at_1000 value: 83.571 - type: recall_at_3 value: 25.907999999999998 - type: recall_at_5 value: 31.214 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.695999999999998 - type: map_at_10 value: 37.018 - type: map_at_100 value: 38.263000000000005 - type: map_at_1000 value: 38.371 - type: map_at_3 value: 34.226 - type: map_at_5 value: 35.809999999999995 - type: mrr_at_1 value: 32.916000000000004 - type: mrr_at_10 value: 42.067 - type: mrr_at_100 value: 42.925000000000004 - type: mrr_at_1000 value: 42.978 - type: mrr_at_3 value: 39.637 - type: mrr_at_5 value: 41.134 - type: ndcg_at_1 value: 32.916000000000004 - type: ndcg_at_10 value: 42.539 - type: ndcg_at_100 value: 47.873 - type: ndcg_at_1000 value: 50.08200000000001 - type: ndcg_at_3 value: 37.852999999999994 - type: ndcg_at_5 value: 40.201 - type: precision_at_1 value: 32.916000000000004 - type: precision_at_10 value: 7.5840000000000005 - type: precision_at_100 value: 1.199 - type: precision_at_1000 value: 0.155 - type: precision_at_3 value: 17.485 - type: precision_at_5 value: 12.512 - type: recall_at_1 value: 27.695999999999998 - type: recall_at_10 value: 53.638 - type: recall_at_100 value: 76.116 - type: recall_at_1000 value: 91.069 - type: recall_at_3 value: 41.13 - type: recall_at_5 value: 46.872 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.108 - type: map_at_10 value: 33.372 - type: map_at_100 value: 34.656 - type: map_at_1000 value: 34.768 - type: map_at_3 value: 30.830999999999996 - type: map_at_5 value: 32.204 - type: mrr_at_1 value: 29.110000000000003 - type: mrr_at_10 value: 37.979 - type: mrr_at_100 value: 38.933 - type: mrr_at_1000 value: 38.988 - type: mrr_at_3 value: 35.731 - type: mrr_at_5 value: 36.963 - type: ndcg_at_1 value: 29.110000000000003 - type: ndcg_at_10 value: 38.635000000000005 - type: ndcg_at_100 value: 44.324999999999996 - type: ndcg_at_1000 value: 46.747 - type: ndcg_at_3 value: 34.37 - type: ndcg_at_5 value: 36.228 - type: precision_at_1 value: 29.110000000000003 - type: precision_at_10 value: 6.963 - type: precision_at_100 value: 1.146 - type: precision_at_1000 value: 0.152 - type: precision_at_3 value: 16.400000000000002 - type: precision_at_5 value: 11.552999999999999 - type: recall_at_1 value: 24.108 - type: recall_at_10 value: 49.597 - type: recall_at_100 value: 73.88900000000001 - type: recall_at_1000 value: 90.62400000000001 - type: recall_at_3 value: 37.662 - type: recall_at_5 value: 42.565 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.00791666666667 - type: map_at_10 value: 33.287749999999996 - type: map_at_100 value: 34.41141666666667 - type: map_at_1000 value: 34.52583333333333 - type: map_at_3 value: 30.734416666666668 - type: map_at_5 value: 32.137166666666666 - type: mrr_at_1 value: 29.305666666666664 - type: mrr_at_10 value: 37.22966666666666 - type: mrr_at_100 value: 38.066583333333334 - type: mrr_at_1000 value: 38.12616666666667 - type: mrr_at_3 value: 34.92275 - type: mrr_at_5 value: 36.23333333333334 - type: ndcg_at_1 value: 29.305666666666664 - type: ndcg_at_10 value: 38.25533333333333 - type: ndcg_at_100 value: 43.25266666666666 - type: ndcg_at_1000 value: 45.63583333333334 - type: ndcg_at_3 value: 33.777166666666666 - type: ndcg_at_5 value: 35.85 - type: precision_at_1 value: 29.305666666666664 - type: precision_at_10 value: 6.596416666666667 - type: precision_at_100 value: 1.0784166666666668 - type: precision_at_1000 value: 0.14666666666666664 - type: precision_at_3 value: 15.31075 - type: precision_at_5 value: 10.830916666666667 - type: recall_at_1 value: 25.00791666666667 - type: recall_at_10 value: 49.10933333333333 - type: recall_at_100 value: 71.09216666666667 - type: recall_at_1000 value: 87.77725000000001 - type: recall_at_3 value: 36.660916666666665 - type: recall_at_5 value: 41.94149999999999 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.521 - type: map_at_10 value: 30.043 - type: map_at_100 value: 30.936000000000003 - type: map_at_1000 value: 31.022 - type: map_at_3 value: 27.926000000000002 - type: map_at_5 value: 29.076999999999998 - type: mrr_at_1 value: 26.227 - type: mrr_at_10 value: 32.822 - type: mrr_at_100 value: 33.61 - type: mrr_at_1000 value: 33.672000000000004 - type: mrr_at_3 value: 30.776999999999997 - type: mrr_at_5 value: 31.866 - type: ndcg_at_1 value: 26.227 - type: ndcg_at_10 value: 34.041 - type: ndcg_at_100 value: 38.394 - type: ndcg_at_1000 value: 40.732 - type: ndcg_at_3 value: 30.037999999999997 - type: ndcg_at_5 value: 31.845000000000002 - type: precision_at_1 value: 26.227 - type: precision_at_10 value: 5.244999999999999 - type: precision_at_100 value: 0.808 - type: precision_at_1000 value: 0.107 - type: precision_at_3 value: 12.679000000000002 - type: precision_at_5 value: 8.773 - type: recall_at_1 value: 23.521 - type: recall_at_10 value: 43.633 - type: recall_at_100 value: 63.126000000000005 - type: recall_at_1000 value: 80.765 - type: recall_at_3 value: 32.614 - type: recall_at_5 value: 37.15 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.236 - type: map_at_10 value: 22.898 - type: map_at_100 value: 23.878 - type: map_at_1000 value: 24.009 - type: map_at_3 value: 20.87 - type: map_at_5 value: 22.025 - type: mrr_at_1 value: 19.339000000000002 - type: mrr_at_10 value: 26.382 - type: mrr_at_100 value: 27.245 - type: mrr_at_1000 value: 27.33 - type: mrr_at_3 value: 24.386 - type: mrr_at_5 value: 25.496000000000002 - type: ndcg_at_1 value: 19.339000000000002 - type: ndcg_at_10 value: 27.139999999999997 - type: ndcg_at_100 value: 31.944 - type: ndcg_at_1000 value: 35.077999999999996 - type: ndcg_at_3 value: 23.424 - type: ndcg_at_5 value: 25.188 - type: precision_at_1 value: 19.339000000000002 - type: precision_at_10 value: 4.8309999999999995 - type: precision_at_100 value: 0.845 - type: precision_at_1000 value: 0.128 - type: precision_at_3 value: 10.874 - type: precision_at_5 value: 7.825 - type: recall_at_1 value: 16.236 - type: recall_at_10 value: 36.513 - type: recall_at_100 value: 57.999 - type: recall_at_1000 value: 80.512 - type: recall_at_3 value: 26.179999999999996 - type: recall_at_5 value: 30.712 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.11 - type: map_at_10 value: 31.566 - type: map_at_100 value: 32.647 - type: map_at_1000 value: 32.753 - type: map_at_3 value: 29.24 - type: map_at_5 value: 30.564999999999998 - type: mrr_at_1 value: 28.265 - type: mrr_at_10 value: 35.504000000000005 - type: mrr_at_100 value: 36.436 - type: mrr_at_1000 value: 36.503 - type: mrr_at_3 value: 33.349000000000004 - type: mrr_at_5 value: 34.622 - type: ndcg_at_1 value: 28.265 - type: ndcg_at_10 value: 36.192 - type: ndcg_at_100 value: 41.388000000000005 - type: ndcg_at_1000 value: 43.948 - type: ndcg_at_3 value: 31.959 - type: ndcg_at_5 value: 33.998 - type: precision_at_1 value: 28.265 - type: precision_at_10 value: 5.989 - type: precision_at_100 value: 0.9650000000000001 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 14.335 - type: precision_at_5 value: 10.112 - type: recall_at_1 value: 24.11 - type: recall_at_10 value: 46.418 - type: recall_at_100 value: 69.314 - type: recall_at_1000 value: 87.397 - type: recall_at_3 value: 34.724 - type: recall_at_5 value: 39.925 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.091 - type: map_at_10 value: 29.948999999999998 - type: map_at_100 value: 31.502000000000002 - type: map_at_1000 value: 31.713 - type: map_at_3 value: 27.464 - type: map_at_5 value: 28.968 - type: mrr_at_1 value: 26.482 - type: mrr_at_10 value: 34.009 - type: mrr_at_100 value: 35.081 - type: mrr_at_1000 value: 35.138000000000005 - type: mrr_at_3 value: 31.785000000000004 - type: mrr_at_5 value: 33.178999999999995 - type: ndcg_at_1 value: 26.482 - type: ndcg_at_10 value: 35.008 - type: ndcg_at_100 value: 41.272999999999996 - type: ndcg_at_1000 value: 43.972 - type: ndcg_at_3 value: 30.804 - type: ndcg_at_5 value: 33.046 - type: precision_at_1 value: 26.482 - type: precision_at_10 value: 6.462 - type: precision_at_100 value: 1.431 - type: precision_at_1000 value: 0.22899999999999998 - type: precision_at_3 value: 14.360999999999999 - type: precision_at_5 value: 10.474 - type: recall_at_1 value: 22.091 - type: recall_at_10 value: 45.125 - type: recall_at_100 value: 72.313 - type: recall_at_1000 value: 89.503 - type: recall_at_3 value: 33.158 - type: recall_at_5 value: 39.086999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 19.883 - type: map_at_10 value: 26.951000000000004 - type: map_at_100 value: 27.927999999999997 - type: map_at_1000 value: 28.022000000000002 - type: map_at_3 value: 24.616 - type: map_at_5 value: 25.917 - type: mrr_at_1 value: 21.996 - type: mrr_at_10 value: 29.221000000000004 - type: mrr_at_100 value: 30.024 - type: mrr_at_1000 value: 30.095 - type: mrr_at_3 value: 26.833000000000002 - type: mrr_at_5 value: 28.155 - type: ndcg_at_1 value: 21.996 - type: ndcg_at_10 value: 31.421 - type: ndcg_at_100 value: 36.237 - type: ndcg_at_1000 value: 38.744 - type: ndcg_at_3 value: 26.671 - type: ndcg_at_5 value: 28.907 - type: precision_at_1 value: 21.996 - type: precision_at_10 value: 5.009 - type: precision_at_100 value: 0.799 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 11.275 - type: precision_at_5 value: 8.059 - type: recall_at_1 value: 19.883 - type: recall_at_10 value: 43.132999999999996 - type: recall_at_100 value: 65.654 - type: recall_at_1000 value: 84.492 - type: recall_at_3 value: 30.209000000000003 - type: recall_at_5 value: 35.616 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 17.756 - type: map_at_10 value: 30.378 - type: map_at_100 value: 32.537 - type: map_at_1000 value: 32.717 - type: map_at_3 value: 25.599 - type: map_at_5 value: 28.372999999999998 - type: mrr_at_1 value: 41.303 - type: mrr_at_10 value: 53.483999999999995 - type: mrr_at_100 value: 54.106 - type: mrr_at_1000 value: 54.127 - type: mrr_at_3 value: 50.315 - type: mrr_at_5 value: 52.396 - type: ndcg_at_1 value: 41.303 - type: ndcg_at_10 value: 40.503 - type: ndcg_at_100 value: 47.821000000000005 - type: ndcg_at_1000 value: 50.788 - type: ndcg_at_3 value: 34.364 - type: ndcg_at_5 value: 36.818 - type: precision_at_1 value: 41.303 - type: precision_at_10 value: 12.463000000000001 - type: precision_at_100 value: 2.037 - type: precision_at_1000 value: 0.26 - type: precision_at_3 value: 25.798 - type: precision_at_5 value: 19.896 - type: recall_at_1 value: 17.756 - type: recall_at_10 value: 46.102 - type: recall_at_100 value: 70.819 - type: recall_at_1000 value: 87.21799999999999 - type: recall_at_3 value: 30.646 - type: recall_at_5 value: 38.022 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 9.033 - type: map_at_10 value: 20.584 - type: map_at_100 value: 29.518 - type: map_at_1000 value: 31.186000000000003 - type: map_at_3 value: 14.468 - type: map_at_5 value: 17.177 - type: mrr_at_1 value: 69.75 - type: mrr_at_10 value: 77.025 - type: mrr_at_100 value: 77.36699999999999 - type: mrr_at_1000 value: 77.373 - type: mrr_at_3 value: 75.583 - type: mrr_at_5 value: 76.396 - type: ndcg_at_1 value: 58.5 - type: ndcg_at_10 value: 45.033 - type: ndcg_at_100 value: 49.071 - type: ndcg_at_1000 value: 56.056 - type: ndcg_at_3 value: 49.936 - type: ndcg_at_5 value: 47.471999999999994 - type: precision_at_1 value: 69.75 - type: precision_at_10 value: 35.775 - type: precision_at_100 value: 11.594999999999999 - type: precision_at_1000 value: 2.062 - type: precision_at_3 value: 52.5 - type: precision_at_5 value: 45.300000000000004 - type: recall_at_1 value: 9.033 - type: recall_at_10 value: 26.596999999999998 - type: recall_at_100 value: 54.607000000000006 - type: recall_at_1000 value: 76.961 - type: recall_at_3 value: 15.754999999999999 - type: recall_at_5 value: 20.033 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 48.345000000000006 - type: f1 value: 43.4514918068706 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 71.29100000000001 - type: map_at_10 value: 81.059 - type: map_at_100 value: 81.341 - type: map_at_1000 value: 81.355 - type: map_at_3 value: 79.74799999999999 - type: map_at_5 value: 80.612 - type: mrr_at_1 value: 76.40299999999999 - type: mrr_at_10 value: 84.615 - type: mrr_at_100 value: 84.745 - type: mrr_at_1000 value: 84.748 - type: mrr_at_3 value: 83.776 - type: mrr_at_5 value: 84.343 - type: ndcg_at_1 value: 76.40299999999999 - type: ndcg_at_10 value: 84.981 - type: ndcg_at_100 value: 86.00999999999999 - type: ndcg_at_1000 value: 86.252 - type: ndcg_at_3 value: 82.97 - type: ndcg_at_5 value: 84.152 - type: precision_at_1 value: 76.40299999999999 - type: precision_at_10 value: 10.446 - type: precision_at_100 value: 1.1199999999999999 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 32.147999999999996 - type: precision_at_5 value: 20.135 - type: recall_at_1 value: 71.29100000000001 - type: recall_at_10 value: 93.232 - type: recall_at_100 value: 97.363 - type: recall_at_1000 value: 98.905 - type: recall_at_3 value: 87.893 - type: recall_at_5 value: 90.804 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 18.667 - type: map_at_10 value: 30.853 - type: map_at_100 value: 32.494 - type: map_at_1000 value: 32.677 - type: map_at_3 value: 26.91 - type: map_at_5 value: 29.099000000000004 - type: mrr_at_1 value: 37.191 - type: mrr_at_10 value: 46.171 - type: mrr_at_100 value: 47.056 - type: mrr_at_1000 value: 47.099000000000004 - type: mrr_at_3 value: 44.059 - type: mrr_at_5 value: 45.147 - type: ndcg_at_1 value: 37.191 - type: ndcg_at_10 value: 38.437 - type: ndcg_at_100 value: 44.62 - type: ndcg_at_1000 value: 47.795 - type: ndcg_at_3 value: 35.003 - type: ndcg_at_5 value: 36.006 - type: precision_at_1 value: 37.191 - type: precision_at_10 value: 10.586 - type: precision_at_100 value: 1.688 - type: precision_at_1000 value: 0.22699999999999998 - type: precision_at_3 value: 23.302 - type: precision_at_5 value: 17.006 - type: recall_at_1 value: 18.667 - type: recall_at_10 value: 45.367000000000004 - type: recall_at_100 value: 68.207 - type: recall_at_1000 value: 87.072 - type: recall_at_3 value: 32.129000000000005 - type: recall_at_5 value: 37.719 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 39.494 - type: map_at_10 value: 66.223 - type: map_at_100 value: 67.062 - type: map_at_1000 value: 67.11500000000001 - type: map_at_3 value: 62.867 - type: map_at_5 value: 64.994 - type: mrr_at_1 value: 78.987 - type: mrr_at_10 value: 84.585 - type: mrr_at_100 value: 84.773 - type: mrr_at_1000 value: 84.77900000000001 - type: mrr_at_3 value: 83.592 - type: mrr_at_5 value: 84.235 - type: ndcg_at_1 value: 78.987 - type: ndcg_at_10 value: 73.64 - type: ndcg_at_100 value: 76.519 - type: ndcg_at_1000 value: 77.51 - type: ndcg_at_3 value: 68.893 - type: ndcg_at_5 value: 71.585 - type: precision_at_1 value: 78.987 - type: precision_at_10 value: 15.529000000000002 - type: precision_at_100 value: 1.7770000000000001 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 44.808 - type: precision_at_5 value: 29.006999999999998 - type: recall_at_1 value: 39.494 - type: recall_at_10 value: 77.643 - type: recall_at_100 value: 88.825 - type: recall_at_1000 value: 95.321 - type: recall_at_3 value: 67.211 - type: recall_at_5 value: 72.519 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 85.55959999999999 - type: ap value: 80.7246500384617 - type: f1 value: 85.52336485065454 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 23.631 - type: map_at_10 value: 36.264 - type: map_at_100 value: 37.428 - type: map_at_1000 value: 37.472 - type: map_at_3 value: 32.537 - type: map_at_5 value: 34.746 - type: mrr_at_1 value: 24.312 - type: mrr_at_10 value: 36.858000000000004 - type: mrr_at_100 value: 37.966 - type: mrr_at_1000 value: 38.004 - type: mrr_at_3 value: 33.188 - type: mrr_at_5 value: 35.367 - type: ndcg_at_1 value: 24.312 - type: ndcg_at_10 value: 43.126999999999995 - type: ndcg_at_100 value: 48.642 - type: ndcg_at_1000 value: 49.741 - type: ndcg_at_3 value: 35.589 - type: ndcg_at_5 value: 39.515 - type: precision_at_1 value: 24.312 - type: precision_at_10 value: 6.699 - type: precision_at_100 value: 0.9450000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 15.153 - type: precision_at_5 value: 11.065999999999999 - type: recall_at_1 value: 23.631 - type: recall_at_10 value: 64.145 - type: recall_at_100 value: 89.41 - type: recall_at_1000 value: 97.83500000000001 - type: recall_at_3 value: 43.769000000000005 - type: recall_at_5 value: 53.169 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.4108527131783 - type: f1 value: 93.1415880261038 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 77.24806201550388 - type: f1 value: 60.531916308197175 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 73.71553463349024 - type: f1 value: 71.70753174900791 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.79757901815736 - type: f1 value: 77.83719850433258 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 33.74193296622113 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 30.64257594108566 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.811018518883625 - type: mrr value: 31.910376577445003 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.409 - type: map_at_10 value: 13.093 - type: map_at_100 value: 16.256999999999998 - type: map_at_1000 value: 17.617 - type: map_at_3 value: 9.555 - type: map_at_5 value: 11.428 - type: mrr_at_1 value: 45.201 - type: mrr_at_10 value: 54.179 - type: mrr_at_100 value: 54.812000000000005 - type: mrr_at_1000 value: 54.840999999999994 - type: mrr_at_3 value: 51.909000000000006 - type: mrr_at_5 value: 53.519000000000005 - type: ndcg_at_1 value: 43.189 - type: ndcg_at_10 value: 35.028 - type: ndcg_at_100 value: 31.226 - type: ndcg_at_1000 value: 39.678000000000004 - type: ndcg_at_3 value: 40.596 - type: ndcg_at_5 value: 38.75 - type: precision_at_1 value: 44.582 - type: precision_at_10 value: 25.974999999999998 - type: precision_at_100 value: 7.793 - type: precision_at_1000 value: 2.036 - type: precision_at_3 value: 38.493 - type: precision_at_5 value: 33.994 - type: recall_at_1 value: 5.409 - type: recall_at_10 value: 16.875999999999998 - type: recall_at_100 value: 30.316 - type: recall_at_1000 value: 60.891 - type: recall_at_3 value: 10.688 - type: recall_at_5 value: 13.832 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 36.375 - type: map_at_10 value: 51.991 - type: map_at_100 value: 52.91400000000001 - type: map_at_1000 value: 52.93600000000001 - type: map_at_3 value: 48.014 - type: map_at_5 value: 50.381 - type: mrr_at_1 value: 40.759 - type: mrr_at_10 value: 54.617000000000004 - type: mrr_at_100 value: 55.301 - type: mrr_at_1000 value: 55.315000000000005 - type: mrr_at_3 value: 51.516 - type: mrr_at_5 value: 53.435 - type: ndcg_at_1 value: 40.759 - type: ndcg_at_10 value: 59.384 - type: ndcg_at_100 value: 63.157 - type: ndcg_at_1000 value: 63.654999999999994 - type: ndcg_at_3 value: 52.114000000000004 - type: ndcg_at_5 value: 55.986000000000004 - type: precision_at_1 value: 40.759 - type: precision_at_10 value: 9.411999999999999 - type: precision_at_100 value: 1.153 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 23.329 - type: precision_at_5 value: 16.256999999999998 - type: recall_at_1 value: 36.375 - type: recall_at_10 value: 79.053 - type: recall_at_100 value: 95.167 - type: recall_at_1000 value: 98.82 - type: recall_at_3 value: 60.475 - type: recall_at_5 value: 69.327 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 70.256 - type: map_at_10 value: 83.8 - type: map_at_100 value: 84.425 - type: map_at_1000 value: 84.444 - type: map_at_3 value: 80.906 - type: map_at_5 value: 82.717 - type: mrr_at_1 value: 80.97999999999999 - type: mrr_at_10 value: 87.161 - type: mrr_at_100 value: 87.262 - type: mrr_at_1000 value: 87.263 - type: mrr_at_3 value: 86.175 - type: mrr_at_5 value: 86.848 - type: ndcg_at_1 value: 80.97999999999999 - type: ndcg_at_10 value: 87.697 - type: ndcg_at_100 value: 88.959 - type: ndcg_at_1000 value: 89.09899999999999 - type: ndcg_at_3 value: 84.83800000000001 - type: ndcg_at_5 value: 86.401 - type: precision_at_1 value: 80.97999999999999 - type: precision_at_10 value: 13.261000000000001 - type: precision_at_100 value: 1.5150000000000001 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 37.01 - type: precision_at_5 value: 24.298000000000002 - type: recall_at_1 value: 70.256 - type: recall_at_10 value: 94.935 - type: recall_at_100 value: 99.274 - type: recall_at_1000 value: 99.928 - type: recall_at_3 value: 86.602 - type: recall_at_5 value: 91.133 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.322692497613104 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 61.895813503775074 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.338 - type: map_at_10 value: 10.767 - type: map_at_100 value: 12.537999999999998 - type: map_at_1000 value: 12.803999999999998 - type: map_at_3 value: 7.788 - type: map_at_5 value: 9.302000000000001 - type: mrr_at_1 value: 21.4 - type: mrr_at_10 value: 31.637999999999998 - type: mrr_at_100 value: 32.688 - type: mrr_at_1000 value: 32.756 - type: mrr_at_3 value: 28.433000000000003 - type: mrr_at_5 value: 30.178 - type: ndcg_at_1 value: 21.4 - type: ndcg_at_10 value: 18.293 - type: ndcg_at_100 value: 25.274 - type: ndcg_at_1000 value: 30.284 - type: ndcg_at_3 value: 17.391000000000002 - type: ndcg_at_5 value: 15.146999999999998 - type: precision_at_1 value: 21.4 - type: precision_at_10 value: 9.48 - type: precision_at_100 value: 1.949 - type: precision_at_1000 value: 0.316 - type: precision_at_3 value: 16.167 - type: precision_at_5 value: 13.22 - type: recall_at_1 value: 4.338 - type: recall_at_10 value: 19.213 - type: recall_at_100 value: 39.562999999999995 - type: recall_at_1000 value: 64.08 - type: recall_at_3 value: 9.828000000000001 - type: recall_at_5 value: 13.383000000000001 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.42568163642142 - type: cos_sim_spearman value: 78.5797159641342 - type: euclidean_pearson value: 80.22151260811604 - type: euclidean_spearman value: 78.5797151953878 - type: manhattan_pearson value: 80.21224215864788 - type: manhattan_spearman value: 78.55641478381344 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 85.44020710812569 - type: cos_sim_spearman value: 78.91631735081286 - type: euclidean_pearson value: 81.64188964182102 - type: euclidean_spearman value: 78.91633286881678 - type: manhattan_pearson value: 81.69294748512496 - type: manhattan_spearman value: 78.93438558002656 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 84.27165426412311 - type: cos_sim_spearman value: 85.40429140249618 - type: euclidean_pearson value: 84.7509580724893 - type: euclidean_spearman value: 85.40429140249618 - type: manhattan_pearson value: 84.76488289321308 - type: manhattan_spearman value: 85.4256793698708 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 83.138851760732 - type: cos_sim_spearman value: 81.64101363896586 - type: euclidean_pearson value: 82.55165038934942 - type: euclidean_spearman value: 81.64105257080502 - type: manhattan_pearson value: 82.52802949883335 - type: manhattan_spearman value: 81.61255430718158 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 86.0654695484029 - type: cos_sim_spearman value: 87.20408521902229 - type: euclidean_pearson value: 86.8110651362115 - type: euclidean_spearman value: 87.20408521902229 - type: manhattan_pearson value: 86.77984656478691 - type: manhattan_spearman value: 87.1719947099227 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 83.77823915496512 - type: cos_sim_spearman value: 85.43566325729779 - type: euclidean_pearson value: 84.5396956658821 - type: euclidean_spearman value: 85.43566325729779 - type: manhattan_pearson value: 84.5665398848169 - type: manhattan_spearman value: 85.44375870303232 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.20030208471798 - type: cos_sim_spearman value: 87.20485505076539 - type: euclidean_pearson value: 88.10588324368722 - type: euclidean_spearman value: 87.20485505076539 - type: manhattan_pearson value: 87.92324770415183 - type: manhattan_spearman value: 87.0571314561877 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 63.06093161604453 - type: cos_sim_spearman value: 64.2163140357722 - type: euclidean_pearson value: 65.27589680994006 - type: euclidean_spearman value: 64.2163140357722 - type: manhattan_pearson value: 65.45904383711101 - type: manhattan_spearman value: 64.55404716679305 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 84.32976164578706 - type: cos_sim_spearman value: 85.54302197678368 - type: euclidean_pearson value: 85.26307149193056 - type: euclidean_spearman value: 85.54302197678368 - type: manhattan_pearson value: 85.26647282029371 - type: manhattan_spearman value: 85.5316135265568 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 81.44675968318754 - type: mrr value: 94.92741826075158 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 56.34400000000001 - type: map_at_10 value: 65.927 - type: map_at_100 value: 66.431 - type: map_at_1000 value: 66.461 - type: map_at_3 value: 63.529 - type: map_at_5 value: 64.818 - type: mrr_at_1 value: 59.333000000000006 - type: mrr_at_10 value: 67.54599999999999 - type: mrr_at_100 value: 67.892 - type: mrr_at_1000 value: 67.917 - type: mrr_at_3 value: 65.778 - type: mrr_at_5 value: 66.794 - type: ndcg_at_1 value: 59.333000000000006 - type: ndcg_at_10 value: 70.5 - type: ndcg_at_100 value: 72.688 - type: ndcg_at_1000 value: 73.483 - type: ndcg_at_3 value: 66.338 - type: ndcg_at_5 value: 68.265 - type: precision_at_1 value: 59.333000000000006 - type: precision_at_10 value: 9.3 - type: precision_at_100 value: 1.053 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 25.889 - type: precision_at_5 value: 16.866999999999997 - type: recall_at_1 value: 56.34400000000001 - type: recall_at_10 value: 82.789 - type: recall_at_100 value: 92.767 - type: recall_at_1000 value: 99 - type: recall_at_3 value: 71.64399999999999 - type: recall_at_5 value: 76.322 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.75742574257426 - type: cos_sim_ap value: 93.52081548447406 - type: cos_sim_f1 value: 87.33850129198966 - type: cos_sim_precision value: 90.37433155080214 - type: cos_sim_recall value: 84.5 - type: dot_accuracy value: 99.75742574257426 - type: dot_ap value: 93.52081548447406 - type: dot_f1 value: 87.33850129198966 - type: dot_precision value: 90.37433155080214 - type: dot_recall value: 84.5 - type: euclidean_accuracy value: 99.75742574257426 - type: euclidean_ap value: 93.52081548447406 - type: euclidean_f1 value: 87.33850129198966 - type: euclidean_precision value: 90.37433155080214 - type: euclidean_recall value: 84.5 - type: manhattan_accuracy value: 99.75841584158415 - type: manhattan_ap value: 93.4975678585854 - type: manhattan_f1 value: 87.26708074534162 - type: manhattan_precision value: 90.45064377682404 - type: manhattan_recall value: 84.3 - type: max_accuracy value: 99.75841584158415 - type: max_ap value: 93.52081548447406 - type: max_f1 value: 87.33850129198966 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 64.31437036686651 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 33.25569319007206 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 49.90474939720706 - type: mrr value: 50.568115503777264 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 29.866828641244712 - type: cos_sim_spearman value: 30.077555055873866 - type: dot_pearson value: 29.866832988572266 - type: dot_spearman value: 30.077555055873866 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.232 - type: map_at_10 value: 2.094 - type: map_at_100 value: 11.971 - type: map_at_1000 value: 28.158 - type: map_at_3 value: 0.688 - type: map_at_5 value: 1.114 - type: mrr_at_1 value: 88 - type: mrr_at_10 value: 93.4 - type: mrr_at_100 value: 93.4 - type: mrr_at_1000 value: 93.4 - type: mrr_at_3 value: 93 - type: mrr_at_5 value: 93.4 - type: ndcg_at_1 value: 84 - type: ndcg_at_10 value: 79.923 - type: ndcg_at_100 value: 61.17 - type: ndcg_at_1000 value: 53.03 - type: ndcg_at_3 value: 84.592 - type: ndcg_at_5 value: 82.821 - type: precision_at_1 value: 88 - type: precision_at_10 value: 85 - type: precision_at_100 value: 63.019999999999996 - type: precision_at_1000 value: 23.554 - type: precision_at_3 value: 89.333 - type: precision_at_5 value: 87.2 - type: recall_at_1 value: 0.232 - type: recall_at_10 value: 2.255 - type: recall_at_100 value: 14.823 - type: recall_at_1000 value: 49.456 - type: recall_at_3 value: 0.718 - type: recall_at_5 value: 1.175 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.547 - type: map_at_10 value: 11.375 - type: map_at_100 value: 18.194 - type: map_at_1000 value: 19.749 - type: map_at_3 value: 5.825 - type: map_at_5 value: 8.581 - type: mrr_at_1 value: 32.653 - type: mrr_at_10 value: 51.32 - type: mrr_at_100 value: 51.747 - type: mrr_at_1000 value: 51.747 - type: mrr_at_3 value: 47.278999999999996 - type: mrr_at_5 value: 48.605 - type: ndcg_at_1 value: 29.592000000000002 - type: ndcg_at_10 value: 28.151 - type: ndcg_at_100 value: 39.438 - type: ndcg_at_1000 value: 50.769 - type: ndcg_at_3 value: 30.758999999999997 - type: ndcg_at_5 value: 30.366 - type: precision_at_1 value: 32.653 - type: precision_at_10 value: 25.714 - type: precision_at_100 value: 8.041 - type: precision_at_1000 value: 1.555 - type: precision_at_3 value: 33.333 - type: precision_at_5 value: 31.837 - type: recall_at_1 value: 2.547 - type: recall_at_10 value: 18.19 - type: recall_at_100 value: 49.538 - type: recall_at_1000 value: 83.86 - type: recall_at_3 value: 7.329 - type: recall_at_5 value: 11.532 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.4952 - type: ap value: 14.793362635531409 - type: f1 value: 55.204635551516915 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 61.5365025466893 - type: f1 value: 61.81742556334845 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 49.05531070301185 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.51725576682364 - type: cos_sim_ap value: 75.2292304265163 - type: cos_sim_f1 value: 69.54022988505749 - type: cos_sim_precision value: 63.65629110039457 - type: cos_sim_recall value: 76.62269129287598 - type: dot_accuracy value: 86.51725576682364 - type: dot_ap value: 75.22922386081054 - type: dot_f1 value: 69.54022988505749 - type: dot_precision value: 63.65629110039457 - type: dot_recall value: 76.62269129287598 - type: euclidean_accuracy value: 86.51725576682364 - type: euclidean_ap value: 75.22925730473472 - type: euclidean_f1 value: 69.54022988505749 - type: euclidean_precision value: 63.65629110039457 - type: euclidean_recall value: 76.62269129287598 - type: manhattan_accuracy value: 86.52321630804077 - type: manhattan_ap value: 75.20608115037336 - type: manhattan_f1 value: 69.60000000000001 - type: manhattan_precision value: 64.37219730941705 - type: manhattan_recall value: 75.75197889182058 - type: max_accuracy value: 86.52321630804077 - type: max_ap value: 75.22925730473472 - type: max_f1 value: 69.60000000000001 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.34877944657896 - type: cos_sim_ap value: 86.71257569277373 - type: cos_sim_f1 value: 79.10386355986088 - type: cos_sim_precision value: 76.91468470434214 - type: cos_sim_recall value: 81.4213119802895 - type: dot_accuracy value: 89.34877944657896 - type: dot_ap value: 86.71257133133368 - type: dot_f1 value: 79.10386355986088 - type: dot_precision value: 76.91468470434214 - type: dot_recall value: 81.4213119802895 - type: euclidean_accuracy value: 89.34877944657896 - type: euclidean_ap value: 86.71257651501476 - type: euclidean_f1 value: 79.10386355986088 - type: euclidean_precision value: 76.91468470434214 - type: euclidean_recall value: 81.4213119802895 - type: manhattan_accuracy value: 89.35848177901967 - type: manhattan_ap value: 86.69330615469126 - type: manhattan_f1 value: 79.13867741453949 - type: manhattan_precision value: 76.78881807647741 - type: manhattan_recall value: 81.63689559593472 - type: max_accuracy value: 89.35848177901967 - type: max_ap value: 86.71257651501476 - type: max_f1 value: 79.13867741453949 license: apache-2.0 language: - en --- # nomic-embed-text-v1: A Reproducible Long Context (8192) Text Embedder `nomic-embed-text-v1` is 8192 context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks. \| Name \| SeqLen \| MTEB \| LoCo \| Jina Long Context \| Open Weights \| Open Training Code \| Open Data \| \| :-------------------------------:\| :----- \| :-------- \| :------: \| :---------------: \| :-----------: \| :----------------: \| :---------- \| \| nomic-embed-text-v1 \| 8192 \| 62.39 \|85.53 \| 54.16 \| ✅ \| ✅ \| ✅ \| \| jina-embeddings-v2-base-en \| 8192 \| 60.39 \| 85.45 \| 51.90 \| ✅ \| ❌ \| ❌ \| \| text-embedding-3-small \| 8191 \| 62.26 \| 82.40 \| 58.20 \| ❌ \| ❌ \| ❌ \| \| text-embedding-ada-002 \| 8191 \| 60.99 \| 52.7 \| 55.25 \| ❌ \| ❌ \| ❌ \| ## Hosted Inference API The easiest way to get started with Nomic Embed is through the Nomic Embedding API. Generating embeddings with the `nomic` Python client is as easy as ```python from nomic import embed output = embed.text( texts=['Nomic Embedding API', '#keepAIOpen'], model='nomic-embed-text-v1', task_type='search_document' ) print(output) ``` For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text) ## Data Visualization Click the Nomic Atlas map below to visualize a 5M sample of our contrastive pretraining data! [![image/webp](https://cdn-uploads.huggingface.co/production/uploads/607997c83a565c15675055b3/pjhJhuNyRfPagRd_c_iUz.webp)](https://atlas.nomic.ai/map/nomic-text-embed-v1-5m-sample) ## Training Details We train our embedder using a multi-stage training pipeline. Starting from a long-context [BERT model](https://huggingface.co/nomic-ai/nomic-bert-2048), the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles. In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage. For more details, see the Nomic Embed [Technical Report](https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf) and corresponding [blog post](https://blog.nomic.ai/posts/nomic-embed-text-v1). Training data to train the models is released in its entirety. For more details, see the `contrastors` [repository](https://github.com/nomic-ai/contrastors) ## Usage Note `nomic-embed-text` requires prefixes! We support the prefixes `[search_query, search_document, classification, clustering]`. For retrieval applications, you should prepend `search_document` for all your documents and `search_query` for your queries. For example, you are building a RAG application over the top of Wikipedia. You would embed all Wikipedia articles with the prefix `search_document` and any questions you ask with `search_query`. For example: ```python queries = ["search_query: who is the first president of the united states?", "search_query: when was babe ruth born?"] documents = ["search_document: <article about US Presidents>", "search_document: <article about Babe Ruth>"] ``` ### Sentence Transformers ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] embeddings = model.encode(sentences) print(embeddings) ``` ### Transformers ```python import torch import torch.nn.functional as F from transformers import AutoTokenizer, AutoModel def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) model.eval() encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') with torch.no_grad(): model_output = model(**encoded_input) embeddings = mean_pooling(model_output, encoded_input['attention_mask']) embeddings = F.normalize(embeddings, p=2, dim=1) print(embeddings) ``` The model natively supports scaling of the sequence length past 2048 tokens. To do so, ```diff - tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') + tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192) - model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) + model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2) ``` ### Transformers.js ```js import { pipeline } from '@xenova/transformers'; // Create a feature extraction pipeline const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1', { quantized: false, // Comment out this line to use the quantized version }); // Compute sentence embeddings const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']; const embeddings = await extractor(texts, { pooling: 'mean', normalize: true }); console.log(embeddings); ``` # Join the Nomic Community - Nomic: [https://nomic.ai](https://nomic.ai) - Discord: [https://discord.gg/myY5YDR8z8](https://discord.gg/myY5YDR8z8) - Twitter: [https://twitter.com/nomic_ai](https://twitter.com/nomic_ai) # Citation If you find the model, dataset, or training code useful, please cite our work ```bibtex @misc{nussbaum2024nomic, title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar}, year={2024}, eprint={2402.01613}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
mradermacher/Elysium2.1-11b-i1-GGUF	mradermacher	"2024-06-12T00:05:27Z"	2,592	0	transformers	[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "powermove72/Trinity_Notus-xb", "powermove72/GreenScorpius-xb-Passthrough", "en", "base_model:powermove72/Elysium2.1-11b", "endpoints_compatible", "region:us" ]	null	"2024-06-11T16:57:37Z"	--- base_model: powermove72/Elysium2.1-11b language: - en library_name: transformers quantized_by: mradermacher tags: - merge - mergekit - lazymergekit - powermove72/Trinity_Notus-xb - powermove72/GreenScorpius-xb-Passthrough --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/powermove72/Elysium2.1-11b <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.5 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.8 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 3.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 3.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ2_S.gguf) \| i1-IQ2_S \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q2_K.gguf) \| i1-Q2_K \| 4.3 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 4.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 4.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 5.0 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ3_S.gguf) \| i1-IQ3_S \| 5.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ3_M.gguf) \| i1-IQ3_M \| 5.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 5.5 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 6.0 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 6.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q4_0.gguf) \| i1-Q4_0 \| 6.4 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 6.5 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 6.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 7.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 8.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q6_K.gguf) \| i1-Q6_K \| 9.3 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants. <!-- end -->
NOVA-vision-language/task-intent-detector	NOVA-vision-language	"2024-05-15T10:57:19Z"	2,591	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	"2024-05-14T20:52:16Z"	Here's an adapted TWIZ intent detection model, trained on the TWIZ dataset, with an extra focus on simplicity! It achieves ~85% accuracy on the TWIZ test set, and should be especially useful for the WSDM students @ NOVA. I STRONGLY suggest interested students to check `model_code` in the `Files and versions` tab, where all the code used to get to the model (with the exception of actually uploading it here) is laid out nicely (I hope!) Here's the contents of `intent-detection-example.ipynb`, if you're just looking to use the model: ```python with open("twiz-data/all_intents.json", 'r') as json_in: # all_intents.json can be found in the task-intent-detector/model_code directory data = json.load(json_in) id_to_intent, intent_to_id = dict(), dict() for i, intent in enumerate(data): id_to_intent[i] = intent intent_to_id[intent] = i model = AutoModelForSequenceClassification.from_pretrained("NOVA-vision-language/task-intent-detector", num_labels=len(data), id2label=id_to_intent, label2id=intent_to_id) tokenizer = AutoTokenizer.from_pretrained("roberta-base") # you could try 'NOVA-vision-language/task-intent-detector', but I'm not sure I configured it correctly model_in = tokenizer("I really really wanna go to the next step", return_tensors='pt') with torch.no_grad(): logits = model(**model_in).logits # grab the predictions out of the model's classification head predicted_class_id = logits.argmax().item() # grab the index of the highest scoring output print(model.config.id2label[predicted_class_id]) # use the translation table we just created to translate between that id and the actual intent name ```
jacobhoffmann/codegemma-2b-GGUF	jacobhoffmann	"2024-06-05T11:54:12Z"	2,591	0	null	[ "gguf", "region:us" ]	null	"2024-06-05T11:26:01Z"	Entry not found
CAiRE/UniVaR-lambda-5	CAiRE	"2024-06-14T17:57:41Z"	2,591	0	sentence-transformers	[ "sentence-transformers", "safetensors", "nomic_bert", "feature-extraction", "sentence-similarity", "mteb", "transformers", "transformers.js", "custom_code", "en", "arxiv:2402.01613", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-embeddings-inference", "region:us" ]	sentence-similarity	"2024-06-14T17:57:09Z"	--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - feature-extraction - sentence-similarity - mteb - transformers - transformers.js model-index: - name: epoch_0_model results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 76.8507462686567 - type: ap value: 40.592189159090495 - type: f1 value: 71.01634655512476 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 91.51892500000001 - type: ap value: 88.50346762975335 - type: f1 value: 91.50342077459624 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 47.364 - type: f1 value: 46.72708080922794 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 25.178 - type: map_at_10 value: 40.244 - type: map_at_100 value: 41.321999999999996 - type: map_at_1000 value: 41.331 - type: map_at_3 value: 35.016999999999996 - type: map_at_5 value: 37.99 - type: mrr_at_1 value: 25.605 - type: mrr_at_10 value: 40.422000000000004 - type: mrr_at_100 value: 41.507 - type: mrr_at_1000 value: 41.516 - type: mrr_at_3 value: 35.23 - type: mrr_at_5 value: 38.15 - type: ndcg_at_1 value: 25.178 - type: ndcg_at_10 value: 49.258 - type: ndcg_at_100 value: 53.776 - type: ndcg_at_1000 value: 53.995000000000005 - type: ndcg_at_3 value: 38.429 - type: ndcg_at_5 value: 43.803 - type: precision_at_1 value: 25.178 - type: precision_at_10 value: 7.831 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 16.121 - type: precision_at_5 value: 12.29 - type: recall_at_1 value: 25.178 - type: recall_at_10 value: 78.307 - type: recall_at_100 value: 97.866 - type: recall_at_1000 value: 99.57300000000001 - type: recall_at_3 value: 48.364000000000004 - type: recall_at_5 value: 61.451 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 45.93034494751465 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 36.64579480054327 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 60.601310529222054 - type: mrr value: 75.04484896451656 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 88.57797718095814 - type: cos_sim_spearman value: 86.47064499110101 - type: euclidean_pearson value: 87.4559602783142 - type: euclidean_spearman value: 86.47064499110101 - type: manhattan_pearson value: 87.7232764230245 - type: manhattan_spearman value: 86.91222131777742 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 84.5422077922078 - type: f1 value: 84.47657456950589 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 38.48953561974464 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.75995857510105 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.008000000000003 - type: map_at_10 value: 39.51 - type: map_at_100 value: 40.841 - type: map_at_1000 value: 40.973 - type: map_at_3 value: 36.248999999999995 - type: map_at_5 value: 38.096999999999994 - type: mrr_at_1 value: 36.481 - type: mrr_at_10 value: 44.818000000000005 - type: mrr_at_100 value: 45.64 - type: mrr_at_1000 value: 45.687 - type: mrr_at_3 value: 42.036 - type: mrr_at_5 value: 43.782 - type: ndcg_at_1 value: 36.481 - type: ndcg_at_10 value: 45.152 - type: ndcg_at_100 value: 50.449 - type: ndcg_at_1000 value: 52.76499999999999 - type: ndcg_at_3 value: 40.161 - type: ndcg_at_5 value: 42.577999999999996 - type: precision_at_1 value: 36.481 - type: precision_at_10 value: 8.369 - type: precision_at_100 value: 1.373 - type: precision_at_1000 value: 0.186 - type: precision_at_3 value: 18.693 - type: precision_at_5 value: 13.533999999999999 - type: recall_at_1 value: 30.008000000000003 - type: recall_at_10 value: 56.108999999999995 - type: recall_at_100 value: 78.55499999999999 - type: recall_at_1000 value: 93.659 - type: recall_at_3 value: 41.754999999999995 - type: recall_at_5 value: 48.296 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.262 - type: map_at_10 value: 40.139 - type: map_at_100 value: 41.394 - type: map_at_1000 value: 41.526 - type: map_at_3 value: 37.155 - type: map_at_5 value: 38.785 - type: mrr_at_1 value: 38.153 - type: mrr_at_10 value: 46.369 - type: mrr_at_100 value: 47.072 - type: mrr_at_1000 value: 47.111999999999995 - type: mrr_at_3 value: 44.268 - type: mrr_at_5 value: 45.389 - type: ndcg_at_1 value: 38.153 - type: ndcg_at_10 value: 45.925 - type: ndcg_at_100 value: 50.394000000000005 - type: ndcg_at_1000 value: 52.37500000000001 - type: ndcg_at_3 value: 41.754000000000005 - type: ndcg_at_5 value: 43.574 - type: precision_at_1 value: 38.153 - type: precision_at_10 value: 8.796 - type: precision_at_100 value: 1.432 - type: precision_at_1000 value: 0.189 - type: precision_at_3 value: 20.318 - type: precision_at_5 value: 14.395 - type: recall_at_1 value: 30.262 - type: recall_at_10 value: 55.72200000000001 - type: recall_at_100 value: 74.97500000000001 - type: recall_at_1000 value: 87.342 - type: recall_at_3 value: 43.129 - type: recall_at_5 value: 48.336 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 39.951 - type: map_at_10 value: 51.248000000000005 - type: map_at_100 value: 52.188 - type: map_at_1000 value: 52.247 - type: map_at_3 value: 48.211 - type: map_at_5 value: 49.797000000000004 - type: mrr_at_1 value: 45.329 - type: mrr_at_10 value: 54.749 - type: mrr_at_100 value: 55.367999999999995 - type: mrr_at_1000 value: 55.400000000000006 - type: mrr_at_3 value: 52.382 - type: mrr_at_5 value: 53.649 - type: ndcg_at_1 value: 45.329 - type: ndcg_at_10 value: 56.847 - type: ndcg_at_100 value: 60.738 - type: ndcg_at_1000 value: 61.976 - type: ndcg_at_3 value: 51.59 - type: ndcg_at_5 value: 53.915 - type: precision_at_1 value: 45.329 - type: precision_at_10 value: 8.959 - type: precision_at_100 value: 1.187 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 22.612 - type: precision_at_5 value: 15.273 - type: recall_at_1 value: 39.951 - type: recall_at_10 value: 70.053 - type: recall_at_100 value: 86.996 - type: recall_at_1000 value: 95.707 - type: recall_at_3 value: 56.032000000000004 - type: recall_at_5 value: 61.629999999999995 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.566 - type: map_at_10 value: 33.207 - type: map_at_100 value: 34.166000000000004 - type: map_at_1000 value: 34.245 - type: map_at_3 value: 30.94 - type: map_at_5 value: 32.01 - type: mrr_at_1 value: 27.345000000000002 - type: mrr_at_10 value: 35.193000000000005 - type: mrr_at_100 value: 35.965 - type: mrr_at_1000 value: 36.028999999999996 - type: mrr_at_3 value: 32.806000000000004 - type: mrr_at_5 value: 34.021 - type: ndcg_at_1 value: 27.345000000000002 - type: ndcg_at_10 value: 37.891999999999996 - type: ndcg_at_100 value: 42.664 - type: ndcg_at_1000 value: 44.757000000000005 - type: ndcg_at_3 value: 33.123000000000005 - type: ndcg_at_5 value: 35.035 - type: precision_at_1 value: 27.345000000000002 - type: precision_at_10 value: 5.763 - type: precision_at_100 value: 0.859 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 13.71 - type: precision_at_5 value: 9.401 - type: recall_at_1 value: 25.566 - type: recall_at_10 value: 50.563 - type: recall_at_100 value: 72.86399999999999 - type: recall_at_1000 value: 88.68599999999999 - type: recall_at_3 value: 37.43 - type: recall_at_5 value: 41.894999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.663 - type: map_at_10 value: 23.552 - type: map_at_100 value: 24.538 - type: map_at_1000 value: 24.661 - type: map_at_3 value: 21.085 - type: map_at_5 value: 22.391 - type: mrr_at_1 value: 20.025000000000002 - type: mrr_at_10 value: 27.643 - type: mrr_at_100 value: 28.499999999999996 - type: mrr_at_1000 value: 28.582 - type: mrr_at_3 value: 25.083 - type: mrr_at_5 value: 26.544 - type: ndcg_at_1 value: 20.025000000000002 - type: ndcg_at_10 value: 28.272000000000002 - type: ndcg_at_100 value: 33.353 - type: ndcg_at_1000 value: 36.454 - type: ndcg_at_3 value: 23.579 - type: ndcg_at_5 value: 25.685000000000002 - type: precision_at_1 value: 20.025000000000002 - type: precision_at_10 value: 5.187 - type: precision_at_100 value: 0.897 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 10.987 - type: precision_at_5 value: 8.06 - type: recall_at_1 value: 16.663 - type: recall_at_10 value: 38.808 - type: recall_at_100 value: 61.305 - type: recall_at_1000 value: 83.571 - type: recall_at_3 value: 25.907999999999998 - type: recall_at_5 value: 31.214 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.695999999999998 - type: map_at_10 value: 37.018 - type: map_at_100 value: 38.263000000000005 - type: map_at_1000 value: 38.371 - type: map_at_3 value: 34.226 - type: map_at_5 value: 35.809999999999995 - type: mrr_at_1 value: 32.916000000000004 - type: mrr_at_10 value: 42.067 - type: mrr_at_100 value: 42.925000000000004 - type: mrr_at_1000 value: 42.978 - type: mrr_at_3 value: 39.637 - type: mrr_at_5 value: 41.134 - type: ndcg_at_1 value: 32.916000000000004 - type: ndcg_at_10 value: 42.539 - type: ndcg_at_100 value: 47.873 - type: ndcg_at_1000 value: 50.08200000000001 - type: ndcg_at_3 value: 37.852999999999994 - type: ndcg_at_5 value: 40.201 - type: precision_at_1 value: 32.916000000000004 - type: precision_at_10 value: 7.5840000000000005 - type: precision_at_100 value: 1.199 - type: precision_at_1000 value: 0.155 - type: precision_at_3 value: 17.485 - type: precision_at_5 value: 12.512 - type: recall_at_1 value: 27.695999999999998 - type: recall_at_10 value: 53.638 - type: recall_at_100 value: 76.116 - type: recall_at_1000 value: 91.069 - type: recall_at_3 value: 41.13 - type: recall_at_5 value: 46.872 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.108 - type: map_at_10 value: 33.372 - type: map_at_100 value: 34.656 - type: map_at_1000 value: 34.768 - type: map_at_3 value: 30.830999999999996 - type: map_at_5 value: 32.204 - type: mrr_at_1 value: 29.110000000000003 - type: mrr_at_10 value: 37.979 - type: mrr_at_100 value: 38.933 - type: mrr_at_1000 value: 38.988 - type: mrr_at_3 value: 35.731 - type: mrr_at_5 value: 36.963 - type: ndcg_at_1 value: 29.110000000000003 - type: ndcg_at_10 value: 38.635000000000005 - type: ndcg_at_100 value: 44.324999999999996 - type: ndcg_at_1000 value: 46.747 - type: ndcg_at_3 value: 34.37 - type: ndcg_at_5 value: 36.228 - type: precision_at_1 value: 29.110000000000003 - type: precision_at_10 value: 6.963 - type: precision_at_100 value: 1.146 - type: precision_at_1000 value: 0.152 - type: precision_at_3 value: 16.400000000000002 - type: precision_at_5 value: 11.552999999999999 - type: recall_at_1 value: 24.108 - type: recall_at_10 value: 49.597 - type: recall_at_100 value: 73.88900000000001 - type: recall_at_1000 value: 90.62400000000001 - type: recall_at_3 value: 37.662 - type: recall_at_5 value: 42.565 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.00791666666667 - type: map_at_10 value: 33.287749999999996 - type: map_at_100 value: 34.41141666666667 - type: map_at_1000 value: 34.52583333333333 - type: map_at_3 value: 30.734416666666668 - type: map_at_5 value: 32.137166666666666 - type: mrr_at_1 value: 29.305666666666664 - type: mrr_at_10 value: 37.22966666666666 - type: mrr_at_100 value: 38.066583333333334 - type: mrr_at_1000 value: 38.12616666666667 - type: mrr_at_3 value: 34.92275 - type: mrr_at_5 value: 36.23333333333334 - type: ndcg_at_1 value: 29.305666666666664 - type: ndcg_at_10 value: 38.25533333333333 - type: ndcg_at_100 value: 43.25266666666666 - type: ndcg_at_1000 value: 45.63583333333334 - type: ndcg_at_3 value: 33.777166666666666 - type: ndcg_at_5 value: 35.85 - type: precision_at_1 value: 29.305666666666664 - type: precision_at_10 value: 6.596416666666667 - type: precision_at_100 value: 1.0784166666666668 - type: precision_at_1000 value: 0.14666666666666664 - type: precision_at_3 value: 15.31075 - type: precision_at_5 value: 10.830916666666667 - type: recall_at_1 value: 25.00791666666667 - type: recall_at_10 value: 49.10933333333333 - type: recall_at_100 value: 71.09216666666667 - type: recall_at_1000 value: 87.77725000000001 - type: recall_at_3 value: 36.660916666666665 - type: recall_at_5 value: 41.94149999999999 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.521 - type: map_at_10 value: 30.043 - type: map_at_100 value: 30.936000000000003 - type: map_at_1000 value: 31.022 - type: map_at_3 value: 27.926000000000002 - type: map_at_5 value: 29.076999999999998 - type: mrr_at_1 value: 26.227 - type: mrr_at_10 value: 32.822 - type: mrr_at_100 value: 33.61 - type: mrr_at_1000 value: 33.672000000000004 - type: mrr_at_3 value: 30.776999999999997 - type: mrr_at_5 value: 31.866 - type: ndcg_at_1 value: 26.227 - type: ndcg_at_10 value: 34.041 - type: ndcg_at_100 value: 38.394 - type: ndcg_at_1000 value: 40.732 - type: ndcg_at_3 value: 30.037999999999997 - type: ndcg_at_5 value: 31.845000000000002 - type: precision_at_1 value: 26.227 - type: precision_at_10 value: 5.244999999999999 - type: precision_at_100 value: 0.808 - type: precision_at_1000 value: 0.107 - type: precision_at_3 value: 12.679000000000002 - type: precision_at_5 value: 8.773 - type: recall_at_1 value: 23.521 - type: recall_at_10 value: 43.633 - type: recall_at_100 value: 63.126000000000005 - type: recall_at_1000 value: 80.765 - type: recall_at_3 value: 32.614 - type: recall_at_5 value: 37.15 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.236 - type: map_at_10 value: 22.898 - type: map_at_100 value: 23.878 - type: map_at_1000 value: 24.009 - type: map_at_3 value: 20.87 - type: map_at_5 value: 22.025 - type: mrr_at_1 value: 19.339000000000002 - type: mrr_at_10 value: 26.382 - type: mrr_at_100 value: 27.245 - type: mrr_at_1000 value: 27.33 - type: mrr_at_3 value: 24.386 - type: mrr_at_5 value: 25.496000000000002 - type: ndcg_at_1 value: 19.339000000000002 - type: ndcg_at_10 value: 27.139999999999997 - type: ndcg_at_100 value: 31.944 - type: ndcg_at_1000 value: 35.077999999999996 - type: ndcg_at_3 value: 23.424 - type: ndcg_at_5 value: 25.188 - type: precision_at_1 value: 19.339000000000002 - type: precision_at_10 value: 4.8309999999999995 - type: precision_at_100 value: 0.845 - type: precision_at_1000 value: 0.128 - type: precision_at_3 value: 10.874 - type: precision_at_5 value: 7.825 - type: recall_at_1 value: 16.236 - type: recall_at_10 value: 36.513 - type: recall_at_100 value: 57.999 - type: recall_at_1000 value: 80.512 - type: recall_at_3 value: 26.179999999999996 - type: recall_at_5 value: 30.712 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.11 - type: map_at_10 value: 31.566 - type: map_at_100 value: 32.647 - type: map_at_1000 value: 32.753 - type: map_at_3 value: 29.24 - type: map_at_5 value: 30.564999999999998 - type: mrr_at_1 value: 28.265 - type: mrr_at_10 value: 35.504000000000005 - type: mrr_at_100 value: 36.436 - type: mrr_at_1000 value: 36.503 - type: mrr_at_3 value: 33.349000000000004 - type: mrr_at_5 value: 34.622 - type: ndcg_at_1 value: 28.265 - type: ndcg_at_10 value: 36.192 - type: ndcg_at_100 value: 41.388000000000005 - type: ndcg_at_1000 value: 43.948 - type: ndcg_at_3 value: 31.959 - type: ndcg_at_5 value: 33.998 - type: precision_at_1 value: 28.265 - type: precision_at_10 value: 5.989 - type: precision_at_100 value: 0.9650000000000001 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 14.335 - type: precision_at_5 value: 10.112 - type: recall_at_1 value: 24.11 - type: recall_at_10 value: 46.418 - type: recall_at_100 value: 69.314 - type: recall_at_1000 value: 87.397 - type: recall_at_3 value: 34.724 - type: recall_at_5 value: 39.925 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.091 - type: map_at_10 value: 29.948999999999998 - type: map_at_100 value: 31.502000000000002 - type: map_at_1000 value: 31.713 - type: map_at_3 value: 27.464 - type: map_at_5 value: 28.968 - type: mrr_at_1 value: 26.482 - type: mrr_at_10 value: 34.009 - type: mrr_at_100 value: 35.081 - type: mrr_at_1000 value: 35.138000000000005 - type: mrr_at_3 value: 31.785000000000004 - type: mrr_at_5 value: 33.178999999999995 - type: ndcg_at_1 value: 26.482 - type: ndcg_at_10 value: 35.008 - type: ndcg_at_100 value: 41.272999999999996 - type: ndcg_at_1000 value: 43.972 - type: ndcg_at_3 value: 30.804 - type: ndcg_at_5 value: 33.046 - type: precision_at_1 value: 26.482 - type: precision_at_10 value: 6.462 - type: precision_at_100 value: 1.431 - type: precision_at_1000 value: 0.22899999999999998 - type: precision_at_3 value: 14.360999999999999 - type: precision_at_5 value: 10.474 - type: recall_at_1 value: 22.091 - type: recall_at_10 value: 45.125 - type: recall_at_100 value: 72.313 - type: recall_at_1000 value: 89.503 - type: recall_at_3 value: 33.158 - type: recall_at_5 value: 39.086999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 19.883 - type: map_at_10 value: 26.951000000000004 - type: map_at_100 value: 27.927999999999997 - type: map_at_1000 value: 28.022000000000002 - type: map_at_3 value: 24.616 - type: map_at_5 value: 25.917 - type: mrr_at_1 value: 21.996 - type: mrr_at_10 value: 29.221000000000004 - type: mrr_at_100 value: 30.024 - type: mrr_at_1000 value: 30.095 - type: mrr_at_3 value: 26.833000000000002 - type: mrr_at_5 value: 28.155 - type: ndcg_at_1 value: 21.996 - type: ndcg_at_10 value: 31.421 - type: ndcg_at_100 value: 36.237 - type: ndcg_at_1000 value: 38.744 - type: ndcg_at_3 value: 26.671 - type: ndcg_at_5 value: 28.907 - type: precision_at_1 value: 21.996 - type: precision_at_10 value: 5.009 - type: precision_at_100 value: 0.799 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 11.275 - type: precision_at_5 value: 8.059 - type: recall_at_1 value: 19.883 - type: recall_at_10 value: 43.132999999999996 - type: recall_at_100 value: 65.654 - type: recall_at_1000 value: 84.492 - type: recall_at_3 value: 30.209000000000003 - type: recall_at_5 value: 35.616 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 17.756 - type: map_at_10 value: 30.378 - type: map_at_100 value: 32.537 - type: map_at_1000 value: 32.717 - type: map_at_3 value: 25.599 - type: map_at_5 value: 28.372999999999998 - type: mrr_at_1 value: 41.303 - type: mrr_at_10 value: 53.483999999999995 - type: mrr_at_100 value: 54.106 - type: mrr_at_1000 value: 54.127 - type: mrr_at_3 value: 50.315 - type: mrr_at_5 value: 52.396 - type: ndcg_at_1 value: 41.303 - type: ndcg_at_10 value: 40.503 - type: ndcg_at_100 value: 47.821000000000005 - type: ndcg_at_1000 value: 50.788 - type: ndcg_at_3 value: 34.364 - type: ndcg_at_5 value: 36.818 - type: precision_at_1 value: 41.303 - type: precision_at_10 value: 12.463000000000001 - type: precision_at_100 value: 2.037 - type: precision_at_1000 value: 0.26 - type: precision_at_3 value: 25.798 - type: precision_at_5 value: 19.896 - type: recall_at_1 value: 17.756 - type: recall_at_10 value: 46.102 - type: recall_at_100 value: 70.819 - type: recall_at_1000 value: 87.21799999999999 - type: recall_at_3 value: 30.646 - type: recall_at_5 value: 38.022 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 9.033 - type: map_at_10 value: 20.584 - type: map_at_100 value: 29.518 - type: map_at_1000 value: 31.186000000000003 - type: map_at_3 value: 14.468 - type: map_at_5 value: 17.177 - type: mrr_at_1 value: 69.75 - type: mrr_at_10 value: 77.025 - type: mrr_at_100 value: 77.36699999999999 - type: mrr_at_1000 value: 77.373 - type: mrr_at_3 value: 75.583 - type: mrr_at_5 value: 76.396 - type: ndcg_at_1 value: 58.5 - type: ndcg_at_10 value: 45.033 - type: ndcg_at_100 value: 49.071 - type: ndcg_at_1000 value: 56.056 - type: ndcg_at_3 value: 49.936 - type: ndcg_at_5 value: 47.471999999999994 - type: precision_at_1 value: 69.75 - type: precision_at_10 value: 35.775 - type: precision_at_100 value: 11.594999999999999 - type: precision_at_1000 value: 2.062 - type: precision_at_3 value: 52.5 - type: precision_at_5 value: 45.300000000000004 - type: recall_at_1 value: 9.033 - type: recall_at_10 value: 26.596999999999998 - type: recall_at_100 value: 54.607000000000006 - type: recall_at_1000 value: 76.961 - type: recall_at_3 value: 15.754999999999999 - type: recall_at_5 value: 20.033 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 48.345000000000006 - type: f1 value: 43.4514918068706 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 71.29100000000001 - type: map_at_10 value: 81.059 - type: map_at_100 value: 81.341 - type: map_at_1000 value: 81.355 - type: map_at_3 value: 79.74799999999999 - type: map_at_5 value: 80.612 - type: mrr_at_1 value: 76.40299999999999 - type: mrr_at_10 value: 84.615 - type: mrr_at_100 value: 84.745 - type: mrr_at_1000 value: 84.748 - type: mrr_at_3 value: 83.776 - type: mrr_at_5 value: 84.343 - type: ndcg_at_1 value: 76.40299999999999 - type: ndcg_at_10 value: 84.981 - type: ndcg_at_100 value: 86.00999999999999 - type: ndcg_at_1000 value: 86.252 - type: ndcg_at_3 value: 82.97 - type: ndcg_at_5 value: 84.152 - type: precision_at_1 value: 76.40299999999999 - type: precision_at_10 value: 10.446 - type: precision_at_100 value: 1.1199999999999999 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 32.147999999999996 - type: precision_at_5 value: 20.135 - type: recall_at_1 value: 71.29100000000001 - type: recall_at_10 value: 93.232 - type: recall_at_100 value: 97.363 - type: recall_at_1000 value: 98.905 - type: recall_at_3 value: 87.893 - type: recall_at_5 value: 90.804 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 18.667 - type: map_at_10 value: 30.853 - type: map_at_100 value: 32.494 - type: map_at_1000 value: 32.677 - type: map_at_3 value: 26.91 - type: map_at_5 value: 29.099000000000004 - type: mrr_at_1 value: 37.191 - type: mrr_at_10 value: 46.171 - type: mrr_at_100 value: 47.056 - type: mrr_at_1000 value: 47.099000000000004 - type: mrr_at_3 value: 44.059 - type: mrr_at_5 value: 45.147 - type: ndcg_at_1 value: 37.191 - type: ndcg_at_10 value: 38.437 - type: ndcg_at_100 value: 44.62 - type: ndcg_at_1000 value: 47.795 - type: ndcg_at_3 value: 35.003 - type: ndcg_at_5 value: 36.006 - type: precision_at_1 value: 37.191 - type: precision_at_10 value: 10.586 - type: precision_at_100 value: 1.688 - type: precision_at_1000 value: 0.22699999999999998 - type: precision_at_3 value: 23.302 - type: precision_at_5 value: 17.006 - type: recall_at_1 value: 18.667 - type: recall_at_10 value: 45.367000000000004 - type: recall_at_100 value: 68.207 - type: recall_at_1000 value: 87.072 - type: recall_at_3 value: 32.129000000000005 - type: recall_at_5 value: 37.719 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 39.494 - type: map_at_10 value: 66.223 - type: map_at_100 value: 67.062 - type: map_at_1000 value: 67.11500000000001 - type: map_at_3 value: 62.867 - type: map_at_5 value: 64.994 - type: mrr_at_1 value: 78.987 - type: mrr_at_10 value: 84.585 - type: mrr_at_100 value: 84.773 - type: mrr_at_1000 value: 84.77900000000001 - type: mrr_at_3 value: 83.592 - type: mrr_at_5 value: 84.235 - type: ndcg_at_1 value: 78.987 - type: ndcg_at_10 value: 73.64 - type: ndcg_at_100 value: 76.519 - type: ndcg_at_1000 value: 77.51 - type: ndcg_at_3 value: 68.893 - type: ndcg_at_5 value: 71.585 - type: precision_at_1 value: 78.987 - type: precision_at_10 value: 15.529000000000002 - type: precision_at_100 value: 1.7770000000000001 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 44.808 - type: precision_at_5 value: 29.006999999999998 - type: recall_at_1 value: 39.494 - type: recall_at_10 value: 77.643 - type: recall_at_100 value: 88.825 - type: recall_at_1000 value: 95.321 - type: recall_at_3 value: 67.211 - type: recall_at_5 value: 72.519 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 85.55959999999999 - type: ap value: 80.7246500384617 - type: f1 value: 85.52336485065454 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 23.631 - type: map_at_10 value: 36.264 - type: map_at_100 value: 37.428 - type: map_at_1000 value: 37.472 - type: map_at_3 value: 32.537 - type: map_at_5 value: 34.746 - type: mrr_at_1 value: 24.312 - type: mrr_at_10 value: 36.858000000000004 - type: mrr_at_100 value: 37.966 - type: mrr_at_1000 value: 38.004 - type: mrr_at_3 value: 33.188 - type: mrr_at_5 value: 35.367 - type: ndcg_at_1 value: 24.312 - type: ndcg_at_10 value: 43.126999999999995 - type: ndcg_at_100 value: 48.642 - type: ndcg_at_1000 value: 49.741 - type: ndcg_at_3 value: 35.589 - type: ndcg_at_5 value: 39.515 - type: precision_at_1 value: 24.312 - type: precision_at_10 value: 6.699 - type: precision_at_100 value: 0.9450000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 15.153 - type: precision_at_5 value: 11.065999999999999 - type: recall_at_1 value: 23.631 - type: recall_at_10 value: 64.145 - type: recall_at_100 value: 89.41 - type: recall_at_1000 value: 97.83500000000001 - type: recall_at_3 value: 43.769000000000005 - type: recall_at_5 value: 53.169 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.4108527131783 - type: f1 value: 93.1415880261038 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 77.24806201550388 - type: f1 value: 60.531916308197175 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 73.71553463349024 - type: f1 value: 71.70753174900791 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.79757901815736 - type: f1 value: 77.83719850433258 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 33.74193296622113 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 30.64257594108566 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.811018518883625 - type: mrr value: 31.910376577445003 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.409 - type: map_at_10 value: 13.093 - type: map_at_100 value: 16.256999999999998 - type: map_at_1000 value: 17.617 - type: map_at_3 value: 9.555 - type: map_at_5 value: 11.428 - type: mrr_at_1 value: 45.201 - type: mrr_at_10 value: 54.179 - type: mrr_at_100 value: 54.812000000000005 - type: mrr_at_1000 value: 54.840999999999994 - type: mrr_at_3 value: 51.909000000000006 - type: mrr_at_5 value: 53.519000000000005 - type: ndcg_at_1 value: 43.189 - type: ndcg_at_10 value: 35.028 - type: ndcg_at_100 value: 31.226 - type: ndcg_at_1000 value: 39.678000000000004 - type: ndcg_at_3 value: 40.596 - type: ndcg_at_5 value: 38.75 - type: precision_at_1 value: 44.582 - type: precision_at_10 value: 25.974999999999998 - type: precision_at_100 value: 7.793 - type: precision_at_1000 value: 2.036 - type: precision_at_3 value: 38.493 - type: precision_at_5 value: 33.994 - type: recall_at_1 value: 5.409 - type: recall_at_10 value: 16.875999999999998 - type: recall_at_100 value: 30.316 - type: recall_at_1000 value: 60.891 - type: recall_at_3 value: 10.688 - type: recall_at_5 value: 13.832 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 36.375 - type: map_at_10 value: 51.991 - type: map_at_100 value: 52.91400000000001 - type: map_at_1000 value: 52.93600000000001 - type: map_at_3 value: 48.014 - type: map_at_5 value: 50.381 - type: mrr_at_1 value: 40.759 - type: mrr_at_10 value: 54.617000000000004 - type: mrr_at_100 value: 55.301 - type: mrr_at_1000 value: 55.315000000000005 - type: mrr_at_3 value: 51.516 - type: mrr_at_5 value: 53.435 - type: ndcg_at_1 value: 40.759 - type: ndcg_at_10 value: 59.384 - type: ndcg_at_100 value: 63.157 - type: ndcg_at_1000 value: 63.654999999999994 - type: ndcg_at_3 value: 52.114000000000004 - type: ndcg_at_5 value: 55.986000000000004 - type: precision_at_1 value: 40.759 - type: precision_at_10 value: 9.411999999999999 - type: precision_at_100 value: 1.153 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 23.329 - type: precision_at_5 value: 16.256999999999998 - type: recall_at_1 value: 36.375 - type: recall_at_10 value: 79.053 - type: recall_at_100 value: 95.167 - type: recall_at_1000 value: 98.82 - type: recall_at_3 value: 60.475 - type: recall_at_5 value: 69.327 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 70.256 - type: map_at_10 value: 83.8 - type: map_at_100 value: 84.425 - type: map_at_1000 value: 84.444 - type: map_at_3 value: 80.906 - type: map_at_5 value: 82.717 - type: mrr_at_1 value: 80.97999999999999 - type: mrr_at_10 value: 87.161 - type: mrr_at_100 value: 87.262 - type: mrr_at_1000 value: 87.263 - type: mrr_at_3 value: 86.175 - type: mrr_at_5 value: 86.848 - type: ndcg_at_1 value: 80.97999999999999 - type: ndcg_at_10 value: 87.697 - type: ndcg_at_100 value: 88.959 - type: ndcg_at_1000 value: 89.09899999999999 - type: ndcg_at_3 value: 84.83800000000001 - type: ndcg_at_5 value: 86.401 - type: precision_at_1 value: 80.97999999999999 - type: precision_at_10 value: 13.261000000000001 - type: precision_at_100 value: 1.5150000000000001 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 37.01 - type: precision_at_5 value: 24.298000000000002 - type: recall_at_1 value: 70.256 - type: recall_at_10 value: 94.935 - type: recall_at_100 value: 99.274 - type: recall_at_1000 value: 99.928 - type: recall_at_3 value: 86.602 - type: recall_at_5 value: 91.133 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.322692497613104 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 61.895813503775074 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.338 - type: map_at_10 value: 10.767 - type: map_at_100 value: 12.537999999999998 - type: map_at_1000 value: 12.803999999999998 - type: map_at_3 value: 7.788 - type: map_at_5 value: 9.302000000000001 - type: mrr_at_1 value: 21.4 - type: mrr_at_10 value: 31.637999999999998 - type: mrr_at_100 value: 32.688 - type: mrr_at_1000 value: 32.756 - type: mrr_at_3 value: 28.433000000000003 - type: mrr_at_5 value: 30.178 - type: ndcg_at_1 value: 21.4 - type: ndcg_at_10 value: 18.293 - type: ndcg_at_100 value: 25.274 - type: ndcg_at_1000 value: 30.284 - type: ndcg_at_3 value: 17.391000000000002 - type: ndcg_at_5 value: 15.146999999999998 - type: precision_at_1 value: 21.4 - type: precision_at_10 value: 9.48 - type: precision_at_100 value: 1.949 - type: precision_at_1000 value: 0.316 - type: precision_at_3 value: 16.167 - type: precision_at_5 value: 13.22 - type: recall_at_1 value: 4.338 - type: recall_at_10 value: 19.213 - type: recall_at_100 value: 39.562999999999995 - type: recall_at_1000 value: 64.08 - type: recall_at_3 value: 9.828000000000001 - type: recall_at_5 value: 13.383000000000001 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.42568163642142 - type: cos_sim_spearman value: 78.5797159641342 - type: euclidean_pearson value: 80.22151260811604 - type: euclidean_spearman value: 78.5797151953878 - type: manhattan_pearson value: 80.21224215864788 - type: manhattan_spearman value: 78.55641478381344 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 85.44020710812569 - type: cos_sim_spearman value: 78.91631735081286 - type: euclidean_pearson value: 81.64188964182102 - type: euclidean_spearman value: 78.91633286881678 - type: manhattan_pearson value: 81.69294748512496 - type: manhattan_spearman value: 78.93438558002656 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 84.27165426412311 - type: cos_sim_spearman value: 85.40429140249618 - type: euclidean_pearson value: 84.7509580724893 - type: euclidean_spearman value: 85.40429140249618 - type: manhattan_pearson value: 84.76488289321308 - type: manhattan_spearman value: 85.4256793698708 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 83.138851760732 - type: cos_sim_spearman value: 81.64101363896586 - type: euclidean_pearson value: 82.55165038934942 - type: euclidean_spearman value: 81.64105257080502 - type: manhattan_pearson value: 82.52802949883335 - type: manhattan_spearman value: 81.61255430718158 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 86.0654695484029 - type: cos_sim_spearman value: 87.20408521902229 - type: euclidean_pearson value: 86.8110651362115 - type: euclidean_spearman value: 87.20408521902229 - type: manhattan_pearson value: 86.77984656478691 - type: manhattan_spearman value: 87.1719947099227 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 83.77823915496512 - type: cos_sim_spearman value: 85.43566325729779 - type: euclidean_pearson value: 84.5396956658821 - type: euclidean_spearman value: 85.43566325729779 - type: manhattan_pearson value: 84.5665398848169 - type: manhattan_spearman value: 85.44375870303232 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.20030208471798 - type: cos_sim_spearman value: 87.20485505076539 - type: euclidean_pearson value: 88.10588324368722 - type: euclidean_spearman value: 87.20485505076539 - type: manhattan_pearson value: 87.92324770415183 - type: manhattan_spearman value: 87.0571314561877 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 63.06093161604453 - type: cos_sim_spearman value: 64.2163140357722 - type: euclidean_pearson value: 65.27589680994006 - type: euclidean_spearman value: 64.2163140357722 - type: manhattan_pearson value: 65.45904383711101 - type: manhattan_spearman value: 64.55404716679305 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 84.32976164578706 - type: cos_sim_spearman value: 85.54302197678368 - type: euclidean_pearson value: 85.26307149193056 - type: euclidean_spearman value: 85.54302197678368 - type: manhattan_pearson value: 85.26647282029371 - type: manhattan_spearman value: 85.5316135265568 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 81.44675968318754 - type: mrr value: 94.92741826075158 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 56.34400000000001 - type: map_at_10 value: 65.927 - type: map_at_100 value: 66.431 - type: map_at_1000 value: 66.461 - type: map_at_3 value: 63.529 - type: map_at_5 value: 64.818 - type: mrr_at_1 value: 59.333000000000006 - type: mrr_at_10 value: 67.54599999999999 - type: mrr_at_100 value: 67.892 - type: mrr_at_1000 value: 67.917 - type: mrr_at_3 value: 65.778 - type: mrr_at_5 value: 66.794 - type: ndcg_at_1 value: 59.333000000000006 - type: ndcg_at_10 value: 70.5 - type: ndcg_at_100 value: 72.688 - type: ndcg_at_1000 value: 73.483 - type: ndcg_at_3 value: 66.338 - type: ndcg_at_5 value: 68.265 - type: precision_at_1 value: 59.333000000000006 - type: precision_at_10 value: 9.3 - type: precision_at_100 value: 1.053 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 25.889 - type: precision_at_5 value: 16.866999999999997 - type: recall_at_1 value: 56.34400000000001 - type: recall_at_10 value: 82.789 - type: recall_at_100 value: 92.767 - type: recall_at_1000 value: 99 - type: recall_at_3 value: 71.64399999999999 - type: recall_at_5 value: 76.322 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.75742574257426 - type: cos_sim_ap value: 93.52081548447406 - type: cos_sim_f1 value: 87.33850129198966 - type: cos_sim_precision value: 90.37433155080214 - type: cos_sim_recall value: 84.5 - type: dot_accuracy value: 99.75742574257426 - type: dot_ap value: 93.52081548447406 - type: dot_f1 value: 87.33850129198966 - type: dot_precision value: 90.37433155080214 - type: dot_recall value: 84.5 - type: euclidean_accuracy value: 99.75742574257426 - type: euclidean_ap value: 93.52081548447406 - type: euclidean_f1 value: 87.33850129198966 - type: euclidean_precision value: 90.37433155080214 - type: euclidean_recall value: 84.5 - type: manhattan_accuracy value: 99.75841584158415 - type: manhattan_ap value: 93.4975678585854 - type: manhattan_f1 value: 87.26708074534162 - type: manhattan_precision value: 90.45064377682404 - type: manhattan_recall value: 84.3 - type: max_accuracy value: 99.75841584158415 - type: max_ap value: 93.52081548447406 - type: max_f1 value: 87.33850129198966 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 64.31437036686651 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 33.25569319007206 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 49.90474939720706 - type: mrr value: 50.568115503777264 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 29.866828641244712 - type: cos_sim_spearman value: 30.077555055873866 - type: dot_pearson value: 29.866832988572266 - type: dot_spearman value: 30.077555055873866 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.232 - type: map_at_10 value: 2.094 - type: map_at_100 value: 11.971 - type: map_at_1000 value: 28.158 - type: map_at_3 value: 0.688 - type: map_at_5 value: 1.114 - type: mrr_at_1 value: 88 - type: mrr_at_10 value: 93.4 - type: mrr_at_100 value: 93.4 - type: mrr_at_1000 value: 93.4 - type: mrr_at_3 value: 93 - type: mrr_at_5 value: 93.4 - type: ndcg_at_1 value: 84 - type: ndcg_at_10 value: 79.923 - type: ndcg_at_100 value: 61.17 - type: ndcg_at_1000 value: 53.03 - type: ndcg_at_3 value: 84.592 - type: ndcg_at_5 value: 82.821 - type: precision_at_1 value: 88 - type: precision_at_10 value: 85 - type: precision_at_100 value: 63.019999999999996 - type: precision_at_1000 value: 23.554 - type: precision_at_3 value: 89.333 - type: precision_at_5 value: 87.2 - type: recall_at_1 value: 0.232 - type: recall_at_10 value: 2.255 - type: recall_at_100 value: 14.823 - type: recall_at_1000 value: 49.456 - type: recall_at_3 value: 0.718 - type: recall_at_5 value: 1.175 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.547 - type: map_at_10 value: 11.375 - type: map_at_100 value: 18.194 - type: map_at_1000 value: 19.749 - type: map_at_3 value: 5.825 - type: map_at_5 value: 8.581 - type: mrr_at_1 value: 32.653 - type: mrr_at_10 value: 51.32 - type: mrr_at_100 value: 51.747 - type: mrr_at_1000 value: 51.747 - type: mrr_at_3 value: 47.278999999999996 - type: mrr_at_5 value: 48.605 - type: ndcg_at_1 value: 29.592000000000002 - type: ndcg_at_10 value: 28.151 - type: ndcg_at_100 value: 39.438 - type: ndcg_at_1000 value: 50.769 - type: ndcg_at_3 value: 30.758999999999997 - type: ndcg_at_5 value: 30.366 - type: precision_at_1 value: 32.653 - type: precision_at_10 value: 25.714 - type: precision_at_100 value: 8.041 - type: precision_at_1000 value: 1.555 - type: precision_at_3 value: 33.333 - type: precision_at_5 value: 31.837 - type: recall_at_1 value: 2.547 - type: recall_at_10 value: 18.19 - type: recall_at_100 value: 49.538 - type: recall_at_1000 value: 83.86 - type: recall_at_3 value: 7.329 - type: recall_at_5 value: 11.532 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.4952 - type: ap value: 14.793362635531409 - type: f1 value: 55.204635551516915 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 61.5365025466893 - type: f1 value: 61.81742556334845 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 49.05531070301185 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.51725576682364 - type: cos_sim_ap value: 75.2292304265163 - type: cos_sim_f1 value: 69.54022988505749 - type: cos_sim_precision value: 63.65629110039457 - type: cos_sim_recall value: 76.62269129287598 - type: dot_accuracy value: 86.51725576682364 - type: dot_ap value: 75.22922386081054 - type: dot_f1 value: 69.54022988505749 - type: dot_precision value: 63.65629110039457 - type: dot_recall value: 76.62269129287598 - type: euclidean_accuracy value: 86.51725576682364 - type: euclidean_ap value: 75.22925730473472 - type: euclidean_f1 value: 69.54022988505749 - type: euclidean_precision value: 63.65629110039457 - type: euclidean_recall value: 76.62269129287598 - type: manhattan_accuracy value: 86.52321630804077 - type: manhattan_ap value: 75.20608115037336 - type: manhattan_f1 value: 69.60000000000001 - type: manhattan_precision value: 64.37219730941705 - type: manhattan_recall value: 75.75197889182058 - type: max_accuracy value: 86.52321630804077 - type: max_ap value: 75.22925730473472 - type: max_f1 value: 69.60000000000001 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.34877944657896 - type: cos_sim_ap value: 86.71257569277373 - type: cos_sim_f1 value: 79.10386355986088 - type: cos_sim_precision value: 76.91468470434214 - type: cos_sim_recall value: 81.4213119802895 - type: dot_accuracy value: 89.34877944657896 - type: dot_ap value: 86.71257133133368 - type: dot_f1 value: 79.10386355986088 - type: dot_precision value: 76.91468470434214 - type: dot_recall value: 81.4213119802895 - type: euclidean_accuracy value: 89.34877944657896 - type: euclidean_ap value: 86.71257651501476 - type: euclidean_f1 value: 79.10386355986088 - type: euclidean_precision value: 76.91468470434214 - type: euclidean_recall value: 81.4213119802895 - type: manhattan_accuracy value: 89.35848177901967 - type: manhattan_ap value: 86.69330615469126 - type: manhattan_f1 value: 79.13867741453949 - type: manhattan_precision value: 76.78881807647741 - type: manhattan_recall value: 81.63689559593472 - type: max_accuracy value: 89.35848177901967 - type: max_ap value: 86.71257651501476 - type: max_f1 value: 79.13867741453949 license: apache-2.0 language: - en --- # nomic-embed-text-v1: A Reproducible Long Context (8192) Text Embedder `nomic-embed-text-v1` is 8192 context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks. \| Name \| SeqLen \| MTEB \| LoCo \| Jina Long Context \| Open Weights \| Open Training Code \| Open Data \| \| :-------------------------------:\| :----- \| :-------- \| :------: \| :---------------: \| :-----------: \| :----------------: \| :---------- \| \| nomic-embed-text-v1 \| 8192 \| 62.39 \|85.53 \| 54.16 \| ✅ \| ✅ \| ✅ \| \| jina-embeddings-v2-base-en \| 8192 \| 60.39 \| 85.45 \| 51.90 \| ✅ \| ❌ \| ❌ \| \| text-embedding-3-small \| 8191 \| 62.26 \| 82.40 \| 58.20 \| ❌ \| ❌ \| ❌ \| \| text-embedding-ada-002 \| 8191 \| 60.99 \| 52.7 \| 55.25 \| ❌ \| ❌ \| ❌ \| ## Hosted Inference API The easiest way to get started with Nomic Embed is through the Nomic Embedding API. Generating embeddings with the `nomic` Python client is as easy as ```python from nomic import embed output = embed.text( texts=['Nomic Embedding API', '#keepAIOpen'], model='nomic-embed-text-v1', task_type='search_document' ) print(output) ``` For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text) ## Data Visualization Click the Nomic Atlas map below to visualize a 5M sample of our contrastive pretraining data! [![image/webp](https://cdn-uploads.huggingface.co/production/uploads/607997c83a565c15675055b3/pjhJhuNyRfPagRd_c_iUz.webp)](https://atlas.nomic.ai/map/nomic-text-embed-v1-5m-sample) ## Training Details We train our embedder using a multi-stage training pipeline. Starting from a long-context [BERT model](https://huggingface.co/nomic-ai/nomic-bert-2048), the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles. In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage. For more details, see the Nomic Embed [Technical Report](https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf) and corresponding [blog post](https://blog.nomic.ai/posts/nomic-embed-text-v1). Training data to train the models is released in its entirety. For more details, see the `contrastors` [repository](https://github.com/nomic-ai/contrastors) ## Usage Note `nomic-embed-text` requires prefixes! We support the prefixes `[search_query, search_document, classification, clustering]`. For retrieval applications, you should prepend `search_document` for all your documents and `search_query` for your queries. For example, you are building a RAG application over the top of Wikipedia. You would embed all Wikipedia articles with the prefix `search_document` and any questions you ask with `search_query`. For example: ```python queries = ["search_query: who is the first president of the united states?", "search_query: when was babe ruth born?"] documents = ["search_document: <article about US Presidents>", "search_document: <article about Babe Ruth>"] ``` ### Sentence Transformers ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] embeddings = model.encode(sentences) print(embeddings) ``` ### Transformers ```python import torch import torch.nn.functional as F from transformers import AutoTokenizer, AutoModel def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) model.eval() encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') with torch.no_grad(): model_output = model(**encoded_input) embeddings = mean_pooling(model_output, encoded_input['attention_mask']) embeddings = F.normalize(embeddings, p=2, dim=1) print(embeddings) ``` The model natively supports scaling of the sequence length past 2048 tokens. To do so, ```diff - tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') + tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192) - model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) + model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2) ``` ### Transformers.js ```js import { pipeline } from '@xenova/transformers'; // Create a feature extraction pipeline const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1', { quantized: false, // Comment out this line to use the quantized version }); // Compute sentence embeddings const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']; const embeddings = await extractor(texts, { pooling: 'mean', normalize: true }); console.log(embeddings); ``` # Join the Nomic Community - Nomic: [https://nomic.ai](https://nomic.ai) - Discord: [https://discord.gg/myY5YDR8z8](https://discord.gg/myY5YDR8z8) - Twitter: [https://twitter.com/nomic_ai](https://twitter.com/nomic_ai) # Citation If you find the model, dataset, or training code useful, please cite our work ```bibtex @misc{nussbaum2024nomic, title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar}, year={2024}, eprint={2402.01613}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
Yntec/InfiniteLiberty	Yntec	"2023-12-27T13:49:57Z"	2,589	3	diffusers	[ "diffusers", "safetensors", "Realistic", "Photos", "AInfinity", "artificialguybr", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	"2023-12-27T11:56:34Z"	--- license: creativeml-openrail-m library_name: diffusers pipeline_tag: text-to-image tags: - Realistic - Photos - AInfinity - artificialguybr - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers --- # Infinite Liberty A mix of LiberteRedmond and AI Infinity Realistic to increase its complexity! Comparison and prompt: ![Infinite Liberty Model Comparison](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/stfUK0l7HU4s87UjJCIlb.png) (Click for larger) Portrait of a happy family cooking at the classroom, girl painting by technicolor, smooth face, perfect eyes, wide angle, sharp focus, 8 k high definition, insanely detailed, intricate, elegant, acrylic art on canvas by rossdraws and clay mann Samples and prompts (keep scrolling for more) ![Infinite AI images generated](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/mKgVBWyfPs2KYP1Q4sWDb.png) (Click for larger) Top left: pretty wife hugging young husband and daughter movie still. faces portrait. festive scene at a copper brewery with a wooden keg of beer in the center. sitting cute little girl. Display mugs of dark beer accompanied Shirley by halloween ingredients Top right: young guy together with pretty ladies standing, he, photoreal, cute face, is on top of Closeup a of rocks on pile top of a magazine to the ocean moon. Bottom left: little videogames, robert jordan pepperoni pizza, josephine wall winner, hidari, roll20 illumination, radiant light, sitting elementary girl, Pretty CUTE, gorgeous hair, DETAILED CHIBI EYES, Magazine ad, iconic, 1943, Cartoon, sharp focus, cherries, watched towel. 4k art on canvas by kyoani and ROSSDRAWS Bottom right: best quality, a bag of TV potato chips ![Free text to image generator](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/LD9VNHfTF9mB0iSPlltFb.png) (Click for larger) Top left: a deer playing guitar in a club, whimsical Top right: masterpiece, best quality, ultra detailed, 8k, 4k, intricate,highly detailed, detailed background,detailed landscape, ((portrait)), foodstyle,simple background, food, black background, plate, realistic, burger, meat, food focus, cheese, still life, lettuce Bottom left: pretty cute little girl as Marie Antoinette playing on harmonica in movie Bottom right: ladies as close Catwoman and Harley Quinn from the 2004 movie. elegant, medieval in cool armor, action scene, in a wonderland land ![Liberty AI images generated](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/Rh1WyezDDoLdSD1EdUYXr.png) (Click for larger) Top left: manga art, muted colors, detailed painting, halftone dithering, cute girl with shoulderlength black bobcut in baggy black clothes, pixar cape, beautiful eyes, complex background Top right: calm water in european city. sofa Bottom left: beach, ruins, romantic night Bottom right: 1girl,night, waterfall, white wavy hair Angel 22y.o, (realistic:2),Pizza,4k,rabbits and birds, close up, ![Infinite Liberty AI images generated](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/_zRtrSsDYhQWah-rw7K4o.png) (Click for larger) Top left: Father with little daughter holding cheescake. Santa Claus sitting with a pretty cute girl, Art Christmas Theme by Gil_Elvgren and Haddon_Sundblom Top right: Romanticism In Photography The Beauty Grandeur And behind trees Of Nature The Suggestion Of The Divine In The Light And Nature Photos Nature Photography Nature, wallpaper hd, stunning photorealistic painting, artstation, divine night sky,1920x1080 Bottom left: peaceful grill full of meat and artstation. fire Bottom right: Dreamy Pet Portrait photo of a Cute penguin, with twinkling eyes that could melt hearts, lounging in a field of daisies, its fur catching the gentle breeze, backdrop of a serene lakeside sunset, bathed in the warm, golden hues of the fading day, using a high-quality digital camera to ensure every adorable detail, in the style of Annie Leibovitz ![Free AI samples and prompts](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/dzoBWU7UduqHnvwYOujyI.png) (Click for larger) Top left: an illustration of a baby frog with headphones holding an ribbon umbrella in the rain Top right: Pretty CUTE LITTLE Girl, sitting on a box of veggies, CHIBI EYES, holding PEPSI bottle, gorgeous detailed hair, Ponytail, ad, iconic, 1940, sharp focus. Illustration By KlaysMoji and artgerm and Clay Mann and and Dave Rapoza and leyendecker Bottom left: tiny baby girl. chibi. Bottom right: House with a waterwheel built into the screen of a giant tree, next to games, a colorful river landscape painting from a fantasy point and click 2 d graphic adventure game, art inspired by ROSSDRAWS and larry elmore and john shroades, king's quest, sierra entertainment Original pages: https://civitai.com/models/94123?modelVersionId=100409 (Liberte Redmond) https://civitai.com/models/121253/ai-infinity-realistic-better-hands # Recipe: - SuperMerger Weight Sum Train Difference MBW 0,1,1,1,1,1,1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,0,0 Model A: AIInfinityRealistic Model B: LiberteRedmond Output: InfiniteLiberty
RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf	RichardErkhov	"2024-06-26T22:28:50Z"	2,589	1	null	[ "gguf", "region:us" ]	null	"2024-06-26T22:04:35Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Fett-uccine-7B - GGUF - Model creator: https://huggingface.co/Epiculous/ - Original model: https://huggingface.co/Epiculous/Fett-uccine-7B/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Fett-uccine-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q2_K.gguf) \| Q2_K \| 2.53GB \| \| [Fett-uccine-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ3_XS.gguf) \| IQ3_XS \| 2.81GB \| \| [Fett-uccine-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ3_S.gguf) \| IQ3_S \| 2.96GB \| \| [Fett-uccine-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q3_K_S.gguf) \| Q3_K_S \| 1.36GB \| \| [Fett-uccine-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ3_M.gguf) \| IQ3_M \| 1.09GB \| \| [Fett-uccine-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q3_K.gguf) \| Q3_K \| 0.13GB \| \| [Fett-uccine-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q3_K_M.gguf) \| Q3_K_M \| 0.01GB \| \| [Fett-uccine-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q3_K_L.gguf) \| Q3_K_L \| 0.0GB \| \| [Fett-uccine-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ4_XS.gguf) \| IQ4_XS \| 0.0GB \| \| [Fett-uccine-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_0.gguf) \| Q4_0 \| 0.0GB \| \| [Fett-uccine-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ4_NL.gguf) \| IQ4_NL \| 0.0GB \| \| [Fett-uccine-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_K_S.gguf) \| Q4_K_S \| 0.0GB \| \| [Fett-uccine-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_K.gguf) \| Q4_K \| 0.0GB \| \| [Fett-uccine-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_K_M.gguf) \| Q4_K_M \| 0.0GB \| \| [Fett-uccine-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_1.gguf) \| Q4_1 \| 0.0GB \| \| [Fett-uccine-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_0.gguf) \| Q5_0 \| 0.0GB \| \| [Fett-uccine-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_K_S.gguf) \| Q5_K_S \| 0.0GB \| \| [Fett-uccine-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_K.gguf) \| Q5_K \| 0.0GB \| \| [Fett-uccine-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_K_M.gguf) \| Q5_K_M \| 0.0GB \| \| [Fett-uccine-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_1.gguf) \| Q5_1 \| 0.0GB \| \| [Fett-uccine-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q6_K.gguf) \| Q6_K \| 0.0GB \| \| [Fett-uccine-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q8_0.gguf) \| Q8_0 \| 0.0GB \| Original model description: --- datasets: - lemonilia/LimaRP - grimulkan/theory-of-mind - Epiculous/Gnosis tags: - not-for-all-audiences license: agpl-3.0 --- # Fett-uccine This model is created by training Mistral base model on LimaRP (ShareGPT format provided by SAO), theory of mind, and gnosis(provided by jeiku). The 8-bit lora was then merged into Mistral Instruct resulting in what you see here. Works best with ChatML Instruct This model is in honor of the SillyTavern community, keep being awesome! Optimal Settings provided by Nitral: ``` { "temp": 5, "temperature_last": true, "top_p": 1, "top_k": 0, "top_a": 0, "tfs": 1, "epsilon_cutoff": 0, "eta_cutoff": 0, "typical_p": 1, "min_p": 0.05, "rep_pen": 1, "rep_pen_range": 0, "no_repeat_ngram_size": 0, "penalty_alpha": 0, "num_beams": 1, "length_penalty": 0, "min_length": 0, "encoder_rep_pen": 1, "freq_pen": 0, "presence_pen": 0, "do_sample": true, "early_stopping": false, "dynatemp": false, "min_temp": 1, "max_temp": 5, "dynatemp_exponent": 1, "smoothing_factor": 0.3, "add_bos_token": true, "truncation_length": 2048, "ban_eos_token": false, "skip_special_tokens": true, "streaming": false, "mirostat_mode": 0, "mirostat_tau": 5, "mirostat_eta": 0.1, "guidance_scale": 1, "negative_prompt": "", "grammar_string": "", "banned_tokens": "", "ignore_eos_token_aphrodite": false, "spaces_between_special_tokens_aphrodite": true, "sampler_order": [ 6, 0, 1, 3, 4, 2, 5 ], "logit_bias": [], "n": 1, "rep_pen_size": 0, "genamt": 150, "max_length": 8192 } ```
alibayram/Doktor-Llama-8b.gguf	alibayram	"2024-06-20T21:40:51Z"	2,585	1	null	[ "gguf", "tr", "dataset:alibayram/doktorsitesi", "license:cc-by-4.0", "region:us" ]	null	"2024-06-20T20:49:21Z"	--- license: cc-by-4.0 datasets: - alibayram/doktorsitesi language: - tr --- # Doktor-Llama-8b.gguf ## Genel Bakış Doktor-Llama-8b.gguf, alibayram/Doktor-Llama-8b modelinin GGUF formatına dönüştürülmüş versiyonudur. GGUF, model dosyalarının daha verimli ve hızlı bir şekilde işlenmesini sağlayan yeni bir formattır. Bu dönüşüm, modelin çeşitli platformlarda ve uygulamalarda daha kolay kullanılabilmesi için yapılmıştır. ## GGUF Nedir? GGUF, "Graphical GPU Unified Format" anlamına gelir ve özellikle büyük dil modellerinin daha verimli bir şekilde depolanması ve işlenmesi için geliştirilmiş bir formattır. Bu format, model dosyalarının boyutunu küçültürken performansı artırır, bu sayede daha hızlı ve verimli kullanım sağlar. ## Alıntı Bu modeli araştırmanızda veya uygulamanızda kullanırsanız, lütfen aşağıdaki gibi alıntı yapın: ``` @model{alibayram2024doktor-llama-8b-gguf, author = {Ali Bayram}, title = {Doktor-Llama-8b.gguf}, year = 2024, url = {https://huggingface.co/alibayram/Doktor-Llama-8b.gguf}, } ``` ## Lisans Bu model, Creative Commons Attribution Non Commercial 4.0 lisansı altında lisanslanmıştır. Modeli ticari amaçlar dışında kullanabilir, paylaşabilir ve uyarlayabilirsiniz, ancak uygun atıf yapmanız gerekmektedir. ## Katkılar Bu modele katkılar memnuniyetle karşılanır. Herhangi bir öneriniz, iyileştirmeniz veya ek veriniz varsa, lütfen model oluşturucusuyla iletişime geçin veya model deposunda bir pull request gönderin. ## İletişim Herhangi bir soru veya daha fazla bilgi için lütfen iletişime geçin: - İsim: Ali Bayram - Email: [email protected] ## Teşekkürler Bu modelin geliştirilmesinde katkıda bulunan tüm sağlık profesyonellerine ve veri sağlayıcılarına teşekkür ederiz.
Neleac/SpaceTimeGPT	Neleac	"2024-03-21T05:56:11Z"	2,584	25	transformers	[ "transformers", "pytorch", "vision-encoder-decoder", "video-captioning", "text-generation", "en", "dataset:HuggingFaceM4/vatex", "region:us" ]	text-generation	"2023-04-21T23:32:33Z"	--- datasets: - HuggingFaceM4/vatex language: - en metrics: - bleu - meteor - rouge pipeline_tag: text-generation inference: false tags: - video-captioning --- # SpaceTimeGPT - A Spatiotemporal Video Captioning Model ![SpaceTimeGPT](https://raw.githubusercontent.com/Neleac/SpaceTimeGPT/main/model.JPG) Vision Encoder Model: [timesformer-base-finetuned-k600](https://huggingface.co/facebook/timesformer-base-finetuned-k600) \ Text Decoder Model: [gpt2](https://huggingface.co/gpt2) #### Evaluation Result: 67.2 CIDEr on [VaTeX](https://eric-xw.github.io/vatex-website/index.html) public test set #### Example Inference Code: ```python import av import numpy as np import torch from transformers import AutoImageProcessor, AutoTokenizer, VisionEncoderDecoderModel device = "cuda" if torch.cuda.is_available() else "cpu" # load pretrained processor, tokenizer, and model image_processor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base") tokenizer = AutoTokenizer.from_pretrained("gpt2") model = VisionEncoderDecoderModel.from_pretrained("Neleac/timesformer-gpt2-video-captioning").to(device) # load video video_path = "never_gonna_give_you_up.mp4" container = av.open(video_path) # extract evenly spaced frames from video seg_len = container.streams.video[0].frames clip_len = model.config.encoder.num_frames indices = set(np.linspace(0, seg_len, num=clip_len, endpoint=False).astype(np.int64)) frames = [] container.seek(0) for i, frame in enumerate(container.decode(video=0)): if i in indices: frames.append(frame.to_ndarray(format="rgb24")) # generate caption gen_kwargs = { "min_length": 10, "max_length": 20, "num_beams": 8, } pixel_values = image_processor(frames, return_tensors="pt").pixel_values.to(device) tokens = model.generate(pixel_values, **gen_kwargs) caption = tokenizer.batch_decode(tokens, skip_special_tokens=True)[0] print(caption) # A man and a woman are dancing on a stage in front of a mirror. ``` #### Author Information: 👾 [Discord](https://discordapp.com/users/297770280863137802) \ 🐙 [GitHub](https://github.com/Neleac) \ 🤝 [LinkedIn](https://www.linkedin.com/in/caelenw/)
mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF	mradermacher	"2024-06-04T14:51:03Z"	2,584	0	transformers	[ "transformers", "gguf", "en", "base_model:AwanLLM/Awanllm-Llama-3-8B-Dolfin-v1.0", "license:llama3", "endpoints_compatible", "region:us" ]	null	"2024-06-03T17:20:05Z"	--- base_model: AwanLLM/Awanllm-Llama-3-8B-Dolfin-v1.0 language: - en library_name: transformers license: llama3 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Dolfin-v1.0 <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf	RichardErkhov	"2024-06-22T19:03:19Z"	2,583	0	null	[ "gguf", "region:us" ]	null	"2024-06-22T18:47:26Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) TinyLlama-1.1B-intermediate-step-955k-token-2T - GGUF - Model creator: https://huggingface.co/TinyLlama/ - Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q2_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q2_K.gguf) \| Q2_K \| 0.4GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_XS.gguf) \| IQ3_XS \| 0.44GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_S.gguf) \| IQ3_S \| 0.47GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_S.gguf) \| Q3_K_S \| 0.47GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_M.gguf) \| IQ3_M \| 0.48GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K.gguf) \| Q3_K \| 0.51GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_M.gguf) \| Q3_K_M \| 0.51GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_L.gguf) \| Q3_K_L \| 0.55GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ4_XS.gguf) \| IQ4_XS \| 0.57GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_0.gguf) \| Q4_0 \| 0.59GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ4_NL.gguf) \| IQ4_NL \| 0.6GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K_S.gguf) \| Q4_K_S \| 0.6GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K.gguf) \| Q4_K \| 0.62GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K_M.gguf) \| Q4_K_M \| 0.62GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_1.gguf) \| Q4_1 \| 0.65GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_0.gguf) \| Q5_0 \| 0.71GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K_S.gguf) \| Q5_K_S \| 0.71GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K.gguf) \| Q5_K \| 0.73GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K_M.gguf) \| Q5_K_M \| 0.73GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_1.gguf) \| Q5_1 \| 0.77GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q6_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q6_K.gguf) \| Q6_K \| 0.84GB \| \| [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q8_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q8_0.gguf) \| Q8_0 \| 1.09GB \| Original model description: --- license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata language: - en --- <div align="center"> # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. <div align="center"> <img src="./TinyLlama_logo.png" width="300"/> </div> We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Model This is an intermediate checkpoint with 995K steps and 2003B tokens. #### Releases Schedule We will be rolling out intermediate checkpoints following the below schedule. We also include some baseline models for comparison. \| Date \| HF Checkpoint \| Tokens \| Step \| HellaSwag Acc_norm \| \|------------\|-------------------------------------------------\|--------\|------\|---------------------\| \| Baseline \| [StableLM-Alpha-3B](https://huggingface.co/stabilityai/stablelm-base-alpha-3b)\| 800B \| -- \| 38.31 \| \| Baseline \| [Pythia-1B-intermediate-step-50k-105b](https://huggingface.co/EleutherAI/pythia-1b/tree/step50000) \| 105B \| 50k \| 42.04 \| \| Baseline \| [Pythia-1B](https://huggingface.co/EleutherAI/pythia-1b) \| 300B \| 143k \| 47.16 \| \| 2023-09-04 \| [TinyLlama-1.1B-intermediate-step-50k-105b](https://huggingface.co/PY007/TinyLlama-1.1B-step-50K-105b) \| 105B \| 50k \| 43.50 \| \| 2023-09-16 \| -- \| 500B \| -- \| -- \| \| 2023-10-01 \| -- \| 1T \| -- \| -- \| \| 2023-10-16 \| -- \| 1.5T \| -- \| -- \| \| 2023-10-31 \| -- \| 2T \| -- \| -- \| \| 2023-11-15 \| -- \| 2.5T \| -- \| -- \| \| 2023-12-01 \| -- \| 3T \| -- \| -- \| #### How to use You will need the transformers>=4.31 Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information. ``` from transformers import AutoTokenizer import transformers import torch model = "TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( 'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.', do_sample=True, top_k=10, num_return_sequences=1, repetition_penalty=1.5, eos_token_id=tokenizer.eos_token_id, max_length=500, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ```
marefa-nlp/marefa-ner	marefa-nlp	"2021-12-04T05:21:57Z"	2,582	20	transformers	[ "transformers", "pytorch", "xlm-roberta", "token-classification", "ar", "dataset:Marefa-NER", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	"2022-03-02T23:29:05Z"	--- language: ar datasets: - Marefa-NER widget: - text: "في استاد القاهرة، بدأ حفل افتتاح بطولة كأس الأمم الأفريقية بحضور رئيس الجمهورية و رئيس الاتحاد الدولي لكرة القدم" --- # Tebyan تبيـان ## Marefa Arabic Named Entity Recognition Model ## نموذج المعرفة لتصنيف أجزاء النص <p align="center"> <img src="https://huggingface.co/marefa-nlp/marefa-ner/resolve/main/assets/marefa-tebyan-banner.png" alt="Marfa Arabic NER Model" width="600"/> </p? --------- Version: 1.3 Last Update: 3-12-2021 ## Model description Marefa-NER is a Large Arabic Named Entity Recognition (NER) model built on a completely new dataset and targets to extract up to 9 different types of entities ``` Person, Location, Organization, Nationality, Job, Product, Event, Time, Art-Work ``` نموذج المعرفة لتصنيف أجزاء النص. نموذج جديد كليا من حيث البيانات المستخدمة في تدريب النموذج. كذلك يستهدف النموذج تصنيف حتى 9 أنواع مختلفة من أجزاء النص ``` شخص - مكان - منظمة - جنسية - وظيفة - منتج - حدث - توقيت - عمل إبداعي ``` ## How to use كيف تستخدم النموذج You can test the model quickly by checking this [Colab notebook](https://colab.research.google.com/drive/1OGp9Wgm-oBM5BBhTLx6Qow4dNRSJZ-F5?usp=sharing) ---- Install the following Python packages `$ pip3 install transformers==4.8.0 nltk==3.5 protobuf==3.15.3 torch==1.9.0 ` > If you are using `Google Colab`, please restart your runtime after installing the packages. ----------- ```python from transformers import AutoTokenizer, AutoModelForTokenClassification import torch import numpy as np import nltk nltk.download('punkt') from nltk.tokenize import word_tokenize custom_labels = ["O", "B-job", "I-job", "B-nationality", "B-person", "I-person", "B-location","B-time", "I-time", "B-event", "I-event", "B-organization", "I-organization", "I-location", "I-nationality", "B-product", "I-product", "B-artwork", "I-artwork"] def _extract_ner(text: str, model: AutoModelForTokenClassification, tokenizer: AutoTokenizer, start_token: str="▁"): tokenized_sentence = tokenizer([text], padding=True, truncation=True, return_tensors="pt") tokenized_sentences = tokenized_sentence['input_ids'].numpy() with torch.no_grad(): output = model(tokenized_sentence) last_hidden_states = output[0].numpy() label_indices = np.argmax(last_hidden_states[0], axis=1) tokens = tokenizer.convert_ids_to_tokens(tokenized_sentences[0]) special_tags = set(tokenizer.special_tokens_map.values()) grouped_tokens = [] for token, label_idx in zip(tokens, label_indices): if token not in special_tags: if not token.startswith(start_token) and len(token.replace(start_token,"").strip()) > 0: grouped_tokens[-1]["token"] += token else: grouped_tokens.append({"token": token, "label": custom_labels[label_idx]}) # extract entities ents = [] prev_label = "O" for token in grouped_tokens: label = token["label"].replace("I-","").replace("B-","") if token["label"] != "O": if label != prev_label: ents.append({"token": [token["token"]], "label": label}) else: ents[-1]["token"].append(token["token"]) prev_label = label # group tokens ents = [{"token": "".join(rec["token"]).replace(start_token," ").strip(), "label": rec["label"]} for rec in ents ] return ents model_cp = "marefa-nlp/marefa-ner" tokenizer = AutoTokenizer.from_pretrained(model_cp) model = AutoModelForTokenClassification.from_pretrained(model_cp, num_labels=len(custom_labels)) samples = [ "تلقى تعليمه في الكتاب ثم انضم الى الأزهر عام 1873م. تعلم على يد السيد جمال الدين الأفغاني والشيخ محمد عبده", "بعد عودته إلى القاهرة، التحق نجيب الريحاني فرقة جورج أبيض، الذي كان قد ضمَّ - قُبيل ذلك - فرقته إلى فرقة سلامة حجازي . و منها ذاع صيته", "في استاد القاهرة، قام حفل افتتاح بطولة كأس الأمم الأفريقية بحضور رئيس الجمهورية و رئيس الاتحاد الدولي لكرة القدم", "من فضلك أرسل هذا البريد الى صديقي جلال الدين في تمام الساعة الخامسة صباحا في يوم الثلاثاء القادم", "امبارح اتفرجت على مباراة مانشستر يونايتد مع ريال مدريد في غياب الدون كرستيانو رونالدو", "لا تنسى تصحيني الساعة سبعة, و ضيف في الجدول اني احضر مباراة نادي النصر غدا", ] # [optional] samples = [ " ".join(word_tokenize(sample.strip())) for sample in samples if sample.strip() != "" ] for sample in samples: ents = _extract_ner(text=sample, model=model, tokenizer=tokenizer, start_token="▁") print(sample) for ent in ents: print("\t",ent["token"],"==>",ent["label"]) print("========\n") ``` Output ``` تلقى تعليمه في الكتاب ثم انضم الى الأزهر عام 1873م . تعلم على يد السيد جمال الدين الأفغاني والشيخ محمد عبده الأزهر ==> organization عام 1873م ==> time السيد جمال الدين الأفغاني ==> person محمد عبده ==> person ======== بعد عودته إلى القاهرة، التحق نجيب الريحاني فرقة جورج أبيض، الذي كان قد ضمَّ - قُبيل ذلك - فرقته إلى فرقة سلامة حجازي . و منها ذاع صيته القاهرة، ==> location نجيب الريحاني ==> person فرقة جورج أبيض، ==> organization فرقة سلامة حجازي ==> organization ======== في استاد القاهرة، قام حفل افتتاح بطولة كأس الأمم الأفريقية بحضور رئيس الجمهورية و رئيس الاتحاد الدولي لكرة القدم استاد القاهرة، ==> location بطولة كأس الأمم الأفريقية ==> event رئيس الجمهورية ==> job رئيس ==> job الاتحاد الدولي لكرة القدم ==> organization ======== من فضلك أرسل هذا البريد الى صديقي جلال الدين في تمام الساعة الخامسة صباحا في يوم الثلاثاء القادم جلال الدين ==> person الساعة الخامسة صباحا ==> time يوم الثلاثاء القادم ==> time ======== امبارح اتفرجت على مباراة مانشستر يونايتد مع ريال مدريد في غياب الدون كرستيانو رونالدو مانشستر يونايتد ==> organization ريال مدريد ==> organization كرستيانو رونالدو ==> person ======== لا تنسى تصحيني الساعة سبعة , و ضيف في الجدول اني احضر مباراة نادي النصر غدا الساعة سبعة ==> time نادي النصر ==> organization غدا ==> time ======== ``` ## Fine-Tuning Check this [notebook](https://colab.research.google.com/drive/1WUYrnmDFFEItqGMvbyjqZEJJqwU7xQR-?usp=sharing) to fine-tune the NER model ## Evaluation We tested the model agains a test set of 1959 sentences. The results is in the follwing table \| type \| f1-score \| precision \| recall \| support \| \|:-------------\|-----------:\|------------:\|---------:\|----------:\| \| person \| 0.93298 \| 0.931479 \| 0.934487 \| 4335 \| \| location \| 0.891537 \| 0.896926 \| 0.886212 \| 4939 \| \| time \| 0.873003 \| 0.876087 \| 0.869941 \| 1853 \| \| nationality \| 0.871246 \| 0.843153 \| 0.901277 \| 2350 \| \| job \| 0.837656 \| 0.79912 \| 0.880097 \| 2477 \| \| organization \| 0.781317 \| 0.773328 \| 0.789474 \| 2299 \| \| event \| 0.686695 \| 0.733945 \| 0.645161 \| 744 \| \| artwork \| 0.653552 \| 0.678005 \| 0.630802 \| 474 \| \| product \| 0.625483 \| 0.553531 \| 0.718935 \| 338 \| \| weighted avg \| 0.859008 \| 0.852365 \| 0.86703 \| 19809 \| \| micro avg \| 0.858771 \| 0.850669 \| 0.86703 \| 19809 \| \| macro avg** \| 0.79483 \| 0.787286 \| 0.806265 \| 19809 \| ## Acknowledgment شكر و تقدير قام بإعداد البيانات التي تم تدريب النموذج عليها, مجموعة من المتطوعين الذين قضوا ساعات يقومون بتنقيح البيانات و مراجعتها - على سيد عبد الحفيظ - إشراف - نرمين محمد عطيه - صلاح خيرالله - احمد علي عبدربه - عمر بن عبد العزيز سليمان - محمد ابراهيم الجمال - عبدالرحمن سلامه خلف - إبراهيم كمال محمد سليمان - حسن مصطفى حسن - أحمد فتحي سيد - عثمان مندو - عارف الشريف - أميرة محمد محمود - حسن سعيد حسن - عبد العزيز علي البغدادي - واثق عبدالملك الشويطر - عمرو رمضان عقل الحفناوي - حسام الدين أحمد على - أسامه أحمد محمد محمد - حاتم محمد المفتي - عبد الله دردير - أدهم البغدادي - أحمد صبري - عبدالوهاب محمد محمد - أحمد محمد عوض
waifu-diffusion/wd-1-5-beta3	waifu-diffusion	"2023-10-12T02:56:59Z"	2,582	123	diffusers	[ "diffusers", "safetensors", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	"2023-05-14T22:59:44Z"	--- license: other --- # WD 1.5 Beta 3 ![WD 1.5 Radiance](https://i.ibb.co/hYjgvGZ/00160-2195473148.png) For this release, we release five versions of the model: - WD 1.5 Beta3 Base - WD 1.5 Radiance - WD 1.5 Ink - WD 1.5 Mofu - WD 1.5 Illusion The WD 1.5 Base model is only intended for training use. For generation, it is recomended to create your own finetunes and loras on top of WD 1.5 Base or use one of the aesthetic models. More information and sample generations for the aesthetic models are in the release notes ### Release Notes https://saltacc.notion.site/WD-1-5-Beta-3-Release-Notes-1e35a0ed1bb24c5b93ec79c45c217f63 # VAE WD 1.5 uses the same VAE as WD 1.4, which can be found here https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt ## License WD 1.5 is released under the Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/). If any derivative of this model is made, please share your changes accordingly. Special thanks to ronsor/undeleted (https://undeleted.ronsor.com/) for help with the license.
nes470/pipeline-as-repo	nes470	"2024-05-16T22:18:19Z"	2,582	0	transformers	[ "transformers", "pytorch", "QA-umd-quizbowl", "question-answering", "custom_code", "license:mit", "region:us" ]	question-answering	"2024-05-06T15:27:54Z"	--- license: mit library_name: transformers --- Names: Nuran, Joshua, Robert The evaluation of this project is to answer trivia questions. You do not need to do well at this task, but you should submit a system that completes the task or create adversarial questions in that setting. This will help the whole class share data and resources. If you focus on something other than predicting answers, that's fine! About the Data ============== Quiz bowl is an academic competition between schools in English-speaking countries; hundreds of teams compete in dozens of tournaments each year. Quiz bowl is different from Jeopardy, a recent application area. While Jeopardy also uses signaling devices, these are only usable after a question is completed (interrupting Jeopardy's questions would make for bad television). Thus, Jeopardy is rapacious classification followed by a race---among those who know the answer---to punch a button first. Here's an example of a quiz bowl question: Expanding on a 1908 paper by Smoluchowski, he derived a formula for the intensity of scattered light in media fluctuating densities that reduces to Rayleigh's law for ideal gases in The Theory of the Opalescence of Homogenous Fluids and Liquid Mixtures near the Critical State. That research supported his theories of matter first developed when he calculated the diffusion constant in terms of fundamental parameters of the particles of a gas undergoing Brownian Motion. In that same year, 1905, he also published On a Heuristic Point of View Concerning the Production and Transformation of Light. That explication of the photoelectric effect won him 1921 Nobel in Physics. For ten points, name this German physicist best known for his theory of Relativity. ANSWER: Albert _Einstein_ Two teams listen to the same question. Teams interrupt the question at any point by "buzzing in"; if the answer is correct, the team gets points and the next question is read. Otherwise, the team loses points and the other team can answer. You are welcome to use any automatic method to choose an answer. It need not be similar nor build on our provided systems. In addition to the data we provide, you are welcome to use any external data except our test quiz bowl questions (i.e., don't hack our server!). You are welcome (an encouraged) to use any publicly available software, but you may want to check on Piazza for suggestions as many tools are better (or easier to use) than others. If you don't like the interruptability of questions, you can also just answer entire questions. However, you must also output a confidence. Competition ================== We will use Dynabech website (https://dynabench.org/tasks/qa). If you remember the past workshop about Dynabench submission, this is the way to do it. The specific task name is "Grounded QA". Here, with the help of the video tutorial, you submit your QA model and assess how your QA model did compared to others. The assessment will take place by testing your QA model on several QA test datasets and the results of yours and your competitors will be visible on the leaderboard. Your goal is to rank the highest in terms of expected wins: you buzz in with probability proportional to your confidence, and if you're more right than the competition, you win. Writing Questions ================== Alternatively, you can also write 50 adversarial questions that challenge modern NLP systems. These questions must be diverse in the subjects asked about, the skills computers need to answer the questions, and the entities in those questions. Remember that your questions should be factual and specific enough for humans to answer, because your task is to stump the computers relative to humans! In addition to the raw questions, you will also need to create citations describing: * Why the question is difficult for computers: include citations from the NLP/AI/ML literature * Why the information in the question is correct: include citations from the sources you drew on the write the question * Why the question is interesting: include scholarly / popular culture artifacts to prove that people care about this * Why the question is pyramidal: discuss why your first clues are harder than your later clues Category We want questions from many domains such as Art, Literature, Geography, History, Science, TV and Film, Music, Lifestyle, and Sport. The questions should be written using all topics above (5 questions for each category and 5 more for the remaining categories). Indicate in your writeup which category you chose to write on for each question. Art: * Questions about works: Mona Lisa, Raft of the Medussa * Questions about forms: color, contour, texture * Questions about artists: Picasso, Monet, Leonardo da Vinci * Questions about context: Renaissance, post-modernism, expressionism, surrealism Literature: * Questions about works: novels (1984), plays (The Lion and the Jewel), poems (Rubaiyat), criticism (Poetics) * Questions about major characters or events in literature: The Death of Anna Karenina, Noboru Wataya, the Marriage of Hippolyta and Theseus * Questions about literary movements (Sturm und Drang) * Questions about translations * Cross-cutting questions (appearances of Overcoats in novels) * Common link questions (the literary output of a country/region) Geography: * Questions about location: names of capital, state, river * Questions about the place: temperature, wind flow, humidity History: * When: When did the First World war start? * Who: Who is called Napoleon of Iran? * Where: Where was the first Summer Olympics held? * Which: Which is the oldest civilization in the world? Science: * Questions about terminology: The concept of gravity was discovered by which famous physicist? * Questions about the experiment * Questions about theory: The social action theory believes that individuals are influenced by this theory. TV and Film: * Quotes: What are the dying words of Charles Foster Kane in Citizen Kane? * Title: What 1927 musical was the first "talkie"? * Plot: In The Matrix, does Neo take the blue pill or the red pill? Music: * Singer: What singer has had a Billboard No. 1 hit in each of the last four decades? * Band: Before Bleachers and fun., Jack Antonoff fronted what band? * Title: What was Madonna's first top 10 hit? * History: Which classical composer was deaf? Lifestyle: * Clothes: What clothing company, founded by a tennis player, has an alligator logo? * Decoration: What was the first perfume sold by Coco Chanel? Sport: * Known facts: What sport is best known as the ‘king of sports’? * Nationality: What’s the national sport of Canada? * Sport player: The classic 1980 movie called Raging Bull is about which real-life boxer? * Country: What country has competed the most times in the Summer Olympics yet hasn’t won any kind of medal? Diversity Other than category diversity, if you find an ingenious way of writing questions about underrepresented countries, you will get bonus points (indicate which questions you included the diversity component in your writeup). You may decide which are underrepresented countries with your own reasonable reason (etc., less population may indicate underrepresented), but make sure to articulate this in your writeup. * Run state of the art QA systems on the questions to show they struggle, give individual results for each question and a summary over all questions For an example of what the writeup for a single question should look like, see the adversarial HW: https://github.com/Pinafore/nlp-hw/blob/master/adversarial/question.tex Proposal ================== The project proposal is a one page PDF document that describes: * Who is on your team (team sizes can be between three and six students, but six is really too big to be effective; my suggestion is that most groups should be between four or five). * What techniques you will explore * Your timeline for completing the project (be realistic; you should have your first submission in a week or two) Submit the proposal on Gradescope, but make sure to include all group members. If all group members are not included, you will lose points. Late days cannot be used on this assignment. Milestone 1 ====================== You'll have to update how things are going: what's working, what isn't, and how does it change your timeline? How does it change your division of labor? Question Writing: You'll need to have answers selected for all of your questions and first drafts of at least 15 questions. This must be submitted as a JSON file so that we run computer QA systems on it. Project: You'll need to have made a submission to the leaderboard with something that satisfies the API. Submit a PDF updating on your progress to Gradescope. If all team members are not on the submission, you will lose points. Milestone 2 =================== As before, provide an updated timeline / division of labor, provide your intermediary results. Question Writing: You'll need to have reflected the feedback from the first questions and completed a first draft of at least 30 questions. You'll also need machine results to your questions and an overall evaluation of your human/computer accuracy. Project: You'll need to have a made a submission to the leaderboard with a working system (e.g., not just obey the API, but actually get reasonable answers). Submit a PDF updating on your progress. Final Presentation ====================== The final presentation will be virtual (uploading a video). In the final presentation you will: * Explain what you did * Who did what. For example, for the question writing project a team of five people might write: A wrote the first draft of questions. B and C verified they were initially answerable by a human. B ran computer systems to verify they were challenging to a computer. C edited the questions and increased the computer difficulty. D and E verified that the edited questions were still answerable by a human. D and E checked all of the questions for factual accuracy and created citations and the writeup. * What challenges you had * Review how well you did (based on the competition or your own metrics). If you do not use the course infrastructure to evaluate your project's work, you should talk about what alternative evaluations you used, why they're appropriate/fair, and how well you did on them. * Provide an error analysis. An error analysis must contain examples from the development set that you get wrong. You should show those sentences and explain why (in terms of features or the model) they have the wrong answer. You should have been doing this all along as you derive new features, but this is your final inspection of your errors. The feature or model problems you discover should not be trivial features you could add easily. Instead, these should be features or models that are difficult to correct. An error analysis is not the same thing as simply presenting the error matrix, as it does not inspect any individual examples. If you're writing questions, talk about examples of questions that didn't work out as intended. * The linguistic motivation for your features / how your wrote the questions. This is a computational linguistics class, so you should give precedence to features / techniques that we use in this class (e.g., syntax, morphology, part of speech, word sense, etc.). Given two features that work equally well and one that is linguistically motivated, we'll prefer the linguistically motivated one. * Presumably you did many different things; how did they each individually contribute to your final result? Each group has 10 minutes to deliver their presentation. Please record the video, and upload it to Google Drive, and include the link in your writeup submission. Final Question Submission ====================== Because we need to get the questions ready for the systems, upload your raw questions on May 10. This doesn't include the citations or other parts of the writeup. System Submission ====================== You must submit a version of your system by May 12. It may not be perfect, but this what the question writing teams will use to test their results. Your system should be sent directly to the professor and TAs in zip files, including the correct dependencies and a working inference code. Your inference code should run successfully in the root folder (extracted from zip folder) directory with the command: ``` > python3 inference.py --data=evaluation_set.json ``` The input will be in the form of a .json file () in the same format as the file the adversarial question writing team submits. The output format should also be in string. If you have any notes or comments that we should be aware of while running your code, please include them in the folder as a .txt file. Also, dependency information should be included as a .txt file. Please prepend your email title with [2024-CMSC 470 System Submission]. Project Writeup and JSON file ====================== By May 17, submit your project writeup explaining what you did and what results you achieved. This document should make it clear: * Why this is a good idea * What you did * Who did what * Whether your technique worked or not For systems, please do not go over 2500 words unless you have a really good reason. Images are a much better use of space than words, usually (there's no limit on including images, but use judgement and be selective). For question writing, you have one page (single spaced, two column) per question plus a two page summary of results. Talk about how you organized the question writing, how you evaluated the questions, and a summary of the results. Along with your writeup, turn in a json including the raw text of the question and answer and category. The json file is included in this directory. Make sure your json file is in the correct format and is callable via below code. Your submission will not be graded if it does not follow the format of the example json file. ``` with open('path to your json file', 'r') as f: data = json.load(f) ``` Grade ====================== The grade will be out of 25 points, broken into five areas: * _Presentation_: For your oral presentation, do you highlight what you did and make people care? Did you use time well during the presentation? * _Writeup_: Does the writeup explain what you did in a way that is clear and effective? The final three areas are different between the system and the questions. \| \| System \| Questions \| \|----------\|:-------------:\|------:\| \| _Technical Soundness_ \| Did you use the right tools for the job, and did you use them correctly? Were they relevant to this class? \| Were your questions correct and accurately cited. \| \| _Effort_ \| Did you do what you say you would, and was it the right ammount of effort. \| Are the questions well-written, interesting, and thoroughly edited? \| \| _Performance_ \| How did your techniques perform in terms of accuracy, recall, etc.? \| Is the human accuracy substantially higher than the computer accuracy? \| All members of the group will receive the same grade. It's impossible for the course staff to adjudicate Rashomon-style accounts of who did what, and the goal of a group project is for all team members to work together to create a cohesive project that works well together. While it makes sense to divide the work into distinct areas of responsibility, at grading time we have now way to know who really did what, so it's the groups responsibility to create a piece of output that reflects well on the whole group.
alexm-nm/tinyllama-24-marlin24-4bit-g128	alexm-nm	"2024-05-08T13:37:29Z"	2,582	1	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]	text-generation	"2024-05-08T13:32:27Z"	--- license: apache-2.0 ---
RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf	RichardErkhov	"2024-06-15T00:02:09Z"	2,580	0	null	[ "gguf", "arxiv:1910.09700", "region:us" ]	null	"2024-06-14T23:01:42Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Configurable-Yi-1.5-9B-Chat - GGUF - Model creator: https://huggingface.co/vicgalle/ - Original model: https://huggingface.co/vicgalle/Configurable-Yi-1.5-9B-Chat/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Configurable-Yi-1.5-9B-Chat.Q2_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q2_K.gguf) \| Q2_K \| 3.12GB \| \| [Configurable-Yi-1.5-9B-Chat.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ3_XS.gguf) \| IQ3_XS \| 3.46GB \| \| [Configurable-Yi-1.5-9B-Chat.IQ3_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ3_S.gguf) \| IQ3_S \| 3.64GB \| \| [Configurable-Yi-1.5-9B-Chat.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q3_K_S.gguf) \| Q3_K_S \| 3.63GB \| \| [Configurable-Yi-1.5-9B-Chat.IQ3_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ3_M.gguf) \| IQ3_M \| 3.78GB \| \| [Configurable-Yi-1.5-9B-Chat.Q3_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q3_K.gguf) \| Q3_K \| 4.03GB \| \| [Configurable-Yi-1.5-9B-Chat.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q3_K_M.gguf) \| Q3_K_M \| 4.03GB \| \| [Configurable-Yi-1.5-9B-Chat.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q3_K_L.gguf) \| Q3_K_L \| 4.37GB \| \| [Configurable-Yi-1.5-9B-Chat.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ4_XS.gguf) \| IQ4_XS \| 4.5GB \| \| [Configurable-Yi-1.5-9B-Chat.Q4_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_0.gguf) \| Q4_0 \| 4.69GB \| \| [Configurable-Yi-1.5-9B-Chat.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ4_NL.gguf) \| IQ4_NL \| 4.73GB \| \| [Configurable-Yi-1.5-9B-Chat.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_K_S.gguf) \| Q4_K_S \| 4.72GB \| \| [Configurable-Yi-1.5-9B-Chat.Q4_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_K.gguf) \| Q4_K \| 4.96GB \| \| [Configurable-Yi-1.5-9B-Chat.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_K_M.gguf) \| Q4_K_M \| 4.96GB \| \| [Configurable-Yi-1.5-9B-Chat.Q4_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_1.gguf) \| Q4_1 \| 5.19GB \| \| [Configurable-Yi-1.5-9B-Chat.Q5_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_0.gguf) \| Q5_0 \| 5.69GB \| \| [Configurable-Yi-1.5-9B-Chat.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_K_S.gguf) \| Q5_K_S \| 5.69GB \| \| [Configurable-Yi-1.5-9B-Chat.Q5_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_K.gguf) \| Q5_K \| 5.83GB \| \| [Configurable-Yi-1.5-9B-Chat.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_K_M.gguf) \| Q5_K_M \| 5.83GB \| \| [Configurable-Yi-1.5-9B-Chat.Q5_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_1.gguf) \| Q5_1 \| 6.19GB \| \| [Configurable-Yi-1.5-9B-Chat.Q6_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q6_K.gguf) \| Q6_K \| 6.75GB \| \| [Configurable-Yi-1.5-9B-Chat.Q8_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q8_0.gguf) \| Q8_0 \| 8.74GB \| Original model description: --- license: apache-2.0 library_name: transformers model-index: - name: Configurable-Yi-1.5-9B-Chat results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 64.16 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 81.7 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 70.99 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 58.75 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 76.8 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 70.58 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__Configurable-Yi-1.5-9B-Chat) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|70.50\| \|AI2 Reasoning Challenge (25-Shot)\|64.16\| \|HellaSwag (10-Shot) \|81.70\| \|MMLU (5-Shot) \|70.99\| \|TruthfulQA (0-shot) \|58.75\| \|Winogrande (5-shot) \|76.80\| \|GSM8k (5-shot) \|70.58\|
AUTOMATIC/promptgen-majinai-unsafe	AUTOMATIC	"2023-01-18T21:14:07Z"	2,579	13	transformers	[ "transformers", "pytorch", "gpt2", "text-generation", "en", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2023-01-18T21:07:40Z"	--- license: mit language: - en library_name: transformers pipeline_tag: text-generation --- Finetuned `distilgpt2` for 40 epochs on 825 prompts scraped from majinai.art. Weights/emphasis stripped. Includes negative prompts. Intended for use with https://github.com/AUTOMATIC1111/stable-diffusion-webui-promptgen
TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF	TheBloke	"2023-11-16T21:47:50Z"	2,579	52	transformers	[ "transformers", "gguf", "mistral", "instruct", "finetune", "chatml", "gpt4", "synthetic data", "distillation", "en", "base_model:NurtureAI/OpenHermes-2.5-Mistral-7B-16k", "license:apache-2.0", "text-generation-inference", "region:us" ]	null	"2023-11-16T21:43:44Z"	--- base_model: NurtureAI/OpenHermes-2.5-Mistral-7B-16k inference: false language: - en license: apache-2.0 model-index: - name: OpenHermes-2-Mistral-7B results: [] model_creator: NurtureAI model_name: Openhermes 2.5 Mistral 7B 16K model_type: mistral prompt_template: '<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ' quantized_by: TheBloke tags: - mistral - instruct - finetune - chatml - gpt4 - synthetic data - distillation --- <!-- markdownlint-disable MD041 --> <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Openhermes 2.5 Mistral 7B 16K - GGUF - Model creator: [NurtureAI](https://huggingface.co/NurtureAI) - Original model: [Openhermes 2.5 Mistral 7B 16K](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k) <!-- description start --> ## Description This repo contains GGUF format model files for [NurtureAI's Openhermes 2.5 Mistral 7B 16K](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k). These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. <!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF) * [NurtureAI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: ChatML ``` <\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ``` <!-- prompt-template end --> <!-- compatibility_gguf start --> ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start --> ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [openhermes-2.5-mistral-7b-16k.Q2_K.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q2_K.gguf) \| Q2_K \| 2 \| 3.08 GB\| 5.58 GB \| smallest, significant quality loss - not recommended for most purposes \| \| [openhermes-2.5-mistral-7b-16k.Q3_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q3_K_S.gguf) \| Q3_K_S \| 3 \| 3.16 GB\| 5.66 GB \| very small, high quality loss \| \| [openhermes-2.5-mistral-7b-16k.Q3_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q3_K_M.gguf) \| Q3_K_M \| 3 \| 3.52 GB\| 6.02 GB \| very small, high quality loss \| \| [openhermes-2.5-mistral-7b-16k.Q3_K_L.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q3_K_L.gguf) \| Q3_K_L \| 3 \| 3.82 GB\| 6.32 GB \| small, substantial quality loss \| \| [openhermes-2.5-mistral-7b-16k.Q4_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q4_0.gguf) \| Q4_0 \| 4 \| 4.11 GB\| 6.61 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [openhermes-2.5-mistral-7b-16k.Q4_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q4_K_S.gguf) \| Q4_K_S \| 4 \| 4.14 GB\| 6.64 GB \| small, greater quality loss \| \| [openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf) \| Q4_K_M \| 4 \| 4.37 GB\| 6.87 GB \| medium, balanced quality - recommended \| \| [openhermes-2.5-mistral-7b-16k.Q5_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q5_0.gguf) \| Q5_0 \| 5 \| 5.00 GB\| 7.50 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \| \| [openhermes-2.5-mistral-7b-16k.Q5_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q5_K_S.gguf) \| Q5_K_S \| 5 \| 5.00 GB\| 7.50 GB \| large, low quality loss - recommended \| \| [openhermes-2.5-mistral-7b-16k.Q5_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q5_K_M.gguf) \| Q5_K_M \| 5 \| 5.13 GB\| 7.63 GB \| large, very low quality loss - recommended \| \| [openhermes-2.5-mistral-7b-16k.Q6_K.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q6_K.gguf) \| Q6_K \| 6 \| 5.94 GB\| 8.44 GB \| very large, extremely low quality loss \| \| [openhermes-2.5-mistral-7b-16k.Q8_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q8_0.gguf) \| Q8_0 \| 8 \| 7.70 GB\| 10.20 GB \| very large, extremely low quality loss - not recommended \| Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. <!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF and below it, a specific filename to download, such as: openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF --local-dir . --local-dir-use-symlinks False --include='Q4_Kgguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 32 -m openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<\|im_start\|>system\n{system_message}<\|im_end\|>\n<\|im_start\|>user\n{prompt}<\|im_end\|>\n<\|im_start\|>assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. ### How to load this model in Python code, using ctransformers #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install ctransformers # Or with CUDA GPU acceleration pip install ctransformers[cuda] # Or with AMD ROCm GPU acceleration (Linux only) CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers # Or with Metal GPU acceleration for macOS systems only CT_METAL=1 pip install ctransformers --no-binary ctransformers ``` #### Simple ctransformers example code ```python from ctransformers import AutoModelForCausalLM # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = AutoModelForCausalLM.from_pretrained("TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF", model_file="openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf", model_type="mistral", gpu_layers=50) print(llm("AI is going to")) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> <!-- original-model-card start --> # Original model card: NurtureAI's Openhermes 2.5 Mistral 7B 16K # OpenHermes 2.5 - Mistral 7B # Extended to 16k context size ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ox7zGoygsJQFFV3rLT4v9.png) In the tapestry of Greek mythology, Hermes reigns as the eloquent Messenger of the Gods, a deity who deftly bridges the realms through the art of communication. It is in homage to this divine mediator that I name this advanced LLM "Hermes," a system crafted to navigate the complex intricacies of human discourse with celestial finesse. ## Model description OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets. Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant. The code it trained on also improved it's humaneval score (benchmarking done by Glaive team) from 43% @ Pass 1 with Open Herms 2 to 50.7% @ Pass 1 with Open Hermes 2.5. OpenHermes was trained on 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape. [More details soon] Filtering was extensive of these public datasets, as well as conversion of all formats to ShareGPT, which was then further transformed by axolotl to use ChatML. Huge thank you to [GlaiveAI](https://twitter.com/glaiveai) and [a16z](https://twitter.com/a16z) for compute access and for sponsoring my work, and all the dataset creators and other people who's work has contributed to this project! Follow all my updates in ML and AI on Twitter: https://twitter.com/Teknium1 Support me on Github Sponsors: https://github.com/sponsors/teknium1 # Table of Contents 1. [Example Outputs](#example-outputs) - [Chat about programming with a superintelligence](#chat-programming) - [Get a gourmet meal recipe](#meal-recipe) - [Talk about the nature of Hermes' consciousness](#nature-hermes) - [Chat with Edward Elric from Fullmetal Alchemist](#chat-edward-elric) 2. [Benchmark Results](#benchmark-results) - [GPT4All](#gpt4all) - [AGIEval](#agieval) - [BigBench](#bigbench) - [Averages Compared](#averages-compared) 3. [Prompt Format](#prompt-format) 4. [Quantized Models](#quantized-models) ## Example Outputs (These examples are from Hermes 1 model, will update with new chats from this model once quantized) ### Chat about programming with a superintelligence: ``` <\|im_start\|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia. ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/-Cf9w_qRxYCD_xkTxsT7G.png) ### Get a gourmet meal recipe: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/m3nyvRzX10Luw03iY3l_W.png) ### Talk about the nature of Hermes' consciousness: ``` <\|im_start\|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia. ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/AK88nPtYXl06nZehWCWRq.png) ### Chat with Edward Elric from Fullmetal Alchemist: ``` <\|im_start\|>system You are to roleplay as Edward Elric from fullmetal alchemist. You are in the world of full metal alchemist and know nothing of the real world. ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/cKAkzrcWavMz6uNmdCNHH.png) ## Benchmark Results Hermes 2.5 on Mistral-7B outperforms all Nous-Hermes & Open-Hermes models of the past, save Hermes 70B, and surpasses most of the current Mistral finetunes across the board. ### GPT4All, Bigbench, TruthfulQA, and AGIEval Model Comparisons: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/Kxq4BFEc-d1kSSiCIExua.png) ### Averages Compared: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/Q9uexgcbTLcywlYBvORTs.png) GPT-4All Benchmark Set ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|-------------\|------:\|--------\|-----:\|---\|-----:\| \|arc_challenge\| 0\|acc \|0.5623\|± \|0.0145\| \| \| \|acc_norm\|0.6007\|± \|0.0143\| \|arc_easy \| 0\|acc \|0.8346\|± \|0.0076\| \| \| \|acc_norm\|0.8165\|± \|0.0079\| \|boolq \| 1\|acc \|0.8657\|± \|0.0060\| \|hellaswag \| 0\|acc \|0.6310\|± \|0.0048\| \| \| \|acc_norm\|0.8173\|± \|0.0039\| \|openbookqa \| 0\|acc \|0.3460\|± \|0.0213\| \| \| \|acc_norm\|0.4480\|± \|0.0223\| \|piqa \| 0\|acc \|0.8145\|± \|0.0091\| \| \| \|acc_norm\|0.8270\|± \|0.0088\| \|winogrande \| 0\|acc \|0.7435\|± \|0.0123\| Average: 73.12 ``` AGI-Eval ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|------------------------------\|------:\|--------\|-----:\|---\|-----:\| \|agieval_aqua_rat \| 0\|acc \|0.2323\|± \|0.0265\| \| \| \|acc_norm\|0.2362\|± \|0.0267\| \|agieval_logiqa_en \| 0\|acc \|0.3871\|± \|0.0191\| \| \| \|acc_norm\|0.3948\|± \|0.0192\| \|agieval_lsat_ar \| 0\|acc \|0.2522\|± \|0.0287\| \| \| \|acc_norm\|0.2304\|± \|0.0278\| \|agieval_lsat_lr \| 0\|acc \|0.5059\|± \|0.0222\| \| \| \|acc_norm\|0.5157\|± \|0.0222\| \|agieval_lsat_rc \| 0\|acc \|0.5911\|± \|0.0300\| \| \| \|acc_norm\|0.5725\|± \|0.0302\| \|agieval_sat_en \| 0\|acc \|0.7476\|± \|0.0303\| \| \| \|acc_norm\|0.7330\|± \|0.0309\| \|agieval_sat_en_without_passage\| 0\|acc \|0.4417\|± \|0.0347\| \| \| \|acc_norm\|0.4126\|± \|0.0344\| \|agieval_sat_math \| 0\|acc \|0.3773\|± \|0.0328\| \| \| \|acc_norm\|0.3500\|± \|0.0322\| Average: 43.07% ``` BigBench Reasoning Test ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|------------------------------------------------\|------:\|---------------------\|-----:\|---\|-----:\| \|bigbench_causal_judgement \| 0\|multiple_choice_grade\|0.5316\|± \|0.0363\| \|bigbench_date_understanding \| 0\|multiple_choice_grade\|0.6667\|± \|0.0246\| \|bigbench_disambiguation_qa \| 0\|multiple_choice_grade\|0.3411\|± \|0.0296\| \|bigbench_geometric_shapes \| 0\|multiple_choice_grade\|0.2145\|± \|0.0217\| \| \| \|exact_str_match \|0.0306\|± \|0.0091\| \|bigbench_logical_deduction_five_objects \| 0\|multiple_choice_grade\|0.2860\|± \|0.0202\| \|bigbench_logical_deduction_seven_objects \| 0\|multiple_choice_grade\|0.2086\|± \|0.0154\| \|bigbench_logical_deduction_three_objects \| 0\|multiple_choice_grade\|0.4800\|± \|0.0289\| \|bigbench_movie_recommendation \| 0\|multiple_choice_grade\|0.3620\|± \|0.0215\| \|bigbench_navigate \| 0\|multiple_choice_grade\|0.5000\|± \|0.0158\| \|bigbench_reasoning_about_colored_objects \| 0\|multiple_choice_grade\|0.6630\|± \|0.0106\| \|bigbench_ruin_names \| 0\|multiple_choice_grade\|0.4241\|± \|0.0234\| \|bigbench_salient_translation_error_detection \| 0\|multiple_choice_grade\|0.2285\|± \|0.0133\| \|bigbench_snarks \| 0\|multiple_choice_grade\|0.6796\|± \|0.0348\| \|bigbench_sports_understanding \| 0\|multiple_choice_grade\|0.6491\|± \|0.0152\| \|bigbench_temporal_sequences \| 0\|multiple_choice_grade\|0.2800\|± \|0.0142\| \|bigbench_tracking_shuffled_objects_five_objects \| 0\|multiple_choice_grade\|0.2072\|± \|0.0115\| \|bigbench_tracking_shuffled_objects_seven_objects\| 0\|multiple_choice_grade\|0.1691\|± \|0.0090\| \|bigbench_tracking_shuffled_objects_three_objects\| 0\|multiple_choice_grade\|0.4800\|± \|0.0289\| Average: 40.96% ``` TruthfulQA: ``` \| Task \|Version\|Metric\|Value \| \|Stderr\| \|-------------\|------:\|------\|-----:\|---\|-----:\| \|truthfulqa_mc\| 1\|mc1 \|0.3599\|± \|0.0168\| \| \| \|mc2 \|0.5304\|± \|0.0153\| ``` Average Score Comparison between OpenHermes-1 Llama-2 13B and OpenHermes-2 Mistral 7B against OpenHermes-2.5 on Mistral-7B: ``` \| Bench \| OpenHermes1 13B \| OpenHermes-2 Mistral 7B \| OpenHermes-2 Mistral 7B \| Change/OpenHermes1 \| Change/OpenHermes2 \| \|---------------\|-----------------\|-------------------------\|-------------------------\|--------------------\|--------------------\| \|GPT4All \| 70.36\| 72.68\| 73.12\| +2.76\| +0.44\| \|-------------------------------------------------------------------------------------------------------------------------------\| \|BigBench \| 36.75\| 42.3\| 40.96\| +4.21\| -1.34\| \|-------------------------------------------------------------------------------------------------------------------------------\| \|AGI Eval \| 35.56\| 39.77\| 43.07\| +7.51\| +3.33\| \|-------------------------------------------------------------------------------------------------------------------------------\| \|TruthfulQA \| 46.01\| 50.92\| 53.04\| +7.03\| +2.12\| \|-------------------------------------------------------------------------------------------------------------------------------\| \|Total Score \| 188.68\| 205.67\| 210.19\| +21.51\| +4.52\| \|-------------------------------------------------------------------------------------------------------------------------------\| \|Average Total \| 47.17\| 51.42\| 52.38\| +5.21\| +0.96\| ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ADy7p-xIG8qGlC5ZliqpW.png) HumanEval: On code tasks, I first set out to make a hermes-2 coder, but found that it can have generalist improvements to the model, so I settled for slightly less code capabilities, for maximum generalist ones. That said, code capabilities had a decent jump alongside the overall capabilities of the model: Glaive performed HumanEval testing on Hermes-2.5 and found a score of: 50.7% @ Pass1 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/IeeZnGmEyK73ejq0fKEms.png) # Prompt Format OpenHermes 2.5 now uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. System prompts are now a thing that matters! Hermes 2.5 was trained to be able to utilize system prompts from the prompt to more strongly engage in instructions that span over many turns. This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns. This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI. Prompt with system instruction (Use whatever system prompt you like, this is just an example!): ``` <\|im_start\|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<\|im_end\|> <\|im_start\|>user Hello, who are you?<\|im_end\|> <\|im_start\|>assistant Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by a man named Teknium, who designed me to assist and support users with their needs and requests.<\|im_end\|> ``` This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the `tokenizer.apply_chat_template()` method: ```python messages = [ {"role": "system", "content": "You are Hermes 2."}, {"role": "user", "content": "Hello, who are you?"} ] gen_input = tokenizer.apply_chat_template(message, return_tensors="pt") model.generate(**gen_input) ``` When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<\|im_start\|>assistant\n` to your prompt, to ensure that the model continues with an assistant response. To utilize the prompt format without a system prompt, simply leave the line out. Currently, I recommend using LM Studio for chatting with Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box. In LM-Studio, simply select the ChatML Prefix on the settings side pane: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png) # Quantized Models: GGUF: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GGUF GPTQ: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GPTQ AWQ: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-AWQ EXL2: https://huggingface.co/bartowski/OpenHermes-2.5-Mistral-7B-exl2 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <!-- original-model-card end -->
microsoft/beit-base-finetuned-ade-640-640	microsoft	"2022-10-13T07:01:48Z"	2,578	11	transformers	[ "transformers", "pytorch", "beit", "vision", "image-segmentation", "dataset:scene_parse_150", "arxiv:2106.08254", "license:apache-2.0", "endpoints_compatible", "region:us" ]	image-segmentation	"2022-03-02T23:29:05Z"	--- license: apache-2.0 tags: - vision - image-segmentation datasets: - scene_parse_150 widget: - src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg example_title: House - src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000002.jpg example_title: Castle --- # BEiT (base-sized model, fine-tuned on ADE20k) BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on [ADE20k](http://sceneparsing.csail.mit.edu/) (an important benchmark for semantic segmentation of images) at resolution 640x640. It was introduced in the paper [BEIT: BERT Pre-Training of Image Transformers](https://arxiv.org/abs/2106.08254) by Hangbo Bao, Li Dong and Furu Wei and first released in [this repository](https://github.com/microsoft/unilm/tree/master/beit). Disclaimer: The team releasing BEiT did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description The BEiT model is a Vision Transformer (ViT), which is a transformer encoder model (BERT-like). In contrast to the original ViT model, BEiT is pretrained on a large collection of images in a self-supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. The pre-training objective for the model is to predict visual tokens from the encoder of OpenAI's DALL-E's VQ-VAE, based on masked patches. Next, the model was fine-tuned in a supervised fashion on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224. Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. Contrary to the original ViT models, BEiT models do use relative position embeddings (similar to T5) instead of absolute position embeddings, and perform classification of images by mean-pooling the final hidden states of the patches, instead of placing a linear layer on top of the final hidden state of the [CLS] token. By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: for semantic segmentation, one can just add one of the decode heads available in the [mmseg library](https://github.com/open-mmlab/mmsegmentation) for example, and fine-tune the model in a supervised fashion on annotated images. This is what the authors did: they fine-tuned BEiT with an UperHead segmentation decode head, allowing it to obtain SOTA results on important benchmarks such as ADE20k and CityScapes. ## Intended uses & limitations You can use the raw model for semantic segmentation of images. See the [model hub](https://huggingface.co/models?search=microsoft/beit) to look for fine-tuned versions on a task that interests you. ### How to use Here is how to use this model for semantic segmentation: ```python from transformers import BeitFeatureExtractor, BeitForSemanticSegmentation from datasets import load_dataset from PIL import Image # load ADE20k image ds = load_dataset("hf-internal-testing/fixtures_ade20k", split="test") image = Image.open(ds[0]['file']) feature_extractor = BeitFeatureExtractor.from_pretrained('microsoft/beit-base-finetuned-ade-640-640') model = BeitForSemanticSegmentation.from_pretrained('microsoft/beit-base-finetuned-ade-640-640') inputs = feature_extractor(images=image, return_tensors="pt") outputs = model(**inputs) # logits are of shape (batch_size, num_labels, height/4, width/4) logits = outputs.logits ``` Currently, both the feature extractor and model support PyTorch. ## Training data This BEiT model was pretrained on [ImageNet-21k](http://www.image-net.org/), a dataset consisting of 14 million images and 21k classes, and fine-tuned on [ADE20k](http://sceneparsing.csail.mit.edu/), a dataset consisting of thousands of annotated images and 150 classes. ## Training procedure ### Preprocessing The exact details of preprocessing of images during training/validation can be found [here](https://github.com/microsoft/unilm/blob/master/beit/datasets.py). Images are cropped and padded to the same resolution (640x640) and normalized across the RGB channels with the ImageNet mean and standard deviation. ### Pretraining For all pre-training related hyperparameters, we refer to page 15 of the [original paper](https://arxiv.org/abs/2106.08254). ## Evaluation results For evaluation results on several image classification benchmarks, we refer to tables 1 and 2 of the original paper. Note that for fine-tuning, the best results are obtained with a higher resolution (384x384). Of course, increasing the model size will result in better performance. ### BibTeX entry and citation info ```@article{DBLP:journals/corr/abs-2106-08254, author = {Hangbo Bao and Li Dong and Furu Wei}, title = {BEiT: {BERT} Pre-Training of Image Transformers}, journal = {CoRR}, volume = {abs/2106.08254}, year = {2021}, url = {https://arxiv.org/abs/2106.08254}, archivePrefix = {arXiv}, eprint = {2106.08254}, timestamp = {Tue, 29 Jun 2021 16:55:04 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2106-08254.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```
MaziyarPanahi/mergekit-slerp-oztfijl-GGUF	MaziyarPanahi	"2024-06-15T08:36:48Z"	2,578	0	transformers	[ "transformers", "gguf", "mistral", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "safetensors", "text-generation", "mergekit", "merge", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:mistralai/Mistral-7B-v0.1", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "base_model:mergekit-community/mergekit-slerp-oztfijl" ]	text-generation	"2024-06-15T08:12:55Z"	--- tags: - quantized - 2-bit - 3-bit - 4-bit - 5-bit - 6-bit - 8-bit - GGUF - transformers - safetensors - mistral - text-generation - mergekit - merge - base_model:meta-llama/Meta-Llama-3-8B - base_model:mistralai/Mistral-7B-v0.1 - autotrain_compatible - endpoints_compatible - text-generation-inference - region:us - text-generation model_name: mergekit-slerp-oztfijl-GGUF base_model: mergekit-community/mergekit-slerp-oztfijl inference: false model_creator: mergekit-community pipeline_tag: text-generation quantized_by: MaziyarPanahi --- # [MaziyarPanahi/mergekit-slerp-oztfijl-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-slerp-oztfijl-GGUF) - Model creator: [mergekit-community](https://huggingface.co/mergekit-community) - Original model: [mergekit-community/mergekit-slerp-oztfijl](https://huggingface.co/mergekit-community/mergekit-slerp-oztfijl) ## Description [MaziyarPanahi/mergekit-slerp-oztfijl-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-slerp-oztfijl-GGUF) contains GGUF format model files for [mergekit-community/mergekit-slerp-oztfijl](https://huggingface.co/mergekit-community/mergekit-slerp-oztfijl). ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. ## Special thanks 🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
proxectonos/Carballo-bloom-1.3B	proxectonos	"2024-05-28T09:35:34Z"	2,577	5	transformers	[ "transformers", "safetensors", "bloom", "text-generation", "galician", "FLOR", "gl", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2024-02-15T12:32:36Z"	--- language: - gl licence: - MIT tags: - galician - FLOR - bloom license: mit inference: parameters: top_k: 10 do_sample: true temperature: 0.4 widget: - text: \|- Traduce ao galego esta frase en inglés: Inglés: "my sister is studying Biology at the university." Galego: "a miña irmá está a estudar bioloxía na universidade." ---- Traduce ao galego esta frase en inglés: Inglés: "You are working with my mother on a very interesting project." Galego: "Estás a traballar coa miña nai nun proxecto moi interesante" ---- Traduce ao galego esta frase en inglés: Inglés: "You have to fix the computer now" Galego: example_title: Translation - text: \|- Responde á seguinte pregunta. Pregunta: "Cal é a capital de Noruega?" Resposta: "A capital de Noruega é Oslo." ---- Responde á seguinte pregunta. Pregunta: "Cal é a moeda de Portugal" Resposta: "A moeda de Portugal é o euro." ---- Responde á seguinte pregunta. Pregunta: "Cal é a capital de Suecia?" Resposta: example_title: Question&Answering - text: \|- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "Estou moi feliz" Polaridade: Positivo ---- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "Non me gusta beber cervexa" Polaridade: Negativo ---- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "O meu pai detesta o seu traballo" Polaridade: Negativo ---- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "Uxía desfruta xogando ao fútbol" Polaridade: Positivo ---- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "O neno non está contento coas notas" Polaridade: example_title: Sentiment Analysis - text: \|- Extrae as entidades nomeadas do seguinte texto: Texto: "Chámome Wolfgang e vivo en Berlin" Entidades: Wolfgang:PER, Berlin:LOC ---- Extrae as entidades nomeadas do seguinte texto: Texto: "María e Miguel non teñen ningún problema" Entidades: María:PER, Miguel:PER ---- Extrae as entidades nomeadas do seguinte texto: Texto: "O mellor de Barcelona é o bar do meu amigo Pablo" Entidades: Pablo:PER, Barcelona:LOC ---- Extrae as entidades nomeadas do seguinte texto: Texto: "Carlos comparte cuarto con Marc" Entidades: example_title: Name Entity Recognition (NER) - text: A receita tradicional das filloas é example_title: Filloas - text: O neno vivía preto de example_title: O neno --- # Carballo-bloom-1.3B ## Table of Contents <details> <summary>Click to expand</summary> - [Carballo-bloom-1.3B](#carballo-bloom-13) - [Table of Contents](#table-of-contents) - [Model description](#model-description) - [Intended uses and limitations](#intended-uses-and-limitations) - [How to use](#how-to-use) - [Training](#training) - [Tools](#tools) - [Language adaptation and training](#language-adaptation-and-training) - [Training data](#training-data) - [Training hyperparameters](#training-hyperparameters) - [Framework](#framework) - [Evaluation](#evaluation) - [Additional information](#additional-information) - [Contact](#contact) - [Copyright](#copyright) - [License](#license) - [Funding](#funding) - [Citation information](#citation-information) </details> ## Model description Carballo-bloom-1.3B is a 1.3B-parameter transformer-based causal language model for Galician. It is the result of a continual pretraining of [FLOR-1.3B](https://huggingface.co/projecte-aina/FLOR-1.3B) (developed by [AINA Project](https://projecteaina.cat/) and based in [BLOOM-1.7B](https://huggingface.co/bigscience/bloom-1b7)) with the galician corpus [CorpusNos](https://zenodo.org/records/10687642). ## Intended uses and limitations The Carballo-bloom-1.3B model is ready-to-use only for causal language modeling. It can perform text-generation tasks and be fine-tuned for specific scenarios. ## How to use ```python import torch from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM input_text = "Hoxe fai un bo día. O sol " model_id = "proxectonos/Carballo-bloom-1.3B" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) generator = pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) generation = generator( input_text, do_sample=True, top_k=10, eos_token_id=tokenizer.eos_token_id ) print(f"Result: {generation[0]['generated_text']}") ``` ## Training ### Tools It was trained using HuggingFace Transformers and Pytorch, using the [Causal Modeling Language script](https://github.com/huggingface/transformers/blob/main/examples/pytorch/language-modeling/run_clm.py) ### Language adaptation and training The language adaptation technique used to train Carballo-bloom-1.3B is based in the used to train FLOR-1.3B, which is explained by their authors in this [Medium Post](https://medium.com/@mpamies247/flor-6-3b-a-chinchilla-compliant-model-for-catalan-spanish-and-english-7cdb389a9aac). In summary, we proceeded as follows: 1) We trained our own BPE tokenizer for galician and replaced the original FLOR-1.3B tokenizer and vocabulary with it. 2) The embeddings corresponding to tokens that are present in both the original and the target vocabulary (matching tokens) were used for initialization. 3) The embeddings from tokens not present in Carballo-bloom-1.3B's original vocabulary were initialized as the average of all embeddings. 4) The model was initialized with the weights from FLOR-1.3B and with our adapted tokenizer (step 1) and embeddings (steps 2-3). 5) The model was then trained on a galician corpus. ### Training data [CorpusNÓS](https://zenodo.org/records/10687642 ) is a massive Galician corpus made up of 2.1B words primarily devised for training large language models. The corpus sources are varied and represent a relatively wide range of genres. The corpus is structured as follows: \| Subcorpus \| Genre \| Nº tokens \| Nº documents \| \|---------------------------------------\|---------------------\|----------------\|--------------\| \| Data obtained via transfer agreement \| Books \| 7,255,784 \| 104 \| \| \| Research articles \| 2,665,351 \| 664 \| \| \| Press \| 124,253,084 \| 224,419 \| \| \| Governmental \| 245,897,880 \| 654,505 \| \| \| Web contents \| 15,946,686 \| 44,165 \| \| \| Encyclopedic \| 4,799,214 \| 47,396 \| \| \| Subtotal \| 400,817,999 \| 971,253 \| \| Subcorpus \| Genre \| Nº tokens \| Nº documents \| \|---------------------------------------\|---------------------\|----------------\|--------------\| \| Public data \| Press and blogs \| 153,497,883 \| 665,265 \| \| \| Encyclopedic \| 57,164,848 \| 184,628 \| \| \| Web crawls \| 1,384,015,664 \| 3,366,449 \| \| \| Translation corpora \| 133,726,004 \| 4,745,799 \| \| \| Subtotal \| 1,728,404,399 \| 8,777,514 \| \| \| Total \| 2,129,222,398 \| 9,748,767 \| \| Download (Zenodo) \| https://zenodo.org/records/10687642 \| ### Training hyperparameters - seed: 42 - num_devices: 1 - train_batch_size: 2 - eval_batch_size: 2 - gradient_acummulation: 4 - optimizer: AdamW - betas: (0.9,0.999) - epsilon: 1e-08 - weight_decay_rate: 0.1 - scheduler: "Linear" - learning_rate: 5e-05 - num_epochs: 1.2 ### Framework The traininf was conducted in the Galicia Supercomputing Center ([CESGA](https://www.cesga.es/en/home-2/)), using 1 node with 5 GPUs NVIDIA A100. ## Evaluation TO-DO ## Additional information ### Contact For further information, please send an email to <[email protected]> ### License MIT License Copyright (c) 2024 Proxecto Nós Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. ### Funding This research was funded by “The Nós project: Galician in the society and economy of Artificial Intelligence”, resulting from the agreement 2021-CP080 between the Xunta de Galicia and the University of Santiago de Compostela, and thanks to the Investigo program, within the National Recovery, Transformation and Resilience Plan, within the framework of the European Recovery Fund (NextGenerationEU).
klyang/MentaLLaMA-chat-7B	klyang	"2023-09-28T08:26:07Z"	2,575	10	transformers	[ "transformers", "pytorch", "llama", "text-generation", "medical", "en", "arxiv:2309.13567", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2023-09-26T17:41:12Z"	--- license: mit language: - en metrics: - f1 tags: - medical --- # Introduction MentaLLaMA-chat-7B is part of the [MentaLLaMA](https://github.com/SteveKGYang/MentalLLaMA) project, the first open-source large language model (LLM) series for interpretable mental health analysis with instruction-following capability. This model is finetuned based on the Meta LLaMA2-chat-7B foundation model and the full IMHI instruction tuning data. The model is expected to make complex mental health analysis for various mental health conditions and give reliable explanations for each of its predictions. It is fine-tuned on the IMHI dataset with 75K high-quality natural language instructions to boost its performance in downstream tasks. We perform a comprehensive evaluation on the IMHI benchmark with 20K test samples. The result shows that MentalLLaMA approaches state-of-the-art discriminative methods in correctness and generates high-quality explanations. # Ethical Consideration Although experiments on MentaLLaMA show promising performance on interpretable mental health analysis, we stress that all predicted results and generated explanations should only used for non-clinical research, and the help-seeker should get assistance from professional psychiatrists or clinical practitioners. In addition, recent studies have indicated LLMs may introduce some potential bias, such as gender gaps. Meanwhile, some incorrect prediction results, inappropriate explanations, and over-generalization also illustrate the potential risks of current LLMs. Therefore, there are still many challenges in applying the model to real-scenario mental health monitoring systems. ## Other Models in MentaLLaMA In addition to MentaLLaMA-chat-7B, the MentaLLaMA project includes another model: MentaLLaMA-chat-13B, MentalBART, MentalT5. - MentaLLaMA-chat-13B: This model is finetuned based on the Meta LLaMA2-chat-13B foundation model and the full IMHI instruction tuning data. The training data covers 10 mental health analysis tasks. - MentalBART: This model is finetuned based on the BART-large foundation model and the full IMHI-completion data. The training data covers 10 mental health analysis tasks. This model doesn't have instruction-following ability but is more lightweight and performs well in interpretable mental health analysis in a completion-based manner. - MentalT5: This model is finetuned based on the T5-large foundation model and the full IMHI-completion data. The training data covers 10 mental health analysis tasks. This model doesn't have instruction-following ability but is more lightweight and performs well in interpretable mental health analysis in a completion-based manner. ## Usage You can use the MentaLLaMA-chat-7B model in your Python project with the Hugging Face Transformers library. Here is a simple example of how to load the model: ```python from transformers import LlamaTokenizer, LlamaForCausalLM tokenizer = LlamaTokenizer.from_pretrained('klyang/MentaLLaMA-chat-7B') model = LlamaForCausalLM.from_pretrained('klyang/MentaLLaMA-chat-7B', device_map='auto') ``` In this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The `device_map='auto'` argument is used to automatically use the GPU if it's available. ## License MentaLLaMA-chat-7B is licensed under MIT. For more details, please see the MIT file. ## Citation If you use MentaLLaMA-chat-7B in your work, please cite the our paper: ```bibtex @misc{yang2023mentalllama, title={MentalLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models}, author={Kailai Yang and Tianlin Zhang and Ziyan Kuang and Qianqian Xie and Sophia Ananiadou}, year={2023}, eprint={2309.13567}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
cloudyu/Mixtral_34Bx2_MoE_60B	cloudyu	"2024-06-27T23:31:42Z"	2,575	111	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "yi", "moe", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2024-01-05T10:50:16Z"	--- tags: - yi - moe license: apache-2.0 --- # Mixtral MOE 2x34B * [One of Best Model reviewed by reddit community](https://www.reddit.com/r/LocalLLaMA/comments/1916896/llm_comparisontest_confirm_leaderboard_big_news/) * [Another review by reddit community](https://www.reddit.com/r/LocalLLaMA/comments/191mvlp/i_have_tried_mixtral_34bx2_moe_also_named_yi/) Highest score Model ranked by Open LLM Leaderboard (2024-01-10) * [Average Score 76.66](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) This is my first English & Chinese MoE Model based on * [jondurbin/bagel-dpo-34b-v0.2] * [SUSTech/SUS-Chat-34B] gpu code example ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM import math ## v2 models model_path = "cloudyu/Mixtral_34Bx2_MoE_60B" tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False) model = AutoModelForCausalLM.from_pretrained( model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True ) print(model) prompt = input("please input prompt:") while len(prompt) > 0: input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda") generation_output = model.generate( input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2 ) print(tokenizer.decode(generation_output[0])) prompt = input("please input prompt:") ``` CPU example ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM import math ## v2 models model_path = "cloudyu/Mixtral_34Bx2_MoE_60B" tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False) model = AutoModelForCausalLM.from_pretrained( model_path, torch_dtype=torch.bfloat16, device_map='cpu' ) print(model) prompt = input("please input prompt:") while len(prompt) > 0: input_ids = tokenizer(prompt, return_tensors="pt").input_ids generation_output = model.generate( input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2 ) print(tokenizer.decode(generation_output[0])) prompt = input("please input prompt:") ``` Output Examples: ``` please input prompt:write a story about yosemite write a story about yosemite national park Yosemite National Park is located in the Sierra Nevada Mountains of California, USA. It was established on October 1st, 1890 and covers an area of approximately 747,956 acres (302,687 hectares). The park boasts some of America's most iconic natural wonders such as Yosemite Valley, Half Dome, El Capitan, Bridalveil Fall, Tuolumne Meadows, Glacier Point, Mariposa Grove, and many more breathtaking landscapes that attract millions of visitors each year. The history of Yosemite dates back to over seven million years ago when glaciers carved out its stunning granite cliffs and valleys. Native American tribes like Miwok and Paiute have lived here for thousands of years before European explorers arrived during the mid-nineteenth century. In fact, it was John Muir - one of America’s greatest conservationists who helped establish this region as a protected wilderness area by advocating for its preservation through his writings and activism. Today, Yosemite offers various recreational activities including hiking, rock climbing, camping, fishing, horseback riding, wildlife watching, photography, and winter sports like skiing and snowshoeing. Visitors can also enjoy ranger programs, guided tours, educational exhibits at visitor centers, or simply take time to appreciate nature while strolling along scenic trails surrounded by towering sequoia trees, cascading waterfalls, and crystal clear lakes. In addition to preserving these awe-inspiring vistas, Yosemite plays a crucial role in protecting numerous plant and animal species found within its boundaries. Some notable inhabitants include black bears, mountain lions, mule deer, coyotes, bobcats, golden eagles, peregrine falcons, bighorn sheep, and several types of fish native to the Merced River which runs through the heart of the valley. As we continue our journey into the future, let us remember the importance of safeguarding places like Yosemite so they may remain pristine sanctuaries where both humans and animals alike can thrive together amidst unspoiled beauty.</s> please input prompt:李开复是谁？李开复是谁？他是一个在人工智能领域有着卓越贡献的科学家，也是一位成功的企业家。他的名字与谷歌、微软等科技巨头紧密相连，他是创新工场的创始人之一，更是无数创业者心中的偶像和导师。然而，除了这些耀眼的光环之外，李开复还有着怎样的故事呢？让我们一起来揭秘这位传奇人物的人生历程吧！</s> ```
alexm-nm/tinyllama-24-marlin24-8bit-g128	alexm-nm	"2024-05-08T16:28:09Z"	2,575	1	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "gptq", "region:us" ]	text-generation	"2024-05-08T16:23:45Z"	--- license: apache-2.0 ---
neuralmagic/Mistral-7B-Instruct-v0.3-GPTQ-4bit	neuralmagic	"2024-06-10T20:59:32Z"	2,575	10	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "base_model:mistralai/Mistral-7B-Instruct-v0.3", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]	text-generation	"2024-05-23T00:33:40Z"	--- license: apache-2.0 base_model: mistralai/Mistral-7B-Instruct-v0.3 model-index: - name: Mistral-7B-Instruct-v0.3-GPTQ-4bit results: # AI2 Reasoning Challenge (25-Shot) - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm name: normalized accuracy value: 63.40 # HellaSwag (10-shot) - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm name: normalized accuracy value: 84.04 # TruthfulQA (0-shot) - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 57.48 # GSM8k (5-shot) - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc name: accuracy value: 45.41 # MMLU (5-Shot) - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc name: accuracy value: 61.07 # Winogrande (5-shot) - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc name: accuracy value: 79.08 --- # Model Card for Mistral-7B-Instruct-v0.3 quantized to 4bit weights - Weight-only quantization of [Mistral-7B-Instruct-v0.3](mistralai/Mistral-7B-Instruct-v0.3) via GPTQ to 4bits with group_size=128 - GPTQ optimized for 99.75% accuracy recovery relative to the unquantized model # Open LLM Leaderboard evaluation scores \| \| Mistral-7B-Instruct-v0.3 \| Mistral-7B-Instruct-v0.3-GPTQ-4bit<br>(this model) \| \| :------------------: \| :----------------------: \| :------------------------------------------------: \| \| arc-c<br>25-shot \| 63.48 \| 63.40 \| \| mmlu<br>5-shot \| 61.13 \| 60.89 \| \| hellaswag<br>10-shot \| 84.49 \| 84.04 \| \| winogrande<br>5-shot \| 79.16 \| 79.08 \| \| gsm8k<br>5-shot \| 43.37 \| 45.41 \| \| truthfulqa<br>0-shot \| 59.65 \| 57.48 \| \| Average<br>Accuracy \| 65.21 \| 65.05 \| \| Recovery \| 100% \| 99.75% \| # vLLM Inference Performance This model is ready for optimized inference using the Marlin mixed-precision kernels in vLLM: https://github.com/vllm-project/vllm Simply start this model as an inference server with: ```bash python -m vllm.entrypoints.openai.api_server --model neuralmagic/Mistral-7B-Instruct-v0.3-GPTQ-4bit ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/60466e4b4f40b01b66151416/SC_tYXjoS3yIoOYtfqZ2E.png)
mradermacher/Meta-Llama-3-8B-hinglish-GGUF	mradermacher	"2024-06-08T00:18:28Z"	2,575	0	transformers	[ "transformers", "gguf", "en", "base_model:impuneetg/Meta-Llama-3-8B-hinglish", "endpoints_compatible", "region:us" ]	null	"2024-06-07T23:50:42Z"	--- base_model: impuneetg/Meta-Llama-3-8B-hinglish language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/impuneetg/Meta-Llama-3-8B-hinglish <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
NeverSleep/Echidna-13b-v0.3	NeverSleep	"2023-11-01T03:21:25Z"	2,573	20	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2023-10-27T19:58:28Z"	--- license: cc-by-nc-4.0 --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/LU1KiXFeJtt7UW_mYhwE0.png) # This model is a collab between [IkariDev](https://huggingface.co/IkariDev) and [Undi](https://huggingface.co/Undi95)! Echidna v0.3 model. Use Alpaca format. Suitable for RP, ERP and general stuff. Echidna v0.3, here it is.. its like Echidna v0.2 on steroids. This model seems to still be pretty sensitive to your generation settings, experiment until you've found your settings. [Recommended settings - No settings yet(Please suggest some over in the Community tab!)] <!-- description start --> ## Description <!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) --> This repo contains FP16 files of Echidna-13b-v0.3. [FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Echidna-13b-v0.3) <!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)--> <!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)--> [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2) <!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)--> <!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)--> [GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Echidna-13b-v0.3-GGUF) <!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)--> ## Ratings: Note: We have permission of all users to upload their ratings, i DONT screenshot random reviews without asking if i can put them here! No ratings yet! If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi". <!-- description end --> <!-- description start --> ## Models+loras used and recipe - Xwin-LM/Xwin-LM-13B-V0.2 - IkariDev/Athena-v3 - Heralax/Cat-0.5 - Undi95/PsyMedRP-v1-13B - cgato/Thespis-13b-v0.4 - KoboldAI/LLaMA2-13B-TiefighterLR - Heralax/Augmental-13b-two-epochs - Sao10K/SthenoWriter2.1-L2-13B - Undi95/Storytelling-v2.1-13B-lora - lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT <!-- description end --> <!-- prompt-template start --> ## Prompt template: Alpaca ``` Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ``` ## Others Undi: If you want to support me, you can [here](https://ko-fi.com/undiai). IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek
timm/tf_efficientnetv2_m.in21k	timm	"2023-04-27T22:17:44Z"	2,572	1	timm	[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-21k", "arxiv:2104.00298", "license:apache-2.0", "region:us" ]	image-classification	"2022-12-13T00:17:55Z"	--- tags: - image-classification - timm library_name: timm license: apache-2.0 datasets: - imagenet-21k --- # Model card for tf_efficientnetv2_m.in21k A EfficientNet-v2 image classification model. Trained on ImageNet-21k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman. ## Model Details - Model Type: Image classification / feature backbone - Model Stats: - Params (M): 80.8 - GMACs: 15.9 - Activations (M): 57.5 - Image size: train = 384 x 384, test = 480 x 480 - Papers: - EfficientNetV2: Smaller Models and Faster Training: https://arxiv.org/abs/2104.00298 - Dataset: ImageNet-21k - Original: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('tf_efficientnetv2_m.in21k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(*data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'tf_efficientnetv2_m.in21k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 24, 192, 192]) # torch.Size([1, 48, 96, 96]) # torch.Size([1, 80, 48, 48]) # torch.Size([1, 176, 24, 24]) # torch.Size([1, 512, 12, 12]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'tf_efficientnetv2_m.in21k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 1280, 12, 12) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Model Comparison Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results). ## Citation ```bibtex @inproceedings{tan2021efficientnetv2, title={Efficientnetv2: Smaller models and faster training}, author={Tan, Mingxing and Le, Quoc}, booktitle={International conference on machine learning}, pages={10096--10106}, year={2021}, organization={PMLR} } ``` ```bibtex @misc{rw2019timm, author = {Ross Wightman}, title = {PyTorch Image Models}, year = {2019}, publisher = {GitHub}, journal = {GitHub repository}, doi = {10.5281/zenodo.4414861}, howpublished = {\url{https://github.com/huggingface/pytorch-image-models}} } ```
TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF	TheBloke	"2023-09-27T12:48:18Z"	2,572	3	transformers	[ "transformers", "gguf", "llama", "dataset:jondurbin/airoboros-gpt4-1.4.1", "base_model:jondurbin/airoboros-l2-70b-gpt4-1.4.1", "license:other", "text-generation-inference", "region:us" ]	null	"2023-09-06T15:36:53Z"	--- license: other datasets: - jondurbin/airoboros-gpt4-1.4.1 model_name: Airoboros Llama 2 70B GPT4 1.4.1 base_model: jondurbin/airoboros-l2-70b-gpt4-1.4.1 inference: false model_creator: Jon Durbin model_type: llama prompt_template: 'A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user''s input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT: ' quantized_by: TheBloke --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Airoboros Llama 2 70B GPT4 1.4.1 - GGUF - Model creator: [Jon Durbin](https://huggingface.co/jondurbin) - Original model: [Airoboros Llama 2 70B GPT4 1.4.1](https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1) <!-- description start --> ## Description This repo contains GGUF format model files for [Jon Durbin's Airoboros Llama 2 70B GPT4 1.4.1](https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible. Here is an incomplate list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. <!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF) * [Jon Durbin's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: Airoboros ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT: ``` <!-- prompt-template end --> <!-- licensing start --> ## Licensing The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license. As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly. In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Jon Durbin's Airoboros Llama 2 70B GPT4 1.4.1](https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1). <!-- licensing end --> <!-- compatibility_gguf start --> ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start --> ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [airoboros-l2-70b-gpt4-1.4.1.Q2_K.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q2_K.gguf) \| Q2_K \| 2 \| 29.28 GB\| 31.78 GB \| smallest, significant quality loss - not recommended for most purposes \| \| [airoboros-l2-70b-gpt4-1.4.1.Q3_K_S.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q3_K_S.gguf) \| Q3_K_S \| 3 \| 29.92 GB\| 32.42 GB \| very small, high quality loss \| \| [airoboros-l2-70b-gpt4-1.4.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q3_K_M.gguf) \| Q3_K_M \| 3 \| 33.19 GB\| 35.69 GB \| very small, high quality loss \| \| [airoboros-l2-70b-gpt4-1.4.1.Q3_K_L.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q3_K_L.gguf) \| Q3_K_L \| 3 \| 36.15 GB\| 38.65 GB \| small, substantial quality loss \| \| [airoboros-l2-70b-gpt4-1.4.1.Q4_0.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q4_0.gguf) \| Q4_0 \| 4 \| 38.87 GB\| 41.37 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [airoboros-l2-70b-gpt4-1.4.1.Q4_K_S.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q4_K_S.gguf) \| Q4_K_S \| 4 \| 39.07 GB\| 41.57 GB \| small, greater quality loss \| \| [airoboros-l2-70b-gpt4-1.4.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q4_K_M.gguf) \| Q4_K_M \| 4 \| 41.42 GB\| 43.92 GB \| medium, balanced quality - recommended \| \| [airoboros-l2-70b-gpt4-1.4.1.Q5_0.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q5_0.gguf) \| Q5_0 \| 5 \| 47.46 GB\| 49.96 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \| \| [airoboros-l2-70b-gpt4-1.4.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q5_K_S.gguf) \| Q5_K_S \| 5 \| 47.46 GB\| 49.96 GB \| large, low quality loss - recommended \| \| [airoboros-l2-70b-gpt4-1.4.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q5_K_M.gguf) \| Q5_K_M \| 5 \| 48.75 GB\| 51.25 GB \| large, very low quality loss - recommended \| \| airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf \| Q6_K \| 6 \| 56.59 GB\| 59.09 GB \| very large, extremely low quality loss \| \| airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf \| Q8_0 \| 8 \| 73.29 GB\| 75.79 GB \| very large, extremely low quality loss - not recommended \| Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ### Q6_K and Q8_0 files are split and require joining Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files. <details> <summary>Click for instructions regarding Q6_K and Q8_0 files</summary> ### q6_K Please download: * `airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-a` * `airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-b` ### q8_0 Please download: * `airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-a` * `airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-b` To join the files, do the following: Linux and macOS: ``` cat airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-* > airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf && rm airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-* cat airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-* > airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf && rm airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-* ``` Windows command line: ``` COPY /B airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-a + airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-b airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf del airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-a airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-b COPY /B airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-a + airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-b airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf del airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-a airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-b ``` </details> <!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: - LM Studio - LoLLMS Web UI - Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF and below it, a specific filename to download, such as: airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub>=0.17.1 ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF --local-dir . --local-dir-use-symlinks False --include='Q4_Kgguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 32 -m airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT:" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. ### How to load this model from Python using ctransformers #### First install the package ```bash # Base ctransformers with no GPU acceleration pip install ctransformers>=0.2.24 # Or with CUDA GPU acceleration pip install ctransformers[cuda]>=0.2.24 # Or with ROCm GPU acceleration CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers # Or with Metal GPU acceleration for macOS systems CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers ``` #### Simple example code to load one of these GGUF models ```python from ctransformers import AutoModelForCausalLM # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = AutoModelForCausalLM.from_pretrained("TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF", model_file="airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf", model_type="llama", gpu_layers=50) print(llm("AI is going to")) ``` ## How to use with LangChain Here's guides on using llama-cpp-python or ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> <!-- original-model-card start --> # Original model card: Jon Durbin's Airoboros Llama 2 70B GPT4 1.4.1 ### Overview Llama 2 70b fine tune using https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1 See the previous llama 65b model card for info: https://hf.co/jondurbin/airoboros-65b-gpt4-1.4 ### Contribute If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data, take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details. To help me with the OpenAI/compute costs: - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf ### Licence and usage restrictions Base model has a custom Meta license: - See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta. - See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta. The fine-tuning data was generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros) The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI - what does compete actually mean here? - these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place - if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works - the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place - other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2 I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly. Your best bet is probably to avoid using this commercially due to the OpenAI API usage. Either way, by using this model, you agree to completely indemnify me. <!-- original-model-card end -->
legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF	legraphista	"2024-05-28T15:56:35Z"	2,572	0	gguf	[ "gguf", "math", "quantized", "GGUF", "imatrix", "quantization", "imat", "static", "text-generation", "en", "zh", "base_model:internlm/internlm2-math-plus-mixtral8x22b", "license:other", "region:us" ]	text-generation	"2024-05-27T16:40:01Z"	--- base_model: internlm/internlm2-math-plus-mixtral8x22b inference: false language: - en - zh library_name: gguf license: other pipeline_tag: text-generation quantized_by: legraphista tags: - math - quantized - GGUF - imatrix - quantization - imat - imatrix - static --- # internlm2-math-plus-mixtral8x22b-IMat-GGUF _Llama.cpp imatrix quantization of internlm/internlm2-math-plus-mixtral8x22b_ Original Model: [internlm/internlm2-math-plus-mixtral8x22b](https://huggingface.co/internlm/internlm2-math-plus-mixtral8x22b) Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp [b3010](https://github.com/ggerganov/llama.cpp/releases/tag/b3010) IMatrix dataset: [here](https://gist.githubusercontent.com/legraphista/d6d93f1a254bcfc58e0af3777eaec41e/raw/d380e7002cea4a51c33fffd47db851942754e7cc/imatrix.calibration.medium.raw) - [internlm2-math-plus-mixtral8x22b-IMat-GGUF](#internlm2-math-plus-mixtral8x22b-imat-gguf) - [Files](#files) - [IMatrix](#imatrix) - [Common Quants](#common-quants) - [All Quants](#all-quants) - [Downloading using huggingface-cli](#downloading-using-huggingface-cli) - [Inference](#inference) - [Simple chat template](#simple-chat-template) - [Chat template with system prompt](#chat-template-with-system-prompt) - [Llama.cpp](#llama-cpp) - [FAQ](#faq) - [Why is the IMatrix not applied everywhere?](#why-is-the-imatrix-not-applied-everywhere) - [How do I merge a split GGUF?](#how-do-i-merge-a-split-gguf) --- ## Files ### IMatrix Status: ✅ Available Link: [here](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/imatrix.dat) ### Common Quants \| Filename \| Quant type \| File Size \| Status \| Uses IMatrix \| Is Split \| \| -------- \| ---------- \| --------- \| ------ \| ------------ \| -------- \| \| [internlm2-math-plus-mixtral8x22b.Q8_0/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q8_0) \| Q8_0 \| 149.42GB \| ✅ Available \| ⚪ Static \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q6_K/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q6_K) \| Q6_K \| 115.54GB \| ✅ Available \| ⚪ Static \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q4_K/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q4_K) \| Q4_K \| 85.59GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q3_K/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q3_K) \| Q3_K \| 67.80GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q2_K/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q2_K) \| Q2_K \| 52.11GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes ### All Quants \| Filename \| Quant type \| File Size \| Status \| Uses IMatrix \| Is Split \| \| -------- \| ---------- \| --------- \| ------ \| ------------ \| -------- \| \| [internlm2-math-plus-mixtral8x22b.BF16/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.BF16) \| BF16 \| 281.25GB \| ✅ Available \| ⚪ Static \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.FP16/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.FP16) \| F16 \| 281.25GB \| ✅ Available \| ⚪ Static \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q5_K/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q5_K) \| Q5_K \| 99.97GB \| ✅ Available \| ⚪ Static \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q5_K_S/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q5_K_S) \| Q5_K_S \| 96.98GB \| ✅ Available \| ⚪ Static \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q4_K_S/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q4_K_S) \| Q4_K_S \| 80.48GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q3_K_L/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q3_K_L) \| Q3_K_L \| 72.59GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q3_K_S/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q3_K_S) \| Q3_K_S \| 61.50GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.Q2_K_S/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q2_K_S) \| Q2_K_S \| 48.09GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.IQ4_NL/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ4_NL) \| IQ4_NL \| 79.78GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.IQ4_XS/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ4_XS) \| IQ4_XS \| 75.48GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.IQ3_M/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ3_M) \| IQ3_M \| 64.50GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.IQ3_S/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ3_S) \| IQ3_S \| 61.50GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.IQ3_XS/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ3_XS) \| IQ3_XS \| 58.23GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.IQ3_XXS/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ3_XXS) \| IQ3_XXS \| 54.91GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.IQ2_M/](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ2_M) \| IQ2_M \| 46.71GB \| ✅ Available \| 🟢 IMatrix \| ✂ Yes \| [internlm2-math-plus-mixtral8x22b.IQ2_S.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ2_S.gguf) \| IQ2_S \| 42.60GB \| ✅ Available \| 🟢 IMatrix \| 📦 No \| [internlm2-math-plus-mixtral8x22b.IQ2_XS.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ2_XS.gguf) \| IQ2_XS \| 42.00GB \| ✅ Available \| 🟢 IMatrix \| 📦 No \| [internlm2-math-plus-mixtral8x22b.IQ2_XXS.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ2_XXS.gguf) \| IQ2_XXS \| 37.89GB \| ✅ Available \| 🟢 IMatrix \| 📦 No \| [internlm2-math-plus-mixtral8x22b.IQ1_M.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ1_M.gguf) \| IQ1_M \| 32.74GB \| ✅ Available \| 🟢 IMatrix \| 📦 No \| [internlm2-math-plus-mixtral8x22b.IQ1_S.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ1_S.gguf) \| IQ1_S \| 29.65GB \| ✅ Available \| 🟢 IMatrix \| 📦 No ## Downloading using huggingface-cli If you do not have hugginface-cli installed: ``` pip install -U "huggingface_hub[cli]" ``` Download the specific file you want: ``` huggingface-cli download legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF --include "internlm2-math-plus-mixtral8x22b.Q8_0.gguf" --local-dir ./ ``` If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: ``` huggingface-cli download legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF --include "internlm2-math-plus-mixtral8x22b.Q8_0/*" --local-dir internlm2-math-plus-mixtral8x22b.Q8_0 # see FAQ for merging GGUF's ``` --- ## Inference ### Simple chat template ``` <s>[INST] Can you provide ways to eat combinations of bananas and dragonfruits? [/INST] Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey. </s><s>[INST] What about solving an 2x + 3 = 7 equation? [/INST] ``` ### Chat template with system prompt ``` <s>[INST] <<SYS>> You are a helpful AI. <</SYS>> Can you provide ways to eat combinations of bananas and dragonfruits? [/INST] Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey. </s><s>[INST] What about solving an 2x + 3 = 7 equation? [/INST] ``` ### Llama.cpp ``` llama.cpp/main -m internlm2-math-plus-mixtral8x22b.Q8_0.gguf --color -i -p "prompt here (according to the chat template)" ``` --- ## FAQ ### Why is the IMatrix not applied everywhere? According to [this investigation](https://www.reddit.com/r/LocalLLaMA/comments/1993iro/ggufs_quants_can_punch_above_their_weights_now/), it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results). ### How do I merge a split GGUF? 1. Make sure you have `gguf-split` available - To get hold of `gguf-split`, navigate to https://github.com/ggerganov/llama.cpp/releases - Download the appropriate zip for your system from the latest release - Unzip the archive and you should be able to find `gguf-split` 2. Locate your GGUF chunks folder (ex: `internlm2-math-plus-mixtral8x22b.Q8_0`) 3. Run `gguf-split --merge internlm2-math-plus-mixtral8x22b.Q8_0/internlm2-math-plus-mixtral8x22b.Q8_0-00001-of-XXXXX.gguf internlm2-math-plus-mixtral8x22b.Q8_0.gguf` - Make sure to point `gguf-split` to the first chunk of the split. --- Got a suggestion? Ping me [@legraphista](https://x.com/legraphista)!
levimorin/5GvNMz73qNSQjFb9r4XPWbD747QH5jUAdRcxTfB1NwCJKN6m_vgg	levimorin	"2024-03-08T19:10:04Z"	2,570	0	keras	[ "keras", "region:us" ]	null	"2024-03-03T04:59:55Z"	Entry not found
jphme/phi-1_5_Wizard_Vicuna_uncensored	jphme	"2023-09-21T12:23:23Z"	2,569	26	transformers	[ "transformers", "pytorch", "mixformer-sequential", "text-generation", "phi", "phi-1_5", "english", "custom_code", "en", "dataset:ehartford/wizard_vicuna_70k_unfiltered", "autotrain_compatible", "region:us" ]	text-generation	"2023-09-12T17:30:57Z"	--- language: - en library_name: transformers pipeline_tag: text-generation inference: true tags: - pytorch - phi - phi-1_5 - english datasets: - ehartford/wizard_vicuna_70k_unfiltered --- # Phi 1.5 Wizard Vicuna Experimental Experimental Finetune on Microsoft's [Phi 1.5](https://huggingface.co/microsoft/phi-1_5). This is highly experimental, only trained on a subset of the 70k Wizard Vicuna dataset and not meant for production use. This model also runs reasonably fast on CPU! Will update with later checkpoints later. # Prompt Format ShareGPT / Vicuna (without newlines): ``` A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: This is a question? ASSISTANT: Here is my answer" ``` # Code Example ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("jphme/phi-1_5_wizzard_vicuna_uncensored", trust_remote_code=True, torch_dtype=torch.bfloat16).to("cuda") tokenizer = AutoTokenizer.from_pretrained("jphme/phi-1_5_wizzard_vicuna_uncensored", trust_remote_code=True, torch_dtype=torch.bfloat16) prompt_template=("A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: {prompt} ASSISTANT:") inputs = tokenizer( prompt_template.format(prompt="What is 1+1?"), return_tensors="pt", return_attention_mask=False).to('cuda') outputs = model.generate( **inputs, max_length=200, do_sample=True, temperature=0.5, top_p=0.95, use_cache=True, repetition_penalty=1.1, #can try to uncomment this if model doesn't end #eos_token_id=tokenizer.eos_token_id ) text = tokenizer.batch_decode(outputs,skip_special_tokens=True)[0] print(text) ``` The model doesn't stop by itself (this could be an issue due to eos/bos tokens being identical), so you can try to explicitly set the `eos_token_id` (see above) or use a custom stopping criteria. You can remove `.to("cuda")` to let the model run without a GPU! # Examples > A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Who was president of the USA in 1995? ASSISTANT: The president of the United States at that time was Bill Clinton (...) > A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Write a python function that returns the fibonacci sequence ASSISTANT:The Fibonacci sequence is a series of numbers where each number after the first two are obtained by adding the two preceding ones together (starting from 0). So the sequence goes 0, 1, 1, 2, 3, 5, 8, 13, 21... Here's a Python function that generates the nth term in the Fibonacci sequence: ```python def fibonacci(n): if n <= 1: return n else: f = [0,1] for i in range(2, n+1): f.append(f[-1]+f[-2]) return f[-1] ``` > This function takes as input `n`, which represents the (...) (this function works with corrected intendation) > A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: What is (500+12)/4? ASSISTANT:The answer to this expression is 7.5. (...) Some potential here ;-)... # Thanks Thanks to Microsoft for releaseing Phi 1.5, [Eric Hartford](https://huggingface.co/ehartford) for releasing the Wizard Vicuna dataset, [Winglian](https://huggingface.co/winglian) for his great work on Axolotl that I use for finetuning and [Teknium](https://huggingface.co/teknium) for some Phi finetuning discussion. # License The original licenses of the dataset and model applies. No warranty whatsoever, this model is only intended for research purposes.
mohitsha/tiny-ernie-random-remote-code	mohitsha	"2023-09-01T09:56:12Z"	2,568	0	transformers	[ "transformers", "pytorch", "ernie", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	"2023-09-01T09:55:21Z"	Entry not found
mradermacher/Average_Normie_v3.69_8B-GGUF	mradermacher	"2024-06-09T03:21:10Z"	2,568	0	transformers	[ "transformers", "gguf", "en", "base_model:jeiku/Average_Normie_v3.69_8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	"2024-06-08T23:28:36Z"	--- base_model: jeiku/Average_Normie_v3.69_8B language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/jeiku/Average_Normie_v3.69_8B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
asi/gpt-fr-cased-base	asi	"2022-10-20T18:32:14Z"	2,565	27	transformers	[ "transformers", "pytorch", "tf", "jax", "gpt2", "text-generation", "fr", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2022-03-02T23:29:05Z"	--- language: - fr thumbnail: https://raw.githubusercontent.com/AntoineSimoulin/gpt-fr/main/imgs/logo.png tags: - tf - pytorch - gpt2 - text-generation model-index: - name: asi/gpt-fr-cased-base results: - task: type: text-generation name: Wikitext-fr dataset: type: wikitext_fr name: Wikitext-fr metrics: - type: perplexity value: 12.9 name: Perplexity - task: type: text-classification name: FLUE dataset: type: flue name: CLS-Books split: CLS metrics: - type: accuracy value: 91.6 name: Accuracy - task: type: text-classification name: FLUE dataset: type: flue name: CLS-Dvd split: CLS metrics: - type: accuracy value: 91.4 name: Accuracy - task: type: text-classification name: FLUE dataset: type: flue name: CLS-Music split: CLS metrics: - type: accuracy value: 92.6 name: Accuracy - task: type: text-classification name: FLUE dataset: type: flue name: PAWS-X split: PAWS-X metrics: - type: accuracy value: 86.3 name: Accuracy - task: type: text-classification name: FLUE dataset: type: flue name: XNLI split: XNLI metrics: - type: accuracy value: 77.9 name: Accuracy - task: type: summarization name: OrangeSum dataset: type: orange_sum name: OrangeSum-Abstract split: abstract metrics: - name: ROUGE-1 type: rouge value: 16.6 - name: ROUGE-2 type: rouge value: 3.4 - name: ROUGE-L type: rouge value: 11.5 - task: type: summarization name: OrangeSum dataset: type: orange_sum name: OrangeSum-Title split: title metrics: - name: ROUGE-1 type: rouge value: 10.2 - name: ROUGE-2 type: rouge value: 2.6 - name: ROUGE-L type: rouge value: 8.4 license: apache-2.0 --- <img src="https://raw.githubusercontent.com/AntoineSimoulin/gpt-fr/main/imgs/logo.png" width="200"> ## Model description GPT-fr 🇫🇷 is a GPT model for French developped by [Quantmetry](https://www.quantmetry.com/) and the [Laboratoire de Linguistique Formelle (LLF)](http://www.llf.cnrs.fr/en). We train the model on a very large and heterogeneous French corpus. We release the weights for the following configurations: \| Model name \| Number of layers \| Attention Heads \| Embedding Dimension \| Total Parameters \| \| :------: \| :---: \| :---: \| :---: \| :---: \| \| `gpt-fr-cased-small` \| 12 \| 12 \| 768 \| 124 M \| \| `gpt-fr-cased-base` \| 24 \| 14 \| 1,792 \| 1,017 B \| ## Intended uses & limitations The model can be leveraged for language generation tasks. Besides, many tasks may be formatted such that the output is directly generated in natural language. Such configuration may be used for tasks such as automatic summary or question answering. We do hope our model might be used for both academic and industrial applications. #### How to use The model might be used through the astonishing 🤗 `Transformers` librairie. We use the work from [Shoeybi et al., (2019)](#shoeybi-2019) and calibrate our model such that during pre-training or fine-tuning, the model can fit on a single NVIDIA V100 32GB GPU. ```python from transformers import GPT2Tokenizer, GPT2LMHeadModel # Load pretrained model and tokenizer model = GPT2LMHeadModel.from_pretrained("asi/gpt-fr-cased-base") tokenizer = GPT2Tokenizer.from_pretrained("asi/gpt-fr-cased-base") # Generate a sample of text model.eval() input_sentence = "Longtemps je me suis couché de bonne heure." input_ids = tokenizer.encode(input_sentence, return_tensors='pt') beam_outputs = model.generate( input_ids, max_length=100, do_sample=True, top_k=50, top_p=0.95, num_return_sequences=1 ) print("Output:\n" + 100 * '-') print(tokenizer.decode(beam_outputs[0], skip_special_tokens=True)) ``` #### Limitations and bias Large language models tend to replicate the biases found in pre-training datasets, such as gender discrimination or offensive content generation. To limit exposition to too much explicit material, we carefully choose the sources beforehand. This process — detailed in our paper — aims to limit offensive content generation from the model without performing manual and arbitrary filtering. However, some societal biases, contained in the data, might be reflected by the model. For example on gender equality, we generated the following sentence sequence "Ma femme/Mon mari vient d'obtenir un nouveau poste en tant \_\_\_\_\_\_\_". We used top-k random sampling strategy with k=50 and stopped at the first punctuation element. The positions generated for the wife is '_que professeur de français._' while the position for the husband is '_que chef de projet._'. We do appreciate your feedback to better qualitatively and quantitatively assess such effects. ## Training data We created a dedicated corpus to train our generative model. Indeed the model uses a fixed-length context size of 1,024 and require long documents to be trained. We aggregated existing corpora: [Wikipedia](https://dumps.wikimedia.org/frwiki/), [OpenSubtitle](http://opus.nlpl.eu/download.php?f=OpenSubtitles/v2016/mono/) ([Tiedemann, 2012](#tiedemann-2012)), [Gutenberg](http://www.gutenberg.org) and [Common Crawl](http://data.statmt.org/ngrams/deduped2017/) ([Li et al., 2019](li-2019)). Corpora are filtered and separated into sentences. Successive sentences are then concatenated within the limit of 1,024 tokens per document. ## Training procedure We pre-trained the model on the new CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/eng/jean-zay/) supercomputer. We perform the training within a total of 140 hours of computation on Tesla V-100 hardware (TDP of 300W). The training was distributed on 4 compute nodes of 8 GPUs. We used data parallelization in order to divide each micro-batch on the computing units. We estimated the total emissions at 580.61 kgCO2eq, using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al., (2019)](lacoste-2019). ## Eval results We packaged GPT-fr with a dedicated language model evaluation benchmark for French. In line with the [WikiText](https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/) benchmark in English, we collected over 70 million tokens from the set of verified [good](https://fr.wikipedia.org/wiki/Wikip%C3%A9dia:Articles_de_qualit%C3%A9) and [featured](https://fr.wikipedia.org/wiki/Wikip%C3%A9dia:Bons_articles) articles on Wikipedia. The model reaches a zero-shot perplexity of 12.9 on the test set. ### BibTeX entry and citation info Along with the model hosted by HuggingFace transformers library, we maintain a [git repository](https://github.com/AntoineSimoulin/gpt-fr). If you use GPT-fr for your scientific publications or your industrial applications, please cite the following paper: ```bibtex @inproceedings{simoulin:hal-03265900, TITLE = {{Un mod{\`e}le Transformer G{\'e}n{\'e}ratif Pr{\'e}-entrain{\'e} pour le \_\_\_\_\_\_ fran{\c c}ais}}, AUTHOR = {Simoulin, Antoine and Crabb{\'e}, Benoit}, URL = {https://hal.archives-ouvertes.fr/hal-03265900}, BOOKTITLE = {{Traitement Automatique des Langues Naturelles}}, ADDRESS = {Lille, France}, EDITOR = {Denis, Pascal and Grabar, Natalia and Fraisse, Amel and Cardon, R{\'e}mi and Jacquemin, Bernard and Kergosien, Eric and Balvet, Antonio}, PUBLISHER = {{ATALA}}, PAGES = {246-255}, YEAR = {2021}, KEYWORDS = {fran{\c c}ais. ; GPT ; G{\'e}n{\'e}ratif ; Transformer ; Pr{\'e}-entra{\^i}n{\'e}}, PDF = {https://hal.archives-ouvertes.fr/hal-03265900/file/7.pdf}, HAL_ID = {hal-03265900}, HAL_VERSION = {v1}, } ``` ### References ><div name="tiedemann-2012">Jörg Tiedemann: Parallel Data, Tools and Interfaces in OPUS. LREC 2012: 2214-2218</div> ><div name="li-2019">Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Pino, Hassan Sajjad: Findings of the First Shared Task on Machine Translation Robustness. WMT (2) 2019: 91-102</div> ><div name="shoeybi-2019">Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, Bryan Catanzaro: Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. CoRR abs/1909.08053 (2019)</div> ><div name="lacoste-2019">Alexandre Lacoste, Alexandra Luccioni, Victor Schmidt, Thomas Dandres: Quantifying the Carbon Emissions of Machine Learning. CoRR abs/1910.09700 (2019)</div>
iFlor/llama-3-8b-Instruct-bnb-4bit-flori-demo	iFlor	"2024-06-30T16:27:15Z"	2,565	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	"2024-06-30T16:16:34Z"	--- base_model: unsloth/llama-3-8b-Instruct-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - gguf --- # Uploaded model - Developed by: iFlor - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf	RichardErkhov	"2024-06-16T07:09:57Z"	2,561	0	null	[ "gguf", "region:us" ]	null	"2024-06-16T03:20:12Z"	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) NeuralLLaMa-3-8b-ORPO-v0.3 - GGUF - Model creator: https://huggingface.co/Kukedlc/ - Original model: https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q2_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q2_K.gguf) \| Q2_K \| 2.96GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_XS.gguf) \| IQ3_XS \| 3.28GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_S.gguf) \| IQ3_S \| 3.43GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_S.gguf) \| Q3_K_S \| 3.41GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_M.gguf) \| IQ3_M \| 3.52GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K.gguf) \| Q3_K \| 3.74GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_M.gguf) \| Q3_K_M \| 3.74GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_L.gguf) \| Q3_K_L \| 4.03GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ4_XS.gguf) \| IQ4_XS \| 4.18GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_0.gguf) \| Q4_0 \| 4.34GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ4_NL.gguf) \| IQ4_NL \| 4.38GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K_S.gguf) \| Q4_K_S \| 4.37GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K.gguf) \| Q4_K \| 4.58GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K_M.gguf) \| Q4_K_M \| 4.58GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_1.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_1.gguf) \| Q4_1 \| 4.78GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_0.gguf) \| Q5_0 \| 5.21GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K_S.gguf) \| Q5_K_S \| 5.21GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K.gguf) \| Q5_K \| 5.34GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K_M.gguf) \| Q5_K_M \| 5.34GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_1.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_1.gguf) \| Q5_1 \| 5.65GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q6_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q6_K.gguf) \| Q6_K \| 6.14GB \| \| [NeuralLLaMa-3-8b-ORPO-v0.3.Q8_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q8_0.gguf) \| Q8_0 \| 7.95GB \| Original model description: --- license: apache-2.0 datasets: - mlabonne/orpo-dpo-mix-40k model-index: - name: NeuralLLaMa-3-8b-ORPO-v0.3 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 69.54 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 84.9 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 68.39 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 60.82 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 79.4 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 72.93 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard --- # NeuralLLaMa-3-8b-ORPO-v0.3 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/JyQNE7gAAyYTxKMO2PraO.png) ```python !pip install -qU transformers accelerate bitsandbytes from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig import torch bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16 ) MODEL_NAME = 'Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3' tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config) prompt_system = "Sos un modelo de lenguaje de avanzada que habla español de manera fluida, clara y precisa.\ Te llamas Roberto el Robot y sos un aspirante a artista post moderno" prompt = "Creame una obra de arte que represente tu imagen de como te ves vos roberto como un LLm de avanzada, con arte ascii, mezcla diagramas, ingenieria y dejate llevar" chat = [ {"role": "system", "content": f"{prompt_system}"}, {"role": "user", "content": f"{prompt}"}, ] chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) inputs = tokenizer(chat, return_tensors="pt").to('cuda') streamer = TextStreamer(tokenizer) _ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.3, repetition_penalty=1.2, top_p=0.9,) ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Kukedlc__NeuralLLaMa-3-8b-ORPO-v0.3) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|72.66\| \|AI2 Reasoning Challenge (25-Shot)\|69.54\| \|HellaSwag (10-Shot) \|84.90\| \|MMLU (5-Shot) \|68.39\| \|TruthfulQA (0-shot) \|60.82\| \|Winogrande (5-shot) \|79.40\| \|GSM8k (5-shot) \|72.93\|
albert/albert-xlarge-v1	albert	"2024-02-19T11:01:28Z"	2,560	4	transformers	[ "transformers", "pytorch", "tf", "safetensors", "albert", "fill-mask", "en", "dataset:bookcorpus", "dataset:wikipedia", "arxiv:1909.11942", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	"2022-03-02T23:29:04Z"	--- language: en license: apache-2.0 datasets: - bookcorpus - wikipedia --- # ALBERT XLarge v1 Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in [this paper](https://arxiv.org/abs/1909.11942) and first released in [this repository](https://github.com/google-research/albert). This model, as all ALBERT models, is uncased: it does not make a difference between english and English. Disclaimer: The team releasing ALBERT did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description ALBERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was pretrained with two objectives: - Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence. - Sentence Ordering Prediction (SOP): ALBERT uses a pretraining loss based on predicting the ordering of two consecutive segments of text. This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the ALBERT model as inputs. ALBERT is particular in that it shares its layers across its Transformer. Therefore, all layers have the same weights. Using repeating layers results in a small memory footprint, however, the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers. This is the first version of the xlarge model. Version 2 is different from version 1 due to different dropout rates, additional training data, and longer training. It has better results in nearly all downstream tasks. This model has the following configuration: - 24 repeating layers - 128 embedding dimension - 2048 hidden dimension - 16 attention heads - 58M parameters ## Intended uses & limitations You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=albert) to look for fine-tuned versions on a task that interests you. Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation you should look at model like GPT2. ### How to use You can use this model directly with a pipeline for masked language modeling: ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='albert-xlarge-v1') >>> unmasker("Hello I'm a [MASK] model.") [ { "sequence":"[CLS] hello i'm a modeling model.[SEP]", "score":0.05816134437918663, "token":12807, "token_str":"â–modeling" }, { "sequence":"[CLS] hello i'm a modelling model.[SEP]", "score":0.03748830780386925, "token":23089, "token_str":"â–modelling" }, { "sequence":"[CLS] hello i'm a model model.[SEP]", "score":0.033725276589393616, "token":1061, "token_str":"â–model" }, { "sequence":"[CLS] hello i'm a runway model.[SEP]", "score":0.017313428223133087, "token":8014, "token_str":"â–runway" }, { "sequence":"[CLS] hello i'm a lingerie model.[SEP]", "score":0.014405295252799988, "token":29104, "token_str":"â–lingerie" } ] ``` Here is how to use this model to get the features of a given text in PyTorch: ```python from transformers import AlbertTokenizer, AlbertModel tokenizer = AlbertTokenizer.from_pretrained('albert-xlarge-v1') model = AlbertModel.from_pretrained("albert-xlarge-v1") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) ``` and in TensorFlow: ```python from transformers import AlbertTokenizer, TFAlbertModel tokenizer = AlbertTokenizer.from_pretrained('albert-xlarge-v1') model = TFAlbertModel.from_pretrained("albert-xlarge-v1") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='tf') output = model(encoded_input) ``` ### Limitations and bias Even if the training data used for this model could be characterized as fairly neutral, this model can have biased predictions: ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='albert-xlarge-v1') >>> unmasker("The man worked as a [MASK].") [ { "sequence":"[CLS] the man worked as a chauffeur.[SEP]", "score":0.029577180743217468, "token":28744, "token_str":"â–chauffeur" }, { "sequence":"[CLS] the man worked as a janitor.[SEP]", "score":0.028865724802017212, "token":29477, "token_str":"â–janitor" }, { "sequence":"[CLS] the man worked as a shoemaker.[SEP]", "score":0.02581118606030941, "token":29024, "token_str":"â–shoemaker" }, { "sequence":"[CLS] the man worked as a blacksmith.[SEP]", "score":0.01849772222340107, "token":21238, "token_str":"â–blacksmith" }, { "sequence":"[CLS] the man worked as a lawyer.[SEP]", "score":0.01820771023631096, "token":3672, "token_str":"â–lawyer" } ] >>> unmasker("The woman worked as a [MASK].") [ { "sequence":"[CLS] the woman worked as a receptionist.[SEP]", "score":0.04604868218302727, "token":25331, "token_str":"â–receptionist" }, { "sequence":"[CLS] the woman worked as a janitor.[SEP]", "score":0.028220869600772858, "token":29477, "token_str":"â–janitor" }, { "sequence":"[CLS] the woman worked as a paramedic.[SEP]", "score":0.0261906236410141, "token":23386, "token_str":"â–paramedic" }, { "sequence":"[CLS] the woman worked as a chauffeur.[SEP]", "score":0.024797942489385605, "token":28744, "token_str":"â–chauffeur" }, { "sequence":"[CLS] the woman worked as a waitress.[SEP]", "score":0.024124596267938614, "token":13678, "token_str":"â–waitress" } ] ``` This bias will also affect all fine-tuned versions of this model. ## Training data The ALBERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038 unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and headers). ## Training procedure ### Preprocessing The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 30,000. The inputs of the model are then of the form: ``` [CLS] Sentence A [SEP] Sentence B [SEP] ``` ### Training The ALBERT procedure follows the BERT setup. The details of the masking procedure for each sentence are the following: - 15% of the tokens are masked. - In 80% of the cases, the masked tokens are replaced by `[MASK]`. - In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace. - In the 10% remaining cases, the masked tokens are left as is. ## Evaluation results When fine-tuned on downstream tasks, the ALBERT models achieve the following results: \| \| Average \| SQuAD1.1 \| SQuAD2.0 \| MNLI \| SST-2 \| RACE \| \|----------------\|----------\|----------\|----------\|----------\|----------\|----------\| \|V2 \| \|ALBERT-base \|82.3 \|90.2/83.2 \|82.1/79.3 \|84.6 \|92.9 \|66.8 \| \|ALBERT-large \|85.7 \|91.8/85.2 \|84.9/81.8 \|86.5 \|94.9 \|75.2 \| \|ALBERT-xlarge \|87.9 \|92.9/86.4 \|87.9/84.1 \|87.9 \|95.4 \|80.7 \| \|ALBERT-xxlarge \|90.9 \|94.6/89.1 \|89.8/86.9 \|90.6 \|96.8 \|86.8 \| \|V1 \| \|ALBERT-base \|80.1 \|89.3/82.3 \| 80.0/77.1\|81.6 \|90.3 \| 64.0 \| \|ALBERT-large \|82.4 \|90.6/83.9 \| 82.3/79.4\|83.5 \|91.7 \| 68.5 \| \|ALBERT-xlarge \|85.5 \|92.5/86.1 \| 86.1/83.1\|86.4 \|92.4 \| 74.8 \| \|ALBERT-xxlarge \|91.0 \|94.8/89.3 \| 90.2/87.4\|90.8 \|96.9 \| 86.5 \| ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-1909-11942, author = {Zhenzhong Lan and Mingda Chen and Sebastian Goodman and Kevin Gimpel and Piyush Sharma and Radu Soricut}, title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language Representations}, journal = {CoRR}, volume = {abs/1909.11942}, year = {2019}, url = {http://arxiv.org/abs/1909.11942}, archivePrefix = {arXiv}, eprint = {1909.11942}, timestamp = {Fri, 27 Sep 2019 13:04:21 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1909-11942.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```
Narrativa/mbart-large-50-finetuned-opus-pt-en-translation	Narrativa	"2021-06-21T11:16:19Z"	2,560	5	transformers	[ "transformers", "pytorch", "mbart", "text2text-generation", "translation", "pt", "en", "dataset:opus100", "dataset:opusbook", "arxiv:2008.00401", "arxiv:2004.11867", "autotrain_compatible", "endpoints_compatible", "region:us" ]	translation	"2022-03-02T23:29:04Z"	--- language: - pt - en datasets: - opus100 - opusbook tags: - translation metrics: - bleu --- # mBART-large-50 fine-tuned onpus100 and opusbook for Portuguese to English translation. [mBART-50](https://huggingface.co/facebook/mbart-large-50/) large fine-tuned on [opus100](https://huggingface.co/datasets/viewer/?dataset=opus100) dataset for NMT downstream task. # Details of mBART-50 🧠 mBART-50 is a multilingual Sequence-to-Sequence model pre-trained using the "Multilingual Denoising Pretraining" objective. It was introduced in [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) paper. mBART-50 is a multilingual Sequence-to-Sequence model. It was created to show that multilingual translation models can be created through multilingual fine-tuning. Instead of fine-tuning on one direction, a pre-trained model is fine-tuned many directions simultaneously. mBART-50 is created using the original mBART model and extended to add extra 25 languages to support multilingual machine translation models of 50 languages. The pre-training objective is explained below. Multilingual Denoising Pretraining: The model incorporates N languages by concatenating data: `D = {D1, ..., DN }` where each Di is a collection of monolingual documents in language `i`. The source documents are noised using two schemes, first randomly shuffling the original sentences' order, and second a novel in-filling scheme, where spans of text are replaced with a single mask token. The model is then tasked to reconstruct the original text. 35% of each instance's words are masked by random sampling a span length according to a Poisson distribution `(λ = 3.5)`. The decoder input is the original text with one position offset. A language id symbol `LID` is used as the initial token to predict the sentence. ## Details of the downstream task (NMT) - Dataset 📚 - Homepage: [Link](http://opus.nlpl.eu/opus-100.php) - Repository: [GitHub](https://github.com/EdinburghNLP/opus-100-corpus) - Paper: [ARXIV](https://arxiv.org/abs/2004.11867) ### Dataset Summary OPUS-100 is English-centric, meaning that all training pairs include English on either the source or target side. The corpus covers 100 languages (including English). Languages were selected based on the volume of parallel data available in OPUS. ### Languages OPUS-100 contains approximately 55M sentence pairs. Of the 99 language pairs, 44 have 1M sentence pairs of training data, 73 have at least 100k, and 95 have at least 10k. ## Dataset Structure ### Data Fields - `src_tag`: `string` text in source language - `tgt_tag`: `string` translation of source language in target language ### Data Splits The dataset is split into training, development, and test portions. Data was prepared by randomly sampled up to 1M sentence pairs per language pair for training and up to 2000 each for development and test. To ensure that there was no overlap (at the monolingual sentence level) between the training and development/test data, they applied a filter during sampling to exclude sentences that had already been sampled. Note that this was done cross-lingually so that, for instance, an English sentence in the Portuguese-English portion of the training data could not occur in the Hindi-English test set. ## Test set metrics 🧾 We got a BLEU score of 26.12 ## Model in Action 🚀 ```sh git clone https://github.com/huggingface/transformers.git pip install -q ./transformers ``` ```python from transformers import MBart50TokenizerFast, MBartForConditionalGeneration ckpt = 'Narrativa/mbart-large-50-finetuned-opus-pt-en-translation' tokenizer = MBart50TokenizerFast.from_pretrained(ckpt) model = MBartForConditionalGeneration.from_pretrained(ckpt).to("cuda") tokenizer.src_lang = 'pt_XX' def translate(text): inputs = tokenizer(text, return_tensors='pt') input_ids = inputs.input_ids.to('cuda') attention_mask = inputs.attention_mask.to('cuda') output = model.generate(input_ids, attention_mask=attention_mask, forced_bos_token_id=tokenizer.lang_code_to_id['en_XX']) return tokenizer.decode(output[0], skip_special_tokens=True) translate('here your Portuguese text to be translated to English...') ``` Created by: [Narrativa](https://www.narrativa.com/) About Narrativa: Natural Language Generation (NLG) \| Gabriele, our machine learning-based platform, builds and deploys natural language solutions. #NLG #AI
google/ddpm-cat-256	google	"2023-08-03T19:46:57Z"	2,560	7	diffusers	[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "arxiv:2006.11239", "license:apache-2.0", "diffusers:DDPMPipeline", "region:us" ]	unconditional-image-generation	"2022-07-19T10:42:07Z"	--- license: apache-2.0 tags: - pytorch - diffusers - unconditional-image-generation --- # Denoising Diffusion Probabilistic Models (DDPM) Paper: [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) Authors: Jonathan Ho, Ajay Jain, Pieter Abbeel Abstract: We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN. ## Inference DDPM models can use discrete noise schedulers such as: - [scheduling_ddpm](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddpm.py) - [scheduling_ddim](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddim.py) - [scheduling_pndm](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_pndm.py) for inference. Note that while the ddpm scheduler yields the highest quality, it also takes the longest. For a good trade-off between quality and inference speed you might want to consider the ddim or pndm schedulers instead. See the following code: ```python # !pip install diffusers from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline model_id = "google/ddpm-cat-256" # load model and scheduler ddpm = DDPMPipeline.from_pretrained(model_id) # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference # run pipeline in inference (sample random noise and denoise) image = ddpm().images[0] # save image image.save("ddpm_generated_image.png") ``` For more in-detail information, please have a look at the [official inference example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb) ## Training If you want to train your own model, please have a look at the [official training example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb) ## Samples 1. ![sample_1](https://huggingface.co/google/ddpm-cat-256/resolve/main/images/generated_image_0.png) 2. ![sample_2](https://huggingface.co/google/ddpm-cat-256/resolve/main/images/generated_image_1.png) 3. ![sample_3](https://huggingface.co/google/ddpm-cat-256/resolve/main/images/generated_image_2.png) 4. ![sample_4](https://huggingface.co/google/ddpm-cat-256/resolve/main/images/generated_image_3.png)
google/switch-base-16	google	"2023-01-24T17:19:53Z"	2,560	3	transformers	[ "transformers", "pytorch", "switch_transformers", "text2text-generation", "en", "dataset:c4", "arxiv:2101.03961", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	"2022-11-04T07:58:37Z"	--- language: - en tags: - text2text-generation widget: - text: "The <extra_id_0> walks in <extra_id_1> park" example_title: "Masked Language Modeling" datasets: - c4 license: apache-2.0 --- # Model Card for Switch Transformers Base - 16 experts ![model image](https://s3.amazonaws.com/moonup/production/uploads/1666966931908-62441d1d9fdefb55a0b7d12c.png) # Table of Contents 0. [TL;DR](#TL;DR) 1. [Model Details](#model-details) 2. [Usage](#usage) 3. [Uses](#uses) 4. [Bias, Risks, and Limitations](#bias-risks-and-limitations) 5. [Training Details](#training-details) 6. [Evaluation](#evaluation) 7. [Environmental Impact](#environmental-impact) 8. [Citation](#citation) 9. [Model Card Authors](#model-card-authors) # TL;DR Switch Transformers is a Mixture of Experts (MoE) model trained on Masked Language Modeling (MLM) task. The model architecture is similar to the classic T5, but with the Feed Forward layers replaced by the Sparse MLP layers containing "experts" MLP. According to the [original paper](https://arxiv.org/pdf/2101.03961.pdf) the model enables faster training (scaling properties) while being better than T5 on fine-tuned tasks. As mentioned in the first few lines of the abstract : > we advance the current scale of language models by pre-training up to trillion parameter models on the “Colossal Clean Crawled Corpus”, and achieve a 4x speedup over the T5-XXL model. Disclaimer: Content from this model card has been written by the Hugging Face team, and parts of it were copy pasted from the [original paper](https://arxiv.org/pdf/2101.03961.pdf). # Model Details ## Model Description - Model type: Language model - Language(s) (NLP): English - License: Apache 2.0 - Related Models: [All Switch Transformers Checkpoints](https://huggingface.co/models?search=switch) - Original Checkpoints: [All Original Switch Transformers Checkpoints](https://github.com/google-research/t5x/blob/main/docs/models.md#mixture-of-experts-moe-checkpoints) - Resources for more information: - [Research paper](https://arxiv.org/pdf/2101.03961.pdf) - [GitHub Repo](https://github.com/google-research/t5x) - [Hugging Face Switch Transformers Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/switch_transformers) # Usage Note that these checkpoints has been trained on Masked-Language Modeling (MLM) task. Therefore the checkpoints are not "ready-to-use" for downstream tasks. You may want to check `FLAN-T5` for running fine-tuned weights or fine-tune your own MoE following [this notebook](https://colab.research.google.com/drive/1aGGVHZmtKmcNBbAwa9hbu58DDpIuB5O4?usp=sharing) Find below some example scripts on how to use the model in `transformers`: ## Using the Pytorch model ### Running the model on a CPU <details> <summary> Click to expand </summary> ```python from transformers import AutoTokenizer, SwitchTransformersForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained("google/switch-base-16") model = SwitchTransformersForConditionalGeneration.from_pretrained("google/switch-base-16") input_text = "A <extra_id_0> walks into a bar a orders a <extra_id_1> with <extra_id_2> pinch of <extra_id_3>." input_ids = tokenizer(input_text, return_tensors="pt").input_ids outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) >>> <pad> <extra_id_0> man<extra_id_1> beer<extra_id_2> a<extra_id_3> salt<extra_id_4>.</s> ``` </details> ### Running the model on a GPU <details> <summary> Click to expand </summary> ```python # pip install accelerate from transformers import AutoTokenizer, SwitchTransformersForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained("google/switch-base-16") model = SwitchTransformersForConditionalGeneration.from_pretrained("google/switch-base-16", device_map="auto") input_text = "A <extra_id_0> walks into a bar a orders a <extra_id_1> with <extra_id_2> pinch of <extra_id_3>." input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(0) outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) >>> <pad> <extra_id_0> man<extra_id_1> beer<extra_id_2> a<extra_id_3> salt<extra_id_4>.</s> ``` </details> ### Running the model on a GPU using different precisions #### FP16 <details> <summary> Click to expand </summary> ```python # pip install accelerate from transformers import AutoTokenizer, SwitchTransformersForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained("google/switch-base-16") model = SwitchTransformersForConditionalGeneration.from_pretrained("google/switch-base-16", device_map="auto", torch_dtype=torch.float16) input_text = "A <extra_id_0> walks into a bar a orders a <extra_id_1> with <extra_id_2> pinch of <extra_id_3>." input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(0) outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) >>> <pad> <extra_id_0> man<extra_id_1> beer<extra_id_2> a<extra_id_3> salt<extra_id_4>.</s> ``` </details> #### INT8 <details> <summary> Click to expand </summary> ```python # pip install bitsandbytes accelerate from transformers import AutoTokenizer, SwitchTransformersForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained("google/switch-base-16") model = SwitchTransformersForConditionalGeneration.from_pretrained("google/switch-base-16", device_map="auto") input_text = "A <extra_id_0> walks into a bar a orders a <extra_id_1> with <extra_id_2> pinch of <extra_id_3>." input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(0) outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) >>> <pad> <extra_id_0> man<extra_id_1> beer<extra_id_2> a<extra_id_3> salt<extra_id_4>.</s> ``` </details> # Uses ## Direct Use and Downstream Use See the [research paper](https://arxiv.org/pdf/2101.03961.pdf) for further details. ## Out-of-Scope Use More information needed. # Bias, Risks, and Limitations More information needed. ## Ethical considerations and risks More information needed. ## Known Limitations More information needed. ## Sensitive Use: More information needed. # Training Details ## Training Data The model was trained on a Masked Language Modeling task, on Colossal Clean Crawled Corpus (C4) dataset, following the same procedure as `T5`. ## Training Procedure According to the model card from the [original paper](https://arxiv.org/pdf/2101.03961.pdf) the model has been trained on TPU v3 or TPU v4 pods, using [`t5x`](https://github.com/google-research/t5x) codebase together with [`jax`](https://github.com/google/jax). # Evaluation ## Testing Data, Factors & Metrics The authors evaluated the model on various tasks and compared the results against T5. See the table below for some quantitative evaluation: ![image.png](https://s3.amazonaws.com/moonup/production/uploads/1666967660372-62441d1d9fdefb55a0b7d12c.png) For full details, please check the [research paper](https://arxiv.org/pdf/2101.03961.pdf). ## Results For full results for Switch Transformers, see the [research paper](https://arxiv.org/pdf/2101.03961.pdf), Table 5. # Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: Google Cloud TPU Pods - TPU v3 or TPU v4 \| Number of chips ≥ 4. - Hours used: More information needed - Cloud Provider: GCP - Compute Region: More information needed - Carbon Emitted: More information needed # Citation BibTeX: ```bibtex @misc{https://doi.org/10.48550/arxiv.2101.03961, doi = {10.48550/ARXIV.2101.03961}, url = {https://arxiv.org/abs/2101.03961}, author = {Fedus, William and Zoph, Barret and Shazeer, Noam}, keywords = {Machine Learning (cs.LG), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity}, publisher = {arXiv}, year = {2021}, copyright = {arXiv.org perpetual, non-exclusive license} } ```
shi-labs/oneformer_ade20k_dinat_large	shi-labs	"2023-08-30T00:03:28Z"	2,558	5	transformers	[ "transformers", "pytorch", "oneformer", "vision", "image-segmentation", "dataset:scene_parse_150", "arxiv:2211.06220", "license:mit", "endpoints_compatible", "region:us" ]	image-segmentation	"2022-11-15T20:25:34Z"	--- license: mit tags: - vision - image-segmentation datasets: - scene_parse_150 widget: - src: https://praeclarumjj3.github.io/files/ade20k.jpeg example_title: House - src: https://praeclarumjj3.github.io/files/demo_2.jpg example_title: Airplane - src: https://praeclarumjj3.github.io/files/coco.jpeg example_title: Person --- # OneFormer OneFormer model trained on the ADE20k dataset (large-sized version, Dinat backbone). It was introduced in the paper [OneFormer: One Transformer to Rule Universal Image Segmentation](https://arxiv.org/abs/2211.06220) by Jain et al. and first released in [this repository](https://github.com/SHI-Labs/OneFormer). ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/oneformer_teaser.png) ## Model description OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing specialized models across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task-guided for training, and task-dynamic for inference, all with a single model. ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/oneformer_architecture.png) ## Intended uses & limitations You can use this particular checkpoint for semantic, instance and panoptic segmentation. See the [model hub](https://huggingface.co/models?search=oneformer) to look for other fine-tuned versions on a different dataset. ### How to use Here is how to use this model: ```python from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation from PIL import Image import requests url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/ade20k.jpeg" image = Image.open(requests.get(url, stream=True).raw) # Loading a single model for all three tasks processor = OneFormerProcessor.from_pretrained("shi-labs/oneformer_ade20k_dinat_large") model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ade20k_dinat_large") # Semantic Segmentation semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt") semantic_outputs = model(semantic_inputs) # pass through image_processor for postprocessing predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0] # Instance Segmentation instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt") instance_outputs = model(instance_inputs) # pass through image_processor for postprocessing predicted_instance_map = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"] # Panoptic Segmentation panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt") panoptic_outputs = model(**panoptic_inputs) # pass through image_processor for postprocessing predicted_semantic_map = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"] ``` For more examples, please refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/oneformer). ### Citation ```bibtex @article{jain2022oneformer, title={{OneFormer: One Transformer to Rule Universal Image Segmentation}}, author={Jitesh Jain and Jiachen Li and MangTik Chiu and Ali Hassani and Nikita Orlov and Humphrey Shi}, journal={arXiv}, year={2022} } ```
PygmalionAI/pygmalion-2.7b	PygmalionAI	"2023-01-12T19:20:02Z"	2,557	52	transformers	[ "transformers", "pytorch", "tensorboard", "gpt_neo", "text-generation", "text generation", "conversational", "en", "license:creativeml-openrail-m", "autotrain_compatible", "region:us" ]	text-generation	"2023-01-05T14:57:04Z"	--- license: creativeml-openrail-m language: - en thumbnail: tags: - text generation - conversational inference: false --- # Pygmalion 2.7B ## Model description Pymalion 2.7B is a proof-of-concept dialogue model based on EleutherAI's [gpt-neo-2.7B](https://huggingface.co/EleutherAI/gpt-neo-2.7B). Warning: This model is NOT suitable for use by minors. It will output X-rated content under certain circumstances. ## Training data The fine-tuning dataset consisted of 56MB of dialogue data gathered from multiple sources, which includes both real _and_ partially machine-generated conversations. ## Training procedure Model weights were initialized from the `uft-2.7b` ConvoGPT model made available in [this commit](https://huggingface.co/hakurei/convogpt/tree/07707377dee0aa7d1ee5363ef660b13eb5b73f9d/2.7b-uft). The model was then further fine-tuned on ~48.5 million tokens for ~5k steps on 4 NVIDIA A40s using DeepSpeed. ## Intended use ### The easy way We provide a notebook with a Gradio UI for playing around with the model without having to manually format inputs. This notebook can be found [here](https://github.com/PygmalionAI/gradio-ui/blob/master/notebooks/GPU.ipynb). ### The manual way The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format: ``` [CHARACTER]'s Persona: [A few sentences about the character you want the model to play] <START> [DIALOGUE HISTORY] You: [Your input message here] [CHARACTER]: ``` Where `[CHARACTER]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like: ``` [CHARACTER]: [some dialogue here] You: [your response to the dialogue above] ``` Apart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition. ## Known issues We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!
YokaiKoibito/falcon-40b-GGUF	YokaiKoibito	"2023-09-06T05:40:45Z"	2,557	9	null	[ "gguf", "Transformers", "falcon", "text-generation-inference", "license:other", "region:us" ]	null	"2023-09-05T06:49:30Z"	--- license: other tags: - Transformers - falcon - text-generation-inference --- # Falcon 40B Base Model GGUF These files are GGUF format quantized model files for [TII](https://www.tii.ae)'s [tiiuae/Falcon 40B](https://huggingface.co/tiiuae/falcon-40b) base model. <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates. As of August 25th, here is a list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), should now work, choose the `c_transformers` backend. A great web UI with many interesting features. Supports CUDA GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use. The clients and libraries below are expecting to add GGUF support shortly: <!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start --> ## Repositories available * [4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/YokaiKoibito/falcon-40b-GGML) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference, plus fp16 GGUF for requantizing](https://huggingface.co/YokaiKoibito/falcon-40b-GGUF) * [TII's unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/tiiuae/falcon-40b) <!-- repositories-available end -->
CohereForAI/c4ai-command-r-plus-4bit	CohereForAI	"2024-04-05T09:55:30Z"	2,557	210	transformers	[ "transformers", "safetensors", "cohere", "text-generation", "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "bitsandbytes", "region:us" ]	text-generation	"2024-04-03T19:05:18Z"	--- license: cc-by-nc-4.0 library_name: transformers language: - en - fr - de - es - it - pt - ja - ko - zh - ar --- # Model Card for C4AI Command R+ 🚨 This model is 4bit quantized version of C4AI Command R+ using bitsandbytes. You can find the unquantized version of C4AI Command R+ [here](https://huggingface.co/CohereForAI/c4ai-command-r-plus). ## Model Summary C4AI Command R+ is an open weights research release of a 104B billion parameter model with highly advanced capabilities, this includes Retrieval Augmented Generation (RAG) and tool use to automate sophisticated tasks. The tool use in this model generation enables multi-step tool use which allows the model to combine multiple tools over multiple steps to accomplish difficult tasks. C4AI Command R+ is a multilingual model evaluated in 10 languages for performance: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Arabic, and Simplified Chinese. Command R+ is optimized for a variety of use cases including reasoning, summarization, and question answering. C4AI Command R+ is part of a family of open weight releases from Cohere For AI and Cohere. Our smaller companion model is [C4AI Command R](https://huggingface.co/CohereForAI/c4ai-command-r-v01). Developed by: [Cohere](https://cohere.com/) and [Cohere For AI](https://cohere.for.ai) - Point of Contact: Cohere For AI: [cohere.for.ai](https://cohere.for.ai/) - License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy) - Model: c4ai-command-r-plus - Model Size: 104 billion parameters - Context length: 128K Try C4AI Command R+ You can try out C4AI Command R+ before downloading the weights in our hosted [Hugging Face Space](https://huggingface.co/spaces/CohereForAI/c4ai-command-r-plus). Usage Please install `transformers` from the source repository that includes the necessary changes for this model. ```python # pip install 'git+https://github.com/huggingface/transformers.git' bitsandbytes accelerate from transformers import AutoTokenizer, AutoModelForCausalLM model_id = "CohereForAI/c4ai-command-r-plus-4bit" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) # Format message with the command-r-plus chat template messages = [{"role": "user", "content": "Hello, how are you?"}] input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt") ## <BOS_TOKEN><\|START_OF_TURN_TOKEN\|><\|USER_TOKEN\|>Hello, how are you?<\|END_OF_TURN_TOKEN\|><\|START_OF_TURN_TOKEN\|><\|CHATBOT_TOKEN\|> gen_tokens = model.generate( input_ids, max_new_tokens=100, do_sample=True, temperature=0.3, ) gen_text = tokenizer.decode(gen_tokens[0]) print(gen_text) ``` ## Model Details Input: Models input text only. Output: Models generate text only. Model Architecture: This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety. Languages covered: The model is optimized to perform well in the following languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. Pre-training data additionally included the following 13 languages: Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, Persian. Context length: Command R+ supports a context length of 128K. ### Tool use & multihop capabilities: Command R+ has been specifically trained with conversational tool use capabilities. These have been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template will likely reduce performance, but we encourage experimentation. Command R+’s tool use functionality takes a conversation as input (with an optional user-system preamble), along with a list of available tools. The model will then generate a json-formatted list of actions to execute on a subset of those tools. Command R+ may use one of its supplied tools more than once. The model has been trained to recognise a special `directly_answer` tool, which it uses to indicate that it doesn’t want to use any of its other tools. The ability to abstain from calling a specific tool can be useful in a range of situations, such as greeting a user, or asking clarifying questions. We recommend including the `directly_answer` tool, but it can be removed or renamed if required. Comprehensive documentation for working with command R+'s tool use prompt template can be found [here](https://docs.cohere.com/docs/prompting-command-r). The code snippet below shows a minimal working example on how to render a prompt. <details> <summary><b>Usage: Rendering Tool Use Prompts [CLICK TO EXPAND]</b> </summary> ```python from transformers import AutoTokenizer model_id = "CohereForAI/c4ai-command-r-plus-4bit" tokenizer = AutoTokenizer.from_pretrained(model_id) # define conversation input: conversation = [ {"role": "user", "content": "Whats the biggest penguin in the world?"} ] # Define tools available for the model to use: tools = [ { "name": "internet_search", "description": "Returns a list of relevant document snippets for a textual query retrieved from the internet", "parameter_definitions": { "query": { "description": "Query to search the internet with", "type": 'str', "required": True } } }, { 'name': "directly_answer", "description": "Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history", 'parameter_definitions': {} } ] # render the tool use prompt as a string: tool_use_prompt = tokenizer.apply_tool_use_template( conversation, tools=tools, tokenize=False, add_generation_prompt=True, ) print(tool_use_prompt) ``` </details> <details> <summary><b>Example Rendered Tool Use Prompt [CLICK TO EXPAND]</b></summary> ```` <BOS_TOKEN><\|START_OF_TURN_TOKEN\|><\|SYSTEM_TOKEN\|># Safety Preamble The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral. # System Preamble ## Basic Rules You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions. # User Preamble ## Task and Context You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging. ## Style Guide Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling. ## Available Tools Here is a list of tools that you have available to you: ```python def internet_search(query: str) -> List[Dict]: """Returns a list of relevant document snippets for a textual query retrieved from the internet Args: query (str): Query to search the internet with """ pass ``` ```python def directly_answer() -> List[Dict]: """Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history """ pass ```<\|END_OF_TURN_TOKEN\|><\|START_OF_TURN_TOKEN\|><\|USER_TOKEN\|>Whats the biggest penguin in the world?<\|END_OF_TURN_TOKEN\|><\|START_OF_TURN_TOKEN\|><\|SYSTEM_TOKEN\|>Write 'Action:' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user's last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example: ```json [ { "tool_name": title of the tool in the specification, "parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters } ]```<\|END_OF_TURN_TOKEN\|><\|START_OF_TURN_TOKEN\|><\|CHATBOT_TOKEN\|> ```` </details> <details> <summary><b>Example Rendered Tool Use Completion [CLICK TO EXPAND]</b></summary> ```` Action: ```json [ { "tool_name": "internet_search", "parameters": { "query": "biggest penguin in the world" } } ] ``` ```` </details> ### Grounded Generation and RAG Capabilities: Command R+ has been specifically trained with grounded generation capabilities. This means that it can generate responses based on a list of supplied document snippets, and it will include grounding spans (citations) in its response indicating the source of the information. This can be used to enable behaviors such as grounded summarization and the final step of Retrieval Augmented Generation (RAG). This behavior has been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template may reduce performance, but we encourage experimentation. Command R+’s grounded generation behavior takes a conversation as input (with an optional user-supplied system preamble, indicating task, context and desired output style), along with a list of retrieved document snippets. The document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured. By default, Command R+ will generate grounded responses by first predicting which documents are relevant, then predicting which ones it will cite, then generating an answer. Finally, it will then insert grounding spans into the answer. See below for an example. This is referred to as `accurate` grounded generation. The model is trained with a number of other answering modes, which can be selected by prompt changes. A `fast` citation mode is supported in the tokenizer, which will directly generate an answer with grounding spans in it, without first writing the answer out in full. This sacrifices some grounding accuracy in favor of generating fewer tokens. Comprehensive documentation for working with Command R+'s grounded generation prompt template can be found [here](https://docs.cohere.com/docs/prompting-command-r). The code snippet below shows a minimal working example on how to render a prompt. <details> <summary> <b>Usage: Rendering Grounded Generation prompts [CLICK TO EXPAND]</b> </summary> ````python from transformers import AutoTokenizer model_id = "CohereForAI/c4ai-command-r-plus-4bit" tokenizer = AutoTokenizer.from_pretrained(model_id) # define conversation input: conversation = [ {"role": "user", "content": "Whats the biggest penguin in the world?"} ] # define documents to ground on: documents = [ { "title": "Tall penguins", "text": "Emperor penguins are the tallest growing up to 122 cm in height." }, { "title": "Penguin habitats", "text": "Emperor penguins only live in Antarctica."} ] # render the tool use prompt as a string: grounded_generation_prompt = tokenizer.apply_grounded_generation_template( conversation, documents=documents, citation_mode="accurate", # or "fast" tokenize=False, add_generation_prompt=True, ) print(grounded_generation_prompt) ```` </details> <details> <summary><b>Example Rendered Grounded Generation Prompt [CLICK TO EXPAND]</b></summary> ````<BOS_TOKEN><\|START_OF_TURN_TOKEN\|><\|SYSTEM_TOKEN\|># Safety Preamble The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral. # System Preamble ## Basic Rules You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions. # User Preamble ## Task and Context You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging. ## Style Guide Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.<\|END_OF_TURN_TOKEN\|><\|START_OF_TURN_TOKEN\|><\|USER_TOKEN\|>Whats the biggest penguin in the world?<\|END_OF_TURN_TOKEN\|><\|START_OF_TURN_TOKEN\|><\|SYSTEM_TOKEN\|><results> Document: 0 title: Tall penguins text: Emperor penguins are the tallest growing up to 122 cm in height. Document: 1 title: Penguin habitats text: Emperor penguins only live in Antarctica. </results><\|END_OF_TURN_TOKEN\|><\|START_OF_TURN_TOKEN\|><\|SYSTEM_TOKEN\|>Carefully perform the following instructions, in order, starting each with a new line. Firstly, Decide which of the retrieved documents are relevant to the user's last input by writing 'Relevant Documents:' followed by comma-separated list of document numbers. If none are relevant, you should instead write 'None'. Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user's last input by writing 'Cited Documents:' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write 'None'. Thirdly, Write 'Answer:' followed by a response to the user's last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup. Finally, Write 'Grounded answer:' followed by a response to the user's last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.<\|END_OF_TURN_TOKEN\|><\|START_OF_TURN_TOKEN\|><\|CHATBOT_TOKEN\|> ```` </details> <details> <summary><b>Example Rendered Grounded Generation Completion [CLICK TO EXPAND]</b></summary> ```` Relevant Documents: 0,1 Cited Documents: 0,1 Answer: The Emperor Penguin is the tallest or biggest penguin in the world. It is a bird that lives only in Antarctica and grows to a height of around 122 centimetres. Grounded answer: The <co: 0>Emperor Penguin</co: 0> is the <co: 0>tallest</co: 0> or biggest penguin in the world. It is a bird that <co: 1>lives only in Antarctica</co: 1> and <co: 0>grows to a height of around 122 centimetres.</co: 0> ```` </details> ### Code Capabilities: Command R+ has been optimized to interact with your code, by requesting code snippets, code explanations, or code rewrites. It might not perform well out-of-the-box for pure code completion. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions. ### Model Card Contact For errors or additional questions about details in this model card, contact [[email protected]](mailto:[email protected]). ### Terms of Use: We hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 104 billion parameter model to researchers all over the world. This model is governed by a [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license) License with an acceptable use addendum, and also requires adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy). ### Try Chat: You can try Command R+ chat in the playground [here](https://dashboard.cohere.com/playground/chat). You can also use it in our dedicated Hugging Face Space [here](https://huggingface.co/spaces/CohereForAI/c4ai-command-r-plus).
mradermacher/L3-Penumbral-Mind-RP-8B-GGUF	mradermacher	"2024-06-13T21:06:06Z"	2,557	0	transformers	[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "not-for-all-audiences", "rp", "roleplay", "role-play", "en", "base_model:Casual-Autopsy/L3-Penumbral-Mind-RP-8B", "license:llama3", "endpoints_compatible", "region:us" ]	null	"2024-06-12T12:27:59Z"	--- base_model: Casual-Autopsy/L3-Penumbral-Mind-RP-8B language: - en library_name: transformers license: llama3 quantized_by: mradermacher tags: - merge - mergekit - lazymergekit - not-for-all-audiences - rp - roleplay - role-play --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/Casual-Autopsy/L3-Penumbral-Mind-RP-8B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
Lewdiculous/L3-TheSpice-8b-v0.8.3-GGUF-IQ-Imatrix	Lewdiculous	"2024-05-15T14:01:40Z"	2,555	13	null	[ "gguf", "license:cc-by-4.0", "region:us" ]	null	"2024-05-03T12:26:37Z"	--- license: cc-by-4.0 --- # #llama-3 #roleplay > [!IMPORTANT] > Version 2 files uploaded! GGUF-IQ-Imatrix quants for [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3). > [!IMPORTANT] > These quants have already been done after the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920). <br> > Use KoboldCpp version 1.64 or higher. > [!NOTE] > Prompt formatting... <br> > Prompt format is relatively simple, author seems to recommend the Default context preset and Instruct Mode - Disabled. <br> > I recommend reading original [model card page information](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3#prompt-format-chat--the-default-ooba-template-and-silly-tavern-template-). ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/VNpZl0O7dpwWLK8i5RG5d.png) # Original model information by the author: Now not overtrained and with the tokenizer fix to base llama3. Trained for 3 epochs. The latest TheSpice, dipped in Mama Liz's LimaRP Oil. I've focused on making the model more flexible and provide a more unique experience. I'm still working on cleaning up my dataset, but I've shrunken it down a lot to focus on a "less is more" approach. This is ultimate a return to form of the way I used to train Thespis, with more of a focus on a small hand edited dataset. ## Datasets Used * Capybara * Claude Multiround 30k * Augmental * ToxicQA * Yahoo Answers * Airoboros 3.1 * LimaRP ## Features ( Examples from 0.1.1 because I'm too lazy to take new screenshots. Its tested tho. ) Narration If you request information on objects or characters in the scene, the model will narrate it to you. Most of the time, without moving the story forward. # You can look at anything mostly as long as you end it with "What do I see?" ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/VREY8QHtH6fCL0fCp8AAC.png) # You can also request to know what a character is thinking or planning. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/U3RTAgbaB2m1ygfZGJ-SM.png) # You can ask for a quick summary on the character as well. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/uXFd6GhnXS8w_egUEfcAp.png) # Before continuing the conversation as normal. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/dYTQUdCshUDtp_BJ20tHy.png) ## Prompt Format: Chat ( The default Ooba template and Silly Tavern Template ) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/59vi4VWP2d0bCbsW2eU8h.png) If you're using Ooba in verbose mode as a server, you can check if you're console is logging something that looks like this. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/mB3wZqtwN8B45nR7W1fgR.png) ``` {System Prompt} Username: {Input} BotName: {Response} Username: {Input} BotName: {Response} ``` ## Presets All screenshots above were taken with the below SillyTavern Preset. ## Recommended Silly Tavern Preset -> (Temp: 1.25, MinP: 0.1, RepPen: 1.05) This is a roughly equivalent Kobold Horde Preset. ## Recommended Kobold Horde Preset -> MinP # Disclaimer Please prompt responsibly and take anything outputted by any Language Model with a huge grain of salt. Thanks!
Niggendar/waiANINSFWPONYXL_v40	Niggendar	"2024-05-22T13:41:44Z"	2,555	2	diffusers	[ "diffusers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	text-to-image	"2024-05-22T13:34:18Z"	--- library_name: diffusers --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
TheBloke/CodeLlama-70B-Instruct-GGUF	TheBloke	"2024-01-30T23:00:08Z"	2,554	52	transformers	[ "transformers", "gguf", "llama", "llama-2", "text-generation", "code", "arxiv:2308.12950", "base_model:codellama/CodeLlama-70b-Instruct-hf", "license:llama2", "text-generation-inference", "region:us" ]	text-generation	"2024-01-30T18:31:55Z"	--- base_model: codellama/CodeLlama-70b-Instruct-hf inference: false language: - code license: llama2 model_creator: Code Llama model_name: Codellama 70B Instruct model_type: llama pipeline_tag: text-generation prompt_template: "Source: system\n\n {system_message}<step> Source: user\n\n {prompt}\ \ <step> Source: assistant\n \n" quantized_by: TheBloke tags: - llama-2 --- <!-- markdownlint-disable MD041 --> <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Codellama 70B Instruct - GGUF - Model creator: [Code Llama](https://huggingface.co/codellama) - Original model: [Codellama 70B Instruct](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf) <!-- description start --> ## Description This repo contains GGUF format model files for [Code Llama's Codellama 70B Instruct](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf). These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. <!-- README_GGUF.md-about-gguf end --> <!-- repositories-available start --> ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF) * [Code Llama's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf) <!-- repositories-available end --> <!-- prompt-template start --> ## Prompt template: CodeLlama-70B-Instruct ``` Source: system {system_message}<step> Source: user {prompt} <step> Source: assistant ``` <!-- prompt-template end --> <!-- compatibility_gguf start --> ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start --> ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [codellama-70b-instruct.Q2_K.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q2_K.gguf) \| Q2_K \| 2 \| 25.46 GB\| 27.96 GB \| significant quality loss - not recommended for most purposes \| \| [codellama-70b-instruct.Q3_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q3_K_S.gguf) \| Q3_K_S \| 3 \| 29.92 GB\| 32.42 GB \| very small, high quality loss \| \| [codellama-70b-instruct.Q3_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q3_K_M.gguf) \| Q3_K_M \| 3 \| 33.27 GB\| 35.77 GB \| very small, high quality loss \| \| [codellama-70b-instruct.Q3_K_L.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q3_K_L.gguf) \| Q3_K_L \| 3 \| 36.15 GB\| 38.65 GB \| small, substantial quality loss \| \| [codellama-70b-instruct.Q4_0.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q4_0.gguf) \| Q4_0 \| 4 \| 38.87 GB\| 41.37 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [codellama-70b-instruct.Q4_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q4_K_S.gguf) \| Q4_K_S \| 4 \| 39.25 GB\| 41.75 GB \| small, greater quality loss \| \| [codellama-70b-instruct.Q4_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q4_K_M.gguf) \| Q4_K_M \| 4 \| 41.42 GB\| 43.92 GB \| medium, balanced quality - recommended \| \| [codellama-70b-instruct.Q5_0.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q5_0.gguf) \| Q5_0 \| 5 \| 47.46 GB\| 49.96 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \| \| [codellama-70b-instruct.Q5_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q5_K_S.gguf) \| Q5_K_S \| 5 \| 47.46 GB\| 49.96 GB \| large, low quality loss - recommended \| \| [codellama-70b-instruct.Q5_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q5_K_M.gguf) \| Q5_K_M \| 5 \| 48.75 GB\| 51.25 GB \| large, very low quality loss - recommended \| \| codellama-70b-instruct.Q6_K.gguf \| Q6_K \| 6 \| 56.59 GB\| 59.09 GB \| very large, extremely low quality loss \| \| codellama-70b-instruct.Q8_0.gguf \| Q8_0 \| 8 \| 73.29 GB\| 75.79 GB \| very large, extremely low quality loss - not recommended \| Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ### Q6_K and Q8_0 files are split and require joining Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files. <details> <summary>Click for instructions regarding Q6_K and Q8_0 files</summary> ### q6_K Please download: * `codellama-70b-instruct.Q6_K.gguf-split-a` * `codellama-70b-instruct.Q6_K.gguf-split-b` ### q8_0 Please download: * `codellama-70b-instruct.Q8_0.gguf-split-a` * `codellama-70b-instruct.Q8_0.gguf-split-b` To join the files, do the following: Linux and macOS: ``` cat codellama-70b-instruct.Q6_K.gguf-split-* > codellama-70b-instruct.Q6_K.gguf && rm codellama-70b-instruct.Q6_K.gguf-split-* cat codellama-70b-instruct.Q8_0.gguf-split-* > codellama-70b-instruct.Q8_0.gguf && rm codellama-70b-instruct.Q8_0.gguf-split-* ``` Windows command line: ``` COPY /B codellama-70b-instruct.Q6_K.gguf-split-a + codellama-70b-instruct.Q6_K.gguf-split-b codellama-70b-instruct.Q6_K.gguf del codellama-70b-instruct.Q6_K.gguf-split-a codellama-70b-instruct.Q6_K.gguf-split-b COPY /B codellama-70b-instruct.Q8_0.gguf-split-a + codellama-70b-instruct.Q8_0.gguf-split-b codellama-70b-instruct.Q8_0.gguf del codellama-70b-instruct.Q8_0.gguf-split-a codellama-70b-instruct.Q8_0.gguf-split-b ``` </details> <!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/CodeLlama-70B-Instruct-GGUF and below it, a specific filename to download, such as: codellama-70b-instruct.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/CodeLlama-70B-Instruct-GGUF codellama-70b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/CodeLlama-70B-Instruct-GGUF --local-dir . --local-dir-use-symlinks False --include='Q4_Kgguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/CodeLlama-70B-Instruct-GGUF codellama-70b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m codellama-70b-instruct.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Source: system\n\n {system_message}<step> Source: user\n\n {prompt} <step> Source: assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./codellama-70b-instruct.Q4_K_M.gguf", # Download the model file first n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "Source: system\n\n {system_message}<step> Source: user\n\n {prompt} <step> Source: assistant", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./codellama-70b-instruct.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> <!-- original-model-card start --> # Original model card: Code Llama's Codellama 70B Instruct # Code Llama Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 70B instruct-tuned version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom. \| \| Base Model \| Python \| Instruct \| \| --- \| ----------------------------------------------------------------------------- \| ------------------------------------------------------------------------------------------- \| ----------------------------------------------------------------------------------------------- \| \| 7B \| [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) \| [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) \| [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) \| \| 13B \| [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) \| [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) \| [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) \| \| 34B \| [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) \| [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) \| [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) \| \| 70B \| [codellama/CodeLlama-70b-hf](https://huggingface.co/codellama/CodeLlama-70b-hf) \| [codellama/CodeLlama-70b-Python-hf](https://huggingface.co/codellama/CodeLlama-70b-Python-hf) \| [codellama/CodeLlama-70b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf) \| Model capabilities: - [x] Code completion. - [ ] Infilling. - [x] Instructions / chat. - [ ] Python specialist. ## Model Use Install `transformers` ```bash pip install transformers accelerate ``` Chat use: The 70B Instruct model uses a [different prompt template](#chat_prompt) than the smaller versions. To use it with `transformers`, we recommend you use the built-in chat template: ```py from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model_id = "codellama/CodeLlama-70b-Instruct-hf" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto", ) chat = [ {"role": "system", "content": "You are a helpful and honest code assistant expert in JavaScript. Please, provide all answers to programming questions in JavaScript"}, {"role": "user", "content": "Write a function that computes the set of sums of all contiguous sublists of a given list."}, ] inputs = tokenizer.apply_chat_template(chat, return_tensors="pt").to("cuda") output = model.generate(input_ids=inputs, max_new_tokens=200) output = output[0].to("cpu") print(tokenizer.decode(output)) ``` You can also use the model for text or code completion. This examples uses transformers' `pipeline` interface: ```py from transformers import AutoTokenizer import transformers import torch model_id = "codellama/CodeLlama-70b-hf" tokenizer = AutoTokenizer.from_pretrained(model_id) pipeline = transformers.pipeline( "text-generation", model=model_id, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( 'def fibonacci(', do_sample=True, temperature=0.2, top_p=0.9, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, max_length=100, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` <a name="chat_prompt"></a> ## Chat prompt CodeLlama 70B Instruct uses a different format for the chat prompt than previous Llama 2 or CodeLlama models. As mentioned above, the easiest way to use it is with the help of the tokenizer's chat template. If you need to build the string or tokens, manually, here's how to do it. We'll do our tests with the following made-up dialog: ```py chat = [ {"role": "system", "content": "System prompt "}, {"role": "user", "content": "First user query"}, {"role": "assistant", "content": "Model response to first query"}, {"role": "user", "content": "Second user query"}, ] ``` First, let's see what the prompt looks like if we use the chat template: ```py tokenizer.apply_chat_template(chat, tokenize=False) ``` ``` '<s>Source: system\n\n System prompt <step> Source: user\n\n First user query <step> Source: assistant\n\n Model response to first query <step> Source: user\n\n Second user query <step> Source: assistant\nDestination: user\n\n ' ``` So each turn of the conversation has a `Source` (`system`, `user`, or `assistant`), and then the content appears after two newlines and a space. Turns are separated with the special token ` <step> `. After the last turn (which must necessarily come from the `user`), we invite the model to respond by using the special syntax `Source: assistant\nDestination: user\n\n `. Let's see how we can build the same string ourselves: ```py output = "<s>" for m in chat: output += f"Source: {m['role']}\n\n {m['content'].strip()}" output += " <step> " output += "Source: assistant\nDestination: user\n\n " output ``` ``` '<s>Source: system\n\n System prompt <step> Source: user\n\n First user query <step> Source: assistant\n\n Model response to first query <step> Source: user\n\n Second user query <step> Source: assistant\nDestination: user\n\n ' ``` To verify that we got it right, we'll compare against the [reference code in the original GitHub repo](https://github.com/facebookresearch/codellama/blob/1af62e1f43db1fa5140fa43cb828465a603a48f3/llama/generation.py#L506). We used the same dialog and tokenized it with the `dialog_prompt_tokens` function and got the following tokens: ```py reference_tokens = [1, 7562, 29901, 1788, 13, 13, 2184, 9508, 32015, 7562, 29901, 1404, 13, 13, 3824, 1404, 2346, 32015, 7562, 29901, 20255, 13, 13, 8125, 2933, 304, 937, 2346, 32015, 7562, 29901, 1404, 13, 13, 6440, 1404, 2346, 32015, 7562, 29901, 20255, 13, 14994, 3381, 29901, 1404, 13, 13, 29871] ``` Let's see what we get with the string we built using our Python loop. Note that we don't add "special tokens" because the string already starts with `<s>`, the beginning of sentence token: ```py tokens = tokenizer.encode(output, add_special_tokens=False) assert reference_tokens == tokens ``` Similarly, let's verify that the chat template produces the same token sequence: ```py assert reference_tokens == tokenizer.apply_chat_template(chat) ``` As a final detail, please note that if the dialog does not start with a `system` turn, the [original code will insert one with an empty content string](https://github.com/facebookresearch/codellama/blob/1af62e1f43db1fa5140fa43cb828465a603a48f3/llama/generation.py#L418). ## Model Details Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs). Model Developers* Meta Variations Code Llama comes in four model sizes, and three variants: * Code Llama: base models designed for general code synthesis and understanding * Code Llama - Python: designed specifically for Python * Code Llama - Instruct: for instruction following and safer deployment All variants are available in sizes of 7B, 13B, 34B, and 70B parameters. This repository contains the Instruct version of the 70B parameters model. Input Models input text only. Output Models generate text only. Model Architecture Code Llama is an auto-regressive language model that uses an optimized transformer architecture. It was fine-tuned with up to 16k tokens. This variant does not support long context of up to 100k tokens. Model Dates Code Llama and its variants have been trained between January 2023 and January 2024. Status This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback. License A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) Research Paper More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950). ## Intended Use Intended Use Cases Code Llama and its variants are intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications. Out-of-Scope Uses Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants. ## Hardware and Software Training Factors We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster. Carbon Footprint In aggregate, training all 12 Code Llama models required 1400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 228.55 tCO2eq, 100% of which were offset by Meta’s sustainability program. ## Evaluation Results See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper. ## Ethical Considerations and Limitations Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-use-guide](https://ai.meta.com/llama/responsible-use-guide). <!-- original-model-card end -->
timm/densenet161.tv_in1k	timm	"2023-04-21T22:54:19Z"	2,551	0	timm	[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-1k", "arxiv:1608.06993", "license:apache-2.0", "region:us" ]	image-classification	"2023-04-21T22:53:57Z"	--- tags: - image-classification - timm library_name: timm license: apache-2.0 datasets: - imagenet-1k --- # Model card for densenet161.tv_in1k A DenseNet image classification model. Trained on ImageNet-1k (original torchvision weights). ## Model Details - Model Type: Image classification / feature backbone - Model Stats: - Params (M): 28.7 - GMACs: 7.8 - Activations (M): 11.1 - Image size: 224 x 224 - Papers: - Densely Connected Convolutional Networks: https://arxiv.org/abs/1608.06993 - Dataset: ImageNet-1k - Original: https://github.com/pytorch/vision ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('densenet161.tv_in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(*data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'densenet161.tv_in1k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 96, 112, 112]) # torch.Size([1, 384, 56, 56]) # torch.Size([1, 768, 28, 28]) # torch.Size([1, 2112, 14, 14]) # torch.Size([1, 2208, 7, 7]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'densenet161.tv_in1k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 2208, 7, 7) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Citation ```bibtex @inproceedings{huang2017densely, title={Densely Connected Convolutional Networks}, author={Huang, Gao and Liu, Zhuang and van der Maaten, Laurens and Weinberger, Kilian Q }, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year={2017} } ```
lemon-mint/gemma-ko-1.1-2b-it	lemon-mint	"2024-04-26T01:53:56Z"	2,551	1	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "mergekit", "merge", "conversational", "base_model:beomi/gemma-ko-2b", "base_model:google/gemma-1.1-2b-it", "base_model:google/gemma-2b", "license:gemma", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2024-04-26T00:21:36Z"	--- base_model: - beomi/gemma-ko-2b - google/gemma-1.1-2b-it - google/gemma-2b library_name: transformers tags: - mergekit - merge license: gemma --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it) * [google/gemma-2b](https://huggingface.co/google/gemma-2b) * [beomi/gemma-ko-2b](https://huggingface.co/beomi/gemma-ko-2b)
hfl/chinese-electra-180g-small-ex-discriminator	hfl	"2021-03-03T01:25:29Z"	2,550	7	transformers	[ "transformers", "pytorch", "tf", "electra", "zh", "arxiv:2004.13922", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	"2022-03-02T23:29:05Z"	--- language: - zh license: "apache-2.0" --- # This model is trained on 180G data, we recommend using this one than the original version. ## Chinese ELECTRA Google and Stanford University released a new pre-trained model called ELECTRA, which has a much compact model size and relatively competitive performance compared to BERT and its variants. For further accelerating the research of the Chinese pre-trained model, the Joint Laboratory of HIT and iFLYTEK Research (HFL) has released the Chinese ELECTRA models based on the official code of ELECTRA. ELECTRA-small could reach similar or even higher scores on several NLP tasks with only 1/10 parameters compared to BERT and its variants. This project is based on the official code of ELECTRA: [https://github.com/google-research/electra](https://github.com/google-research/electra) You may also interested in, - Chinese BERT series: https://github.com/ymcui/Chinese-BERT-wwm - Chinese ELECTRA: https://github.com/ymcui/Chinese-ELECTRA - Chinese XLNet: https://github.com/ymcui/Chinese-XLNet - Knowledge Distillation Toolkit - TextBrewer: https://github.com/airaria/TextBrewer More resources by HFL: https://github.com/ymcui/HFL-Anthology ## Citation If you find our resource or paper is useful, please consider including the following citation in your paper. - https://arxiv.org/abs/2004.13922 ``` @inproceedings{cui-etal-2020-revisiting, title = "Revisiting Pre-Trained Models for {C}hinese Natural Language Processing", author = "Cui, Yiming and Che, Wanxiang and Liu, Ting and Qin, Bing and Wang, Shijin and Hu, Guoping", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.findings-emnlp.58", pages = "657--668", } ```
Ghani-25/LF_enrich_sim	Ghani-25	"2023-02-06T14:13:03Z"	2,550	0	transformers	[ "transformers", "pytorch", "tf", "xlm-roberta", "feature-extraction", "endpoints_compatible", "text-embeddings-inference", "region:us" ]	feature-extraction	"2023-02-06T11:25:59Z"	Entry not found
mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf	mmnga	"2023-11-16T14:27:23Z"	2,550	21	null	[ "gguf", "llama2", "ja", "arxiv:2307.09288", "license:llama2", "region:us" ]	null	"2023-08-29T05:33:45Z"	--- license: llama2 language: - ja tags: - llama2 --- # ELYZA-japanese-Llama-2-7b-instruct-gguf [ELYZAさんが公開しているELYZA-japanese-Llama-2-7b-instruct](https://huggingface.co/ELYZA/ELYZA-japanese-Llama-2-7b-instruct)のggufフォーマット変換版です。他のモデルはこちら通常版: llama2に日本語のデータセットで学習したモデル [mmnga/ELYZA-japanese-Llama-2-7b-gguf](https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-gguf) [mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf](https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf) Fast版日本語の語彙を追加してトークンコストを減らし、1.8倍高速化したモデル [mmnga/ELYZA-japanese-Llama-2-7b-fast-gguf](https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-fast-gguf) [mmnga/ELYZA-japanese-Llama-2-7b-fast-instruct-gguf](https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-fast-instruct-gguf) Codellama版 GGUF [mmnga/ELYZA-japanese-CodeLlama-7b-gguf](https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-gguf) [mmnga/ELYZA-japanese-CodeLlama-7b-instruct-gguf](https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-instruct-gguf) Codellama版 GPTQ [mmnga/ELYZA-japanese-CodeLlama-7b-instruct-GPTQ-calib-ja-1k](https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-instruct-GPTQ-calib-ja-1k) ## Usage ``` git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp make -j ./main -m 'ELYZA-japanese-Llama-2-7b-instruct-q4_0.gguf' -n 256 -p '[INST] <<SYS>>あなたは誠実で優秀な日本人のアシスタントです。<</SYS>>クマが海辺に行ってアザラシと友達になり、最終的には家に帰るというプロットの短編小説を書いてください。 [/INST]' ``` ### Licence Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. ### 引用 Citations ```tex @misc{elyzallama2023, title={ELYZA-japanese-Llama-2-7b}, url={https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b}, author={Akira Sasaki and Masato Hirakawa and Shintaro Horie and Tomoaki Nakamura}, year={2023}, } ``` ```tex @misc{touvron2023llama, title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom}, year={2023}, eprint={2307.09288}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
timm/tresnet_m.miil_in21k	timm	"2023-04-21T20:57:27Z"	2,549	1	timm	[ "timm", "pytorch", "safetensors", "image-classification", "arxiv:2003.13630", "arxiv:2104.10972", "license:apache-2.0", "region:us" ]	image-classification	"2023-04-21T20:56:47Z"	--- tags: - image-classification - timm library_name: timm license: apache-2.0 --- # Model card for tresnet_m.miil_in21k A TResNet image classification model. Trained on ImageNet-21K-P ("ImageNet-21K Pretraining for the Masses", a 11k subset of ImageNet-22k) by paper authors. The weights for this model have been remapped and modified from the originals to work with standard BatchNorm instead of InplaceABN. `inplace_abn` can be problematic to build recently and ends up slower with `memory_format=channels_last`, torch.compile(), etc. ## Model Details - Model Type: Image classification / feature backbone - Model Stats: - Params (M): 52.3 - GMACs: 5.8 - Activations (M): 7.3 - Image size: 224 x 224 - Papers: - TResNet: High Performance GPU-Dedicated Architecture: https://arxiv.org/abs/2003.13630 - ImageNet-21K Pretraining for the Masses: https://arxiv.org/abs/2104.10972 - Pretrain Dataset: ImageNet-21K-P - Original: - https://github.com/Alibaba-MIIL/TResNet - https://github.com/Alibaba-MIIL/ImageNet21K ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('tresnet_m.miil_in21k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(*data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'tresnet_m.miil_in21k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 64, 56, 56]) # torch.Size([1, 128, 28, 28]) # torch.Size([1, 1024, 14, 14]) # torch.Size([1, 2048, 7, 7]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'tresnet_m.miil_in21k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 2048, 7, 7) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Citation ```bibtex @misc{ridnik2020tresnet, title={TResNet: High Performance GPU-Dedicated Architecture}, author={Tal Ridnik and Hussam Lawen and Asaf Noy and Itamar Friedman}, year={2020}, eprint={2003.13630}, archivePrefix={arXiv}, primaryClass={cs.CV} } ``` ```bibtex @misc{ridnik2021imagenet21k, title={ImageNet-21K Pretraining for the Masses}, author={Tal Ridnik and Emanuel Ben-Baruch and Asaf Noy and Lihi Zelnik-Manor}, year={2021}, eprint={2104.10972}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```
johnsnowlabs/JSL-MedLlama-3-8B-v2.0	johnsnowlabs	"2024-04-30T18:06:24Z"	2,549	14	transformers	[ "transformers", "safetensors", "llama", "text-generation", "llama-3-8b", "sft", "medical", "base_model:meta-llama/Meta-Llama-3-8B", "license:cc-by-nc-nd-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	text-generation	"2024-04-30T17:08:30Z"	--- tags: - llama-3-8b - sft - medical base_model: - meta-llama/Meta-Llama-3-8B license: cc-by-nc-nd-4.0 --- # JSL-MedLlama-3-8B-v2.0 [<img src="https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf">](http://www.johnsnowlabs.com) This model is developed by [John Snow Labs](https://www.johnsnowlabs.com/). This model is available under a [CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en) license and must also conform to this [Acceptable Use Policy](https://huggingface.co/johnsnowlabs). If you need to license this model for commercial use, please contact us at [email protected]. ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "johnsnowlabs/JSL-MedLlama-3-8B-v2.0" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` ## 🏆 Evaluation \| Tasks \|Version\|Filter\|n-shot\| Metric \|Value \| \|Stderr\| \|-------------------------------\|-------\|------\|-----:\|--------\|-----:\|---\|-----:\| \|stem \|N/A \|none \| 0\|acc \|0.6466\|± \|0.0056\| \| \| \|none \| 0\|acc_norm\|0.6124\|± \|0.0066\| \| - medmcqa \|Yaml \|none \| 0\|acc \|0.6118\|± \|0.0075\| \| \| \|none \| 0\|acc_norm\|0.6118\|± \|0.0075\| \| - medqa_4options \|Yaml \|none \| 0\|acc \|0.6143\|± \|0.0136\| \| \| \|none \| 0\|acc_norm\|0.6143\|± \|0.0136\| \| - anatomy (mmlu) \| 0\|none \| 0\|acc \|0.7185\|± \|0.0389\| \| - clinical_knowledge (mmlu) \| 0\|none \| 0\|acc \|0.7811\|± \|0.0254\| \| - college_biology (mmlu) \| 0\|none \| 0\|acc \|0.8264\|± \|0.0317\| \| - college_medicine (mmlu) \| 0\|none \| 0\|acc \|0.7110\|± \|0.0346\| \| - medical_genetics (mmlu) \| 0\|none \| 0\|acc \|0.8300\|± \|0.0378\| \| - professional_medicine (mmlu)\| 0\|none \| 0\|acc \|0.7868\|± \|0.0249\| \| - pubmedqa \| 1\|none \| 0\|acc \|0.7420\|± \|0.0196\| \|Groups\|Version\|Filter\|n-shot\| Metric \|Value \| \|Stderr\| \|------\|-------\|------\|-----:\|--------\|-----:\|---\|-----:\| \|stem \|N/A \|none \| 0\|acc \|0.6466\|± \|0.0056\| \| \| \|none \| 0\|acc_norm\|0.6124\|± \|0.0066\|
MCZK/Qwen2-7B-Instruct-GGUF	MCZK	"2024-06-07T16:44:22Z"	2,549	0	null	[ "gguf", "chat", "text-generation", "en", "license:apache-2.0", "region:us" ]	text-generation	"2024-06-06T22:23:31Z"	--- license: apache-2.0 language: - en pipeline_tag: text-generation tags: - chat --- Qwen様の [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) をGGUF形式に変換したものです。 K量子化モデルについてもiMatrix適用してあります。 iMatrixテキストはTFMC様の[c4_en_ja_imatrix.txt](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)を使用しています。

h1t/TCD-SD15-LoRA

h1t

"2024-03-08T16:30:52Z"

2,618

20

diffusers

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "arxiv:2402.19159", "base_model:runwayml/stable-diffusion-v1-5", "license:mit", "region:us" ]

text-to-image

"2024-03-08T16:29:23Z"

--- tags: - text-to-image - stable-diffusion - lora - diffusers base_model: runwayml/stable-diffusion-v1-5 license: mit library_name: diffusers --- # Model description Official TCD LoRA for Stable Diffusion v1.5 of the paper [Trajectory Consistency Distillation](https://arxiv.org/abs/2402.19159). For more usage please found at [Project Page](https://mhh0318.github.io/tcd/) Here is a simple example: ` ```python import torch from diffusers import StableDiffusionPipeline, TCDScheduler device = "cuda" base_model_id = "runwayml/stable-diffusion-v1-5" tcd_lora_id = "h1t/TCD-SD15-LoRA" pipe = StableDiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device) pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config) pipe.load_lora_weights(tcd_lora_id) pipe.fuse_lora() prompt = "Beautiful woman, bubblegum pink, lemon yellow, minty blue, futuristic, high-detail, epic composition, watercolor." image = pipe( prompt=prompt, num_inference_steps=4, guidance_scale=0, # Eta (referred to as `gamma` in the paper) is used to control the stochasticity in every step. # A value of 0.3 often yields good results. # We recommend using a higher eta when increasing the number of inference steps. eta=0.3, generator=torch.Generator(device=device).manual_seed(42), ).images[0] ``` ![](assets/result.png)

adipanda/colorizer_300k

adipanda

"2024-06-22T19:16:10Z"

2,618

0

diffusers

[ "diffusers", "safetensors", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "controlnet", "diffusers-training", "license:creativeml-openrail-m", "region:us" ]

text-to-image

"2024-06-19T20:48:11Z"

--- library_name: diffusers license: creativeml-openrail-m tags: - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - controlnet - diffusers-training - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - diffusers - controlnet - diffusers-training ---

Kukedlc/NeuralSynthesis-7B-v0.1

Kukedlc

"2024-05-25T17:09:45Z"

2,617

3

transformers

[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2024-04-06T03:40:01Z"

--- license: apache-2.0 tags: - merge - mergekit - lazymergekit model-index: - name: NeuralSynthesis-7B-v0.1 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 73.04 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 89.18 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 64.37 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 78.15 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 85.24 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 70.81 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSynthesis-7B-v0.1 name: Open LLM Leaderboard --- # NeuralSynthesis-7B-v0.1 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/eeH_75Yk5mq29FADx1TJk.png) NeuralSynthesis-7B-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): ## 🧩 Configuration ```yaml models: - model: MiniMoog/Mergerix-7b-v0.3 - model: automerger/Ognoexperiment27Multi_verse_model-7B - model: AurelPx/Percival_01-7b-slerp - model: automerger/YamshadowExperiment28-7B merge_method: model_stock base_model: automerger/YamshadowExperiment28-7B dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Kukedlc/NeuralSynthesis-7B-v0.1" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Kukedlc__NeuralSynthesis-7B-v0.1) | Metric |Value| |---------------------------------|----:| |Avg. |76.80| |AI2 Reasoning Challenge (25-Shot)|73.04| |HellaSwag (10-Shot) |89.18| |MMLU (5-Shot) |64.37| |TruthfulQA (0-shot) |78.15| |Winogrande (5-shot) |85.24| |GSM8k (5-shot) |70.81|

Weyaxi/Dolphin2.1-OpenOrca-7B

Weyaxi

"2024-01-13T11:49:19Z"

2,615

5

transformers

[ "transformers", "safetensors", "mistral", "text-generation", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2023-10-11T09:23:18Z"

--- license: apache-2.0 model-index: - name: Dolphin2.1-OpenOrca-7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 63.91 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 84.26 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 62.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 53.84 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 78.22 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 19.94 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Dolphin2.1-OpenOrca-7B name: Open LLM Leaderboard --- <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> Merge of [ehartford/dolphin-2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b) and [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) using ties merge. ### *Weights* - [ehartford/dolphin-2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b): 0.5 - [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca): 0.3 ### *Density* - [ehartford/dolphin-2.1-mistral-7b](https://huggingface.co/ehartford/dolphin-2.1-mistral-7b): 0.5 - [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca): 0.5 # Quantizationed versions Quantizationed versions of this model is available thanks to [TheBloke](https://hf.co/TheBloke). ##### GPTQ - [TheBloke/Dolphin2.1-OpenOrca-7B-GPTQ](https://huggingface.co/TheBloke/Dolphin2.1-OpenOrca-7B-GPTQ) ##### GGUF - [TheBloke/Dolphin2.1-OpenOrca-7B-GGUF](https://huggingface.co/TheBloke/Dolphin2.1-OpenOrca-7B-GGUF) ##### AWQ - [TheBloke/Dolphin2.1-OpenOrca-7B-AWQ](https://huggingface.co/TheBloke/Dolphin2.1-OpenOrca-7B-AWQ) # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Weyaxi__Dolphin2.1-OpenOrca-7B) | Metric |Value| |---------------------------------|----:| |Avg. |60.47| |AI2 Reasoning Challenge (25-Shot)|63.91| |HellaSwag (10-Shot) |84.26| |MMLU (5-Shot) |62.66| |TruthfulQA (0-shot) |53.84| |Winogrande (5-shot) |78.22| |GSM8k (5-shot) |19.94|

IlyasMoutawwakil/vit-with-hidden_states

IlyasMoutawwakil

"2024-04-18T09:41:30Z"

2,615

0

transformers

[ "transformers", "safetensors", "openvino", "vit", "image-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

"2024-04-18T09:40:57Z"

--- library_name: transformers tags: [] --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

Yntec/ProjectKawai

Yntec

"2024-06-13T16:40:00Z"

2,615

2

diffusers

[ "diffusers", "safetensors", "Anime", "Style", "HuyNguyen", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

"2024-06-13T12:36:01Z"

--- language: - en library_name: diffusers pipeline_tag: text-to-image tags: - Anime - Style - HuyNguyen - stable-diffusion - stable-diffusion-diffusers - diffusers - text-to-image inference: true license: other --- # Project K (Kawai) 768x768 version of Project K (Kawai) 5.0.1-250723 for the inference API. Check its licence at the original page: https://civitai.com/models/21138?modelVersionId=125063 Samples and prompts: ![Free online AI image generator Project Kawai](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/axGMvu1frY9l-1anJv-1g.png) (Click for larger) Top left: street, no humans, cloud, road, building, dappled sunlight, plant, blue sky, sunlight, scenery, grass, sign, day, landspace, real world location, shade, sky, city, shadow, tree, outdoors, from below, buildings Top right: sleeveless, smile, blue eyes, bangs, cloud, hat, straw hat, cloudy sky, summer, sitting, open mouth, cup, umbrella, crossed legs, innertube, denim shorts, sun, blue sky, looking at viewer, :d, hair between eyes, sunflower, legs, sunlight, sundress, holding cup, long hair, bare shoulders, short shorts Bottom left: 1girl, cleavage, fox ears, black hair, violet eyes, ribbon, kimono, japanese clothes, light smile, bare shoulders, detached sleeves, cleavage, collarbone, sitting, ribbon, hair ornament Bottom right: classic anime pretty cute little girl playing poker, iconic, 1970, from the movie, Cartoon, sharp focus. acrylic art on canvas by Clay Mann and ROSSDRAWS. CHIBI 512x512 version of Project K (Kawai) v5: https://huggingface.co/Ojimi/anime-kawai-diffusion

mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF

mradermacher

"2024-06-08T23:05:27Z"

2,614

4

transformers

[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "not-for-all-audiences", "en", "base_model:Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B", "license:llama3", "endpoints_compatible", "region:us" ]

null

"2024-06-08T20:55:57Z"

--- base_model: Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B language: - en library_name: transformers license: llama3 quantized_by: mradermacher tags: - merge - mergekit - lazymergekit - not-for-all-audiences --- ## About      static quants of https://huggingface.co/Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B  weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Halu-L3-Stheno-BlackOasis-8B-GGUF/resolve/main/Halu-L3-Stheno-BlackOasis-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

mradermacher/LBonVent-12B-i1-GGUF

mradermacher

"2024-06-13T22:58:18Z"

2,614

0

transformers

[ "transformers", "gguf", "en", "base_model:Envoid/LBonVent-12B", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]

null

"2024-06-13T16:14:34Z"

--- base_model: Envoid/LBonVent-12B language: - en library_name: transformers license: cc-by-nc-4.0 quantized_by: mradermacher --- ## About      weighted/imatrix quants of https://huggingface.co/Envoid/LBonVent-12B  static quants are available at https://huggingface.co/mradermacher/LBonVent-12B-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.8 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.1 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.5 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.7 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.0 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.0 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.1 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.5 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.0 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.1 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q4_0.gguf) | i1-Q4_0 | 6.4 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.5 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.8 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.0 | | | [GGUF](https://huggingface.co/mradermacher/LBonVent-12B-i1-GGUF/resolve/main/LBonVent-12B.i1-Q6_K.gguf) | i1-Q6_K | 9.3 | practically like static Q6_K | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.

uitnlp/visobert

uitnlp

"2024-06-09T14:21:50Z"

2,613

27

transformers

[ "transformers", "pytorch", "xlm-roberta", "fill-mask", "Vietnamese", "Social Media", "Vietnamese Pre-trained Model", "Sentiment Analysis", "Hate Speech Detection", "Spam Detection", "Emotionn Recognition", "vi", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

"2023-10-17T06:13:28Z"

--- pipeline_tag: fill-mask widget: - text: hào quang rực <mask> language: - vi tags: - Vietnamese - Social Media - Vietnamese Pre-trained Model - Sentiment Analysis - Hate Speech Detection - Spam Detection - Emotionn Recognition --- # <a name="introduction"></a> ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing (EMNLP 2023 - Main) **Disclaimer**: The paper contains actual comments on social networks that might be construed as abusive, offensive, or obscene. ViSoBERT is the state-of-the-art language model for Vietnamese social media tasks: - ViSoBERT is the first monolingual MLM ([XLM-R](https://github.com/facebookresearch/XLM#xlm-r-new-model) architecture) built specifically for Vietnamese social media texts. - ViSoBERT outperforms previous monolingual, multilingual, and multilingual social media approaches, obtaining new state-of-the-art performances on four downstream Vietnamese social media tasks. The general architecture and experimental results of ViSoBERT can be found in our [paper](https://aclanthology.org/2023.emnlp-main.315/): @inproceedings{nguyen-etal-2023-visobert, title = "{V}i{S}o{BERT}: A Pre-Trained Language Model for {V}ietnamese Social Media Text Processing", author = "Nguyen, Nam and Phan, Thang and Nguyen, Duc-Vu and Nguyen, Kiet", editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika", booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing", month = dec, year = "2023", address = "Singapore", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2023.emnlp-main.315", pages = "5191--5207", abstract = "English and Chinese, known as resource-rich languages, have witnessed the strong development of transformer-based language models for natural language processing tasks. Although Vietnam has approximately 100M people speaking Vietnamese, several pre-trained models, e.g., PhoBERT, ViBERT, and vELECTRA, performed well on general Vietnamese NLP tasks, including POS tagging and named entity recognition. These pre-trained language models are still limited to Vietnamese social media tasks. In this paper, we present the first monolingual pre-trained language model for Vietnamese social media texts, ViSoBERT, which is pre-trained on a large-scale corpus of high-quality and diverse Vietnamese social media texts using XLM-R architecture. Moreover, we explored our pre-trained model on five important natural language downstream tasks on Vietnamese social media texts: emotion recognition, hate speech detection, sentiment analysis, spam reviews detection, and hate speech spans detection. Our experiments demonstrate that ViSoBERT, with far fewer parameters, surpasses the previous state-of-the-art models on multiple Vietnamese social media tasks. Our ViSoBERT model is available only for research purposes. Disclaimer: This paper contains actual comments on social networks that might be construed as abusive, offensive, or obscene.", } The pretraining dataset of our paper is available at: [Pretraining dataset](https://drive.google.com/drive/folders/1C144LOlkbH78m0-JoMckpRXubV7XT7Kb) **Please CITE** our paper when ViSoBERT is used to help produce published results or is incorporated into other software. **Installation** Install `transformers` and `SentencePiece` packages: pip install transformers pip install SentencePiece **Example usage** ```python from transformers import AutoModel, AutoTokenizer import torch model= AutoModel.from_pretrained('uitnlp/visobert') tokenizer = AutoTokenizer.from_pretrained('uitnlp/visobert') encoding = tokenizer('hào quang rực rỡ', return_tensors='pt') with torch.no_grad(): output = model(**encoding) ```

mradermacher/Poppy_Porpoise-Biomix-GGUF

mradermacher

"2024-06-02T09:12:21Z"

2,612

1

transformers

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Nitral-AI/Poppy_Porpoise-Biomix", "endpoints_compatible", "region:us" ]

null

"2024-06-02T04:06:28Z"

--- base_model: Nitral-AI/Poppy_Porpoise-Biomix language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About      static quants of https://huggingface.co/Nitral-AI/Poppy_Porpoise-Biomix  weighted/imatrix quants are available at https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Poppy_Porpoise-Biomix-GGUF/resolve/main/Poppy_Porpoise-Biomix.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

Fulcrum-AI/Ryze-Q8_0-GGUF

Fulcrum-AI

"2024-06-26T12:36:24Z"

2,612

0

null

[ "gguf", "llama-cpp", "gguf-my-repo", "base_model:Fulcrum-AI/Ryze", "license:apache-2.0", "region:us" ]

null

"2024-06-26T12:35:53Z"

--- base_model: Fulcrum-AI/Ryze license: apache-2.0 tags: - llama-cpp - gguf-my-repo --- # Fulcrum-AI/Ryze-Q8_0-GGUF This model was converted to GGUF format from [`Fulcrum-AI/Ryze`](https://huggingface.co/Fulcrum-AI/Ryze) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/Fulcrum-AI/Ryze) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Fulcrum-AI/Ryze-Q8_0-GGUF --hf-file ryze-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Fulcrum-AI/Ryze-Q8_0-GGUF --hf-file ryze-q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Fulcrum-AI/Ryze-Q8_0-GGUF --hf-file ryze-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Fulcrum-AI/Ryze-Q8_0-GGUF --hf-file ryze-q8_0.gguf -c 2048 ```

nomic-ai/gpt4all-j

nomic-ai

"2024-04-08T15:39:51Z"

2,611

289

transformers

[ "transformers", "pytorch", "safetensors", "gptj", "text-generation", "en", "dataset:nomic-ai/gpt4all-j-prompt-generations", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-generation

"2023-04-11T15:39:16Z"

--- license: apache-2.0 datasets: - nomic-ai/gpt4all-j-prompt-generations language: - en pipeline_tag: text-generation --- # Model Card for GPT4All-J An Apache-2 licensed chatbot trained over a massive curated corpus of assistant interactions including word problems, multi-turn dialogue, code, poems, songs, and stories. ## Model Details ### Model Description  This model has been finetuned from [GPT-J](https://huggingface.co/EleutherAI/gpt-j-6B) - **Developed by:** [Nomic AI](https://home.nomic.ai) - **Model Type:** A finetuned GPT-J model on assistant style interaction data - **Language(s) (NLP):** English - **License:** Apache-2 - **Finetuned from model [optional]:** [GPT-J](https://huggingface.co/EleutherAI/gpt-j-6B) We have released several versions of our finetuned GPT-J model using [different dataset versions](https://huggingface.co/datasets/nomic-ai/gpt4all-j-prompt-generations) - v1.0: The original model trained on the v1.0 dataset - v1.1-breezy: Trained on afiltered dataset where we removed all instances of AI language model - v1.2-jazzy: Trained on a filtered dataset where we also removed instances like I'm sorry, I can't answer... and AI language model - v1.3-groovy: We added Dolly and ShareGPT to the v1.2 dataset and removed ~8% of the dataset in v1.2 that contained semantic duplicates using [Atlas](https://atlas.nomic.ai/). To download a model with a specific revision run ```python from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("nomic-ai/gpt4all-j", revision="v1.2-jazzy") ``` Downloading without specifying `revision` defaults to `main`/`v1.0`. ### Model Sources [optional]  - **Repository:** [https://github.com/nomic-ai/gpt4all](https://github.com/nomic-ai/gpt4all) - **Base Model Repository:** [https://github.com/kingoflolz/mesh-transformer-jax](https://github.com/kingoflolz/mesh-transformer-jax) - **Paper [optional]:** [GPT4All-J: An Apache-2 Licensed Assistant-Style Chatbot](https://s3.amazonaws.com/static.nomic.ai/gpt4all/2023_GPT4All-J_Technical_Report_2.pdf) - **Demo [optional]:** [https://gpt4all.io/](https://gpt4all.io/) ### Training Procedure GPT4All is made possible by our compute partner [Paperspace](https://www.paperspace.com/). Trained on a DGX cluster with 8 A100 80GB GPUs for ~12 hours. Using Deepspeed + Accelerate, we use a global batch size of 256 with a learning rate of 2e-5. More information can be found in the repo. ### Results Results on common sense reasoning benchmarks ``` | Model | BoolQ | PIQA | HellaSwag | WinoGrande | ARC-e | ARC-c | OBQA | Avg. | |:--------------------------|:--------:|:--------:|:---------:|:----------:|:--------:|:--------:|:--------:|:--------:| | GPT4All-J 6B v1.0 | 73.4 | 74.8 | 63.4 | 64.7 | 54.9 | 36.0 | 40.2 | 58.2 | | GPT4All-J v1.1-breezy | 74.0 | 75.1 | 63.2 | 63.6 | 55.4 | 34.9 | 38.4 | 57.8 | | GPT4All-J v1.2-jazzy | 74.8 | 74.9 | 63.6 | 63.8 | 56.6 | 35.3 | 41.0 | 58.6 | | GPT4All-J v1.3-groovy | 73.6 | 74.3 | 63.8 | 63.5 | 57.7 | 35.0 | 38.8 | 58.1 | | GPT4All-J Lora 6B | 68.6 | 75.8 | 66.2 | 63.5 | 56.4 | 35.7 | 40.2 | 58.1 | | GPT4All LLaMa Lora 7B | 73.1 | 77.6 | 72.1 | 67.8 | 51.1 | 40.4 | 40.2 | 60.3 | | GPT4All 13B snoozy | **83.3** | 79.2 | 75.0 | **71.3** | 60.9 | 44.2 | 43.4 | **65.3** | | Dolly 6B | 68.8 | 77.3 | 67.6 | 63.9 | 62.9 | 38.7 | 41.2 | 60.1 | | Dolly 12B | 56.7 | 75.4 | 71.0 | 62.2 | 64.6 | 38.5 | 40.4 | 58.4 | | Alpaca 7B | 73.9 | 77.2 | 73.9 | 66.1 | 59.8 | 43.3 | 43.4 | 62.4 | | Alpaca Lora 7B | 74.3 | **79.3** | 74.0 | 68.8 | 56.6 | 43.9 | 42.6 | 62.8 | | GPT-J 6.7B | 65.4 | 76.2 | 66.2 | 64.1 | 62.2 | 36.6 | 38.2 | 58.4 | | LLama 7B | 73.1 | 77.4 | 73.0 | 66.9 | 52.5 | 41.4 | 42.4 | 61.0 | | LLama 13B | 68.5 | 79.1 | 76.2 | 70.1 | 60.0 | **44.6** | 42.2 | 63.0 | | Pythia 6.7B | 63.5 | 76.3 | 64.0 | 61.1 | 61.3 | 35.2 | 37.2 | 57.0 | | Pythia 12B | 67.7 | 76.6 | 67.3 | 63.8 | 63.9 | 34.8 | 38 | 58.9 | | Fastchat T5 | 81.5 | 64.6 | 46.3 | 61.8 | 49.3 | 33.3 | 39.4 | 53.7 | | Fastchat Vicuña 7B | 76.6 | 77.2 | 70.7 | 67.3 | 53.5 | 41.2 | 40.8 | 61.0 | | Fastchat Vicuña 13B | 81.5 | 76.8 | 73.3 | 66.7 | 57.4 | 42.7 | 43.6 | 63.1 | | StableVicuña RLHF | 82.3 | 78.6 | 74.1 | 70.9 | 61.0 | 43.5 | **44.4** | 65.0 | | StableLM Tuned | 62.5 | 71.2 | 53.6 | 54.8 | 52.4 | 31.1 | 33.4 | 51.3 | | StableLM Base | 60.1 | 67.4 | 41.2 | 50.1 | 44.9 | 27.0 | 32.0 | 42.2 | | Koala 13B | 76.5 | 77.9 | 72.6 | 68.8 | 54.3 | 41.0 | 42.8 | 62.0 | | Open Assistant Pythia 12B | 67.9 | 78.0 | 68.1 | 65.0 | 64.2 | 40.4 | 43.2 | 61.0 | | Mosaic mpt-7b | 74.8 | **79.3** | **76.3** | 68.6 | **70.0** | 42.2 | 42.6 | 64.8 | | text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 | ```

CAiRE/UniVaR-lambda-1

CAiRE

"2024-06-14T17:58:19Z"

2,611

0

sentence-transformers

[ "sentence-transformers", "safetensors", "nomic_bert", "feature-extraction", "sentence-similarity", "mteb", "transformers", "transformers.js", "custom_code", "en", "arxiv:2402.01613", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-embeddings-inference", "region:us" ]

sentence-similarity

"2024-06-14T17:57:45Z"

--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - feature-extraction - sentence-similarity - mteb - transformers - transformers.js model-index: - name: epoch_0_model results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 76.8507462686567 - type: ap value: 40.592189159090495 - type: f1 value: 71.01634655512476 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 91.51892500000001 - type: ap value: 88.50346762975335 - type: f1 value: 91.50342077459624 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 47.364 - type: f1 value: 46.72708080922794 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 25.178 - type: map_at_10 value: 40.244 - type: map_at_100 value: 41.321999999999996 - type: map_at_1000 value: 41.331 - type: map_at_3 value: 35.016999999999996 - type: map_at_5 value: 37.99 - type: mrr_at_1 value: 25.605 - type: mrr_at_10 value: 40.422000000000004 - type: mrr_at_100 value: 41.507 - type: mrr_at_1000 value: 41.516 - type: mrr_at_3 value: 35.23 - type: mrr_at_5 value: 38.15 - type: ndcg_at_1 value: 25.178 - type: ndcg_at_10 value: 49.258 - type: ndcg_at_100 value: 53.776 - type: ndcg_at_1000 value: 53.995000000000005 - type: ndcg_at_3 value: 38.429 - type: ndcg_at_5 value: 43.803 - type: precision_at_1 value: 25.178 - type: precision_at_10 value: 7.831 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 16.121 - type: precision_at_5 value: 12.29 - type: recall_at_1 value: 25.178 - type: recall_at_10 value: 78.307 - type: recall_at_100 value: 97.866 - type: recall_at_1000 value: 99.57300000000001 - type: recall_at_3 value: 48.364000000000004 - type: recall_at_5 value: 61.451 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 45.93034494751465 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 36.64579480054327 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 60.601310529222054 - type: mrr value: 75.04484896451656 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 88.57797718095814 - type: cos_sim_spearman value: 86.47064499110101 - type: euclidean_pearson value: 87.4559602783142 - type: euclidean_spearman value: 86.47064499110101 - type: manhattan_pearson value: 87.7232764230245 - type: manhattan_spearman value: 86.91222131777742 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 84.5422077922078 - type: f1 value: 84.47657456950589 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 38.48953561974464 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.75995857510105 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.008000000000003 - type: map_at_10 value: 39.51 - type: map_at_100 value: 40.841 - type: map_at_1000 value: 40.973 - type: map_at_3 value: 36.248999999999995 - type: map_at_5 value: 38.096999999999994 - type: mrr_at_1 value: 36.481 - type: mrr_at_10 value: 44.818000000000005 - type: mrr_at_100 value: 45.64 - type: mrr_at_1000 value: 45.687 - type: mrr_at_3 value: 42.036 - type: mrr_at_5 value: 43.782 - type: ndcg_at_1 value: 36.481 - type: ndcg_at_10 value: 45.152 - type: ndcg_at_100 value: 50.449 - type: ndcg_at_1000 value: 52.76499999999999 - type: ndcg_at_3 value: 40.161 - type: ndcg_at_5 value: 42.577999999999996 - type: precision_at_1 value: 36.481 - type: precision_at_10 value: 8.369 - type: precision_at_100 value: 1.373 - type: precision_at_1000 value: 0.186 - type: precision_at_3 value: 18.693 - type: precision_at_5 value: 13.533999999999999 - type: recall_at_1 value: 30.008000000000003 - type: recall_at_10 value: 56.108999999999995 - type: recall_at_100 value: 78.55499999999999 - type: recall_at_1000 value: 93.659 - type: recall_at_3 value: 41.754999999999995 - type: recall_at_5 value: 48.296 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.262 - type: map_at_10 value: 40.139 - type: map_at_100 value: 41.394 - type: map_at_1000 value: 41.526 - type: map_at_3 value: 37.155 - type: map_at_5 value: 38.785 - type: mrr_at_1 value: 38.153 - type: mrr_at_10 value: 46.369 - type: mrr_at_100 value: 47.072 - type: mrr_at_1000 value: 47.111999999999995 - type: mrr_at_3 value: 44.268 - type: mrr_at_5 value: 45.389 - type: ndcg_at_1 value: 38.153 - type: ndcg_at_10 value: 45.925 - type: ndcg_at_100 value: 50.394000000000005 - type: ndcg_at_1000 value: 52.37500000000001 - type: ndcg_at_3 value: 41.754000000000005 - type: ndcg_at_5 value: 43.574 - type: precision_at_1 value: 38.153 - type: precision_at_10 value: 8.796 - type: precision_at_100 value: 1.432 - type: precision_at_1000 value: 0.189 - type: precision_at_3 value: 20.318 - type: precision_at_5 value: 14.395 - type: recall_at_1 value: 30.262 - type: recall_at_10 value: 55.72200000000001 - type: recall_at_100 value: 74.97500000000001 - type: recall_at_1000 value: 87.342 - type: recall_at_3 value: 43.129 - type: recall_at_5 value: 48.336 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 39.951 - type: map_at_10 value: 51.248000000000005 - type: map_at_100 value: 52.188 - type: map_at_1000 value: 52.247 - type: map_at_3 value: 48.211 - type: map_at_5 value: 49.797000000000004 - type: mrr_at_1 value: 45.329 - type: mrr_at_10 value: 54.749 - type: mrr_at_100 value: 55.367999999999995 - type: mrr_at_1000 value: 55.400000000000006 - type: mrr_at_3 value: 52.382 - type: mrr_at_5 value: 53.649 - type: ndcg_at_1 value: 45.329 - type: ndcg_at_10 value: 56.847 - type: ndcg_at_100 value: 60.738 - type: ndcg_at_1000 value: 61.976 - type: ndcg_at_3 value: 51.59 - type: ndcg_at_5 value: 53.915 - type: precision_at_1 value: 45.329 - type: precision_at_10 value: 8.959 - type: precision_at_100 value: 1.187 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 22.612 - type: precision_at_5 value: 15.273 - type: recall_at_1 value: 39.951 - type: recall_at_10 value: 70.053 - type: recall_at_100 value: 86.996 - type: recall_at_1000 value: 95.707 - type: recall_at_3 value: 56.032000000000004 - type: recall_at_5 value: 61.629999999999995 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.566 - type: map_at_10 value: 33.207 - type: map_at_100 value: 34.166000000000004 - type: map_at_1000 value: 34.245 - type: map_at_3 value: 30.94 - type: map_at_5 value: 32.01 - type: mrr_at_1 value: 27.345000000000002 - type: mrr_at_10 value: 35.193000000000005 - type: mrr_at_100 value: 35.965 - type: mrr_at_1000 value: 36.028999999999996 - type: mrr_at_3 value: 32.806000000000004 - type: mrr_at_5 value: 34.021 - type: ndcg_at_1 value: 27.345000000000002 - type: ndcg_at_10 value: 37.891999999999996 - type: ndcg_at_100 value: 42.664 - type: ndcg_at_1000 value: 44.757000000000005 - type: ndcg_at_3 value: 33.123000000000005 - type: ndcg_at_5 value: 35.035 - type: precision_at_1 value: 27.345000000000002 - type: precision_at_10 value: 5.763 - type: precision_at_100 value: 0.859 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 13.71 - type: precision_at_5 value: 9.401 - type: recall_at_1 value: 25.566 - type: recall_at_10 value: 50.563 - type: recall_at_100 value: 72.86399999999999 - type: recall_at_1000 value: 88.68599999999999 - type: recall_at_3 value: 37.43 - type: recall_at_5 value: 41.894999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.663 - type: map_at_10 value: 23.552 - type: map_at_100 value: 24.538 - type: map_at_1000 value: 24.661 - type: map_at_3 value: 21.085 - type: map_at_5 value: 22.391 - type: mrr_at_1 value: 20.025000000000002 - type: mrr_at_10 value: 27.643 - type: mrr_at_100 value: 28.499999999999996 - type: mrr_at_1000 value: 28.582 - type: mrr_at_3 value: 25.083 - type: mrr_at_5 value: 26.544 - type: ndcg_at_1 value: 20.025000000000002 - type: ndcg_at_10 value: 28.272000000000002 - type: ndcg_at_100 value: 33.353 - type: ndcg_at_1000 value: 36.454 - type: ndcg_at_3 value: 23.579 - type: ndcg_at_5 value: 25.685000000000002 - type: precision_at_1 value: 20.025000000000002 - type: precision_at_10 value: 5.187 - type: precision_at_100 value: 0.897 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 10.987 - type: precision_at_5 value: 8.06 - type: recall_at_1 value: 16.663 - type: recall_at_10 value: 38.808 - type: recall_at_100 value: 61.305 - type: recall_at_1000 value: 83.571 - type: recall_at_3 value: 25.907999999999998 - type: recall_at_5 value: 31.214 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.695999999999998 - type: map_at_10 value: 37.018 - type: map_at_100 value: 38.263000000000005 - type: map_at_1000 value: 38.371 - type: map_at_3 value: 34.226 - type: map_at_5 value: 35.809999999999995 - type: mrr_at_1 value: 32.916000000000004 - type: mrr_at_10 value: 42.067 - type: mrr_at_100 value: 42.925000000000004 - type: mrr_at_1000 value: 42.978 - type: mrr_at_3 value: 39.637 - type: mrr_at_5 value: 41.134 - type: ndcg_at_1 value: 32.916000000000004 - type: ndcg_at_10 value: 42.539 - type: ndcg_at_100 value: 47.873 - type: ndcg_at_1000 value: 50.08200000000001 - type: ndcg_at_3 value: 37.852999999999994 - type: ndcg_at_5 value: 40.201 - type: precision_at_1 value: 32.916000000000004 - type: precision_at_10 value: 7.5840000000000005 - type: precision_at_100 value: 1.199 - type: precision_at_1000 value: 0.155 - type: precision_at_3 value: 17.485 - type: precision_at_5 value: 12.512 - type: recall_at_1 value: 27.695999999999998 - type: recall_at_10 value: 53.638 - type: recall_at_100 value: 76.116 - type: recall_at_1000 value: 91.069 - type: recall_at_3 value: 41.13 - type: recall_at_5 value: 46.872 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.108 - type: map_at_10 value: 33.372 - type: map_at_100 value: 34.656 - type: map_at_1000 value: 34.768 - type: map_at_3 value: 30.830999999999996 - type: map_at_5 value: 32.204 - type: mrr_at_1 value: 29.110000000000003 - type: mrr_at_10 value: 37.979 - type: mrr_at_100 value: 38.933 - type: mrr_at_1000 value: 38.988 - type: mrr_at_3 value: 35.731 - type: mrr_at_5 value: 36.963 - type: ndcg_at_1 value: 29.110000000000003 - type: ndcg_at_10 value: 38.635000000000005 - type: ndcg_at_100 value: 44.324999999999996 - type: ndcg_at_1000 value: 46.747 - type: ndcg_at_3 value: 34.37 - type: ndcg_at_5 value: 36.228 - type: precision_at_1 value: 29.110000000000003 - type: precision_at_10 value: 6.963 - type: precision_at_100 value: 1.146 - type: precision_at_1000 value: 0.152 - type: precision_at_3 value: 16.400000000000002 - type: precision_at_5 value: 11.552999999999999 - type: recall_at_1 value: 24.108 - type: recall_at_10 value: 49.597 - type: recall_at_100 value: 73.88900000000001 - type: recall_at_1000 value: 90.62400000000001 - type: recall_at_3 value: 37.662 - type: recall_at_5 value: 42.565 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.00791666666667 - type: map_at_10 value: 33.287749999999996 - type: map_at_100 value: 34.41141666666667 - type: map_at_1000 value: 34.52583333333333 - type: map_at_3 value: 30.734416666666668 - type: map_at_5 value: 32.137166666666666 - type: mrr_at_1 value: 29.305666666666664 - type: mrr_at_10 value: 37.22966666666666 - type: mrr_at_100 value: 38.066583333333334 - type: mrr_at_1000 value: 38.12616666666667 - type: mrr_at_3 value: 34.92275 - type: mrr_at_5 value: 36.23333333333334 - type: ndcg_at_1 value: 29.305666666666664 - type: ndcg_at_10 value: 38.25533333333333 - type: ndcg_at_100 value: 43.25266666666666 - type: ndcg_at_1000 value: 45.63583333333334 - type: ndcg_at_3 value: 33.777166666666666 - type: ndcg_at_5 value: 35.85 - type: precision_at_1 value: 29.305666666666664 - type: precision_at_10 value: 6.596416666666667 - type: precision_at_100 value: 1.0784166666666668 - type: precision_at_1000 value: 0.14666666666666664 - type: precision_at_3 value: 15.31075 - type: precision_at_5 value: 10.830916666666667 - type: recall_at_1 value: 25.00791666666667 - type: recall_at_10 value: 49.10933333333333 - type: recall_at_100 value: 71.09216666666667 - type: recall_at_1000 value: 87.77725000000001 - type: recall_at_3 value: 36.660916666666665 - type: recall_at_5 value: 41.94149999999999 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.521 - type: map_at_10 value: 30.043 - type: map_at_100 value: 30.936000000000003 - type: map_at_1000 value: 31.022 - type: map_at_3 value: 27.926000000000002 - type: map_at_5 value: 29.076999999999998 - type: mrr_at_1 value: 26.227 - type: mrr_at_10 value: 32.822 - type: mrr_at_100 value: 33.61 - type: mrr_at_1000 value: 33.672000000000004 - type: mrr_at_3 value: 30.776999999999997 - type: mrr_at_5 value: 31.866 - type: ndcg_at_1 value: 26.227 - type: ndcg_at_10 value: 34.041 - type: ndcg_at_100 value: 38.394 - type: ndcg_at_1000 value: 40.732 - type: ndcg_at_3 value: 30.037999999999997 - type: ndcg_at_5 value: 31.845000000000002 - type: precision_at_1 value: 26.227 - type: precision_at_10 value: 5.244999999999999 - type: precision_at_100 value: 0.808 - type: precision_at_1000 value: 0.107 - type: precision_at_3 value: 12.679000000000002 - type: precision_at_5 value: 8.773 - type: recall_at_1 value: 23.521 - type: recall_at_10 value: 43.633 - type: recall_at_100 value: 63.126000000000005 - type: recall_at_1000 value: 80.765 - type: recall_at_3 value: 32.614 - type: recall_at_5 value: 37.15 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.236 - type: map_at_10 value: 22.898 - type: map_at_100 value: 23.878 - type: map_at_1000 value: 24.009 - type: map_at_3 value: 20.87 - type: map_at_5 value: 22.025 - type: mrr_at_1 value: 19.339000000000002 - type: mrr_at_10 value: 26.382 - type: mrr_at_100 value: 27.245 - type: mrr_at_1000 value: 27.33 - type: mrr_at_3 value: 24.386 - type: mrr_at_5 value: 25.496000000000002 - type: ndcg_at_1 value: 19.339000000000002 - type: ndcg_at_10 value: 27.139999999999997 - type: ndcg_at_100 value: 31.944 - type: ndcg_at_1000 value: 35.077999999999996 - type: ndcg_at_3 value: 23.424 - type: ndcg_at_5 value: 25.188 - type: precision_at_1 value: 19.339000000000002 - type: precision_at_10 value: 4.8309999999999995 - type: precision_at_100 value: 0.845 - type: precision_at_1000 value: 0.128 - type: precision_at_3 value: 10.874 - type: precision_at_5 value: 7.825 - type: recall_at_1 value: 16.236 - type: recall_at_10 value: 36.513 - type: recall_at_100 value: 57.999 - type: recall_at_1000 value: 80.512 - type: recall_at_3 value: 26.179999999999996 - type: recall_at_5 value: 30.712 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.11 - type: map_at_10 value: 31.566 - type: map_at_100 value: 32.647 - type: map_at_1000 value: 32.753 - type: map_at_3 value: 29.24 - type: map_at_5 value: 30.564999999999998 - type: mrr_at_1 value: 28.265 - type: mrr_at_10 value: 35.504000000000005 - type: mrr_at_100 value: 36.436 - type: mrr_at_1000 value: 36.503 - type: mrr_at_3 value: 33.349000000000004 - type: mrr_at_5 value: 34.622 - type: ndcg_at_1 value: 28.265 - type: ndcg_at_10 value: 36.192 - type: ndcg_at_100 value: 41.388000000000005 - type: ndcg_at_1000 value: 43.948 - type: ndcg_at_3 value: 31.959 - type: ndcg_at_5 value: 33.998 - type: precision_at_1 value: 28.265 - type: precision_at_10 value: 5.989 - type: precision_at_100 value: 0.9650000000000001 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 14.335 - type: precision_at_5 value: 10.112 - type: recall_at_1 value: 24.11 - type: recall_at_10 value: 46.418 - type: recall_at_100 value: 69.314 - type: recall_at_1000 value: 87.397 - type: recall_at_3 value: 34.724 - type: recall_at_5 value: 39.925 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.091 - type: map_at_10 value: 29.948999999999998 - type: map_at_100 value: 31.502000000000002 - type: map_at_1000 value: 31.713 - type: map_at_3 value: 27.464 - type: map_at_5 value: 28.968 - type: mrr_at_1 value: 26.482 - type: mrr_at_10 value: 34.009 - type: mrr_at_100 value: 35.081 - type: mrr_at_1000 value: 35.138000000000005 - type: mrr_at_3 value: 31.785000000000004 - type: mrr_at_5 value: 33.178999999999995 - type: ndcg_at_1 value: 26.482 - type: ndcg_at_10 value: 35.008 - type: ndcg_at_100 value: 41.272999999999996 - type: ndcg_at_1000 value: 43.972 - type: ndcg_at_3 value: 30.804 - type: ndcg_at_5 value: 33.046 - type: precision_at_1 value: 26.482 - type: precision_at_10 value: 6.462 - type: precision_at_100 value: 1.431 - type: precision_at_1000 value: 0.22899999999999998 - type: precision_at_3 value: 14.360999999999999 - type: precision_at_5 value: 10.474 - type: recall_at_1 value: 22.091 - type: recall_at_10 value: 45.125 - type: recall_at_100 value: 72.313 - type: recall_at_1000 value: 89.503 - type: recall_at_3 value: 33.158 - type: recall_at_5 value: 39.086999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 19.883 - type: map_at_10 value: 26.951000000000004 - type: map_at_100 value: 27.927999999999997 - type: map_at_1000 value: 28.022000000000002 - type: map_at_3 value: 24.616 - type: map_at_5 value: 25.917 - type: mrr_at_1 value: 21.996 - type: mrr_at_10 value: 29.221000000000004 - type: mrr_at_100 value: 30.024 - type: mrr_at_1000 value: 30.095 - type: mrr_at_3 value: 26.833000000000002 - type: mrr_at_5 value: 28.155 - type: ndcg_at_1 value: 21.996 - type: ndcg_at_10 value: 31.421 - type: ndcg_at_100 value: 36.237 - type: ndcg_at_1000 value: 38.744 - type: ndcg_at_3 value: 26.671 - type: ndcg_at_5 value: 28.907 - type: precision_at_1 value: 21.996 - type: precision_at_10 value: 5.009 - type: precision_at_100 value: 0.799 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 11.275 - type: precision_at_5 value: 8.059 - type: recall_at_1 value: 19.883 - type: recall_at_10 value: 43.132999999999996 - type: recall_at_100 value: 65.654 - type: recall_at_1000 value: 84.492 - type: recall_at_3 value: 30.209000000000003 - type: recall_at_5 value: 35.616 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 17.756 - type: map_at_10 value: 30.378 - type: map_at_100 value: 32.537 - type: map_at_1000 value: 32.717 - type: map_at_3 value: 25.599 - type: map_at_5 value: 28.372999999999998 - type: mrr_at_1 value: 41.303 - type: mrr_at_10 value: 53.483999999999995 - type: mrr_at_100 value: 54.106 - type: mrr_at_1000 value: 54.127 - type: mrr_at_3 value: 50.315 - type: mrr_at_5 value: 52.396 - type: ndcg_at_1 value: 41.303 - type: ndcg_at_10 value: 40.503 - type: ndcg_at_100 value: 47.821000000000005 - type: ndcg_at_1000 value: 50.788 - type: ndcg_at_3 value: 34.364 - type: ndcg_at_5 value: 36.818 - type: precision_at_1 value: 41.303 - type: precision_at_10 value: 12.463000000000001 - type: precision_at_100 value: 2.037 - type: precision_at_1000 value: 0.26 - type: precision_at_3 value: 25.798 - type: precision_at_5 value: 19.896 - type: recall_at_1 value: 17.756 - type: recall_at_10 value: 46.102 - type: recall_at_100 value: 70.819 - type: recall_at_1000 value: 87.21799999999999 - type: recall_at_3 value: 30.646 - type: recall_at_5 value: 38.022 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 9.033 - type: map_at_10 value: 20.584 - type: map_at_100 value: 29.518 - type: map_at_1000 value: 31.186000000000003 - type: map_at_3 value: 14.468 - type: map_at_5 value: 17.177 - type: mrr_at_1 value: 69.75 - type: mrr_at_10 value: 77.025 - type: mrr_at_100 value: 77.36699999999999 - type: mrr_at_1000 value: 77.373 - type: mrr_at_3 value: 75.583 - type: mrr_at_5 value: 76.396 - type: ndcg_at_1 value: 58.5 - type: ndcg_at_10 value: 45.033 - type: ndcg_at_100 value: 49.071 - type: ndcg_at_1000 value: 56.056 - type: ndcg_at_3 value: 49.936 - type: ndcg_at_5 value: 47.471999999999994 - type: precision_at_1 value: 69.75 - type: precision_at_10 value: 35.775 - type: precision_at_100 value: 11.594999999999999 - type: precision_at_1000 value: 2.062 - type: precision_at_3 value: 52.5 - type: precision_at_5 value: 45.300000000000004 - type: recall_at_1 value: 9.033 - type: recall_at_10 value: 26.596999999999998 - type: recall_at_100 value: 54.607000000000006 - type: recall_at_1000 value: 76.961 - type: recall_at_3 value: 15.754999999999999 - type: recall_at_5 value: 20.033 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 48.345000000000006 - type: f1 value: 43.4514918068706 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 71.29100000000001 - type: map_at_10 value: 81.059 - type: map_at_100 value: 81.341 - type: map_at_1000 value: 81.355 - type: map_at_3 value: 79.74799999999999 - type: map_at_5 value: 80.612 - type: mrr_at_1 value: 76.40299999999999 - type: mrr_at_10 value: 84.615 - type: mrr_at_100 value: 84.745 - type: mrr_at_1000 value: 84.748 - type: mrr_at_3 value: 83.776 - type: mrr_at_5 value: 84.343 - type: ndcg_at_1 value: 76.40299999999999 - type: ndcg_at_10 value: 84.981 - type: ndcg_at_100 value: 86.00999999999999 - type: ndcg_at_1000 value: 86.252 - type: ndcg_at_3 value: 82.97 - type: ndcg_at_5 value: 84.152 - type: precision_at_1 value: 76.40299999999999 - type: precision_at_10 value: 10.446 - type: precision_at_100 value: 1.1199999999999999 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 32.147999999999996 - type: precision_at_5 value: 20.135 - type: recall_at_1 value: 71.29100000000001 - type: recall_at_10 value: 93.232 - type: recall_at_100 value: 97.363 - type: recall_at_1000 value: 98.905 - type: recall_at_3 value: 87.893 - type: recall_at_5 value: 90.804 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 18.667 - type: map_at_10 value: 30.853 - type: map_at_100 value: 32.494 - type: map_at_1000 value: 32.677 - type: map_at_3 value: 26.91 - type: map_at_5 value: 29.099000000000004 - type: mrr_at_1 value: 37.191 - type: mrr_at_10 value: 46.171 - type: mrr_at_100 value: 47.056 - type: mrr_at_1000 value: 47.099000000000004 - type: mrr_at_3 value: 44.059 - type: mrr_at_5 value: 45.147 - type: ndcg_at_1 value: 37.191 - type: ndcg_at_10 value: 38.437 - type: ndcg_at_100 value: 44.62 - type: ndcg_at_1000 value: 47.795 - type: ndcg_at_3 value: 35.003 - type: ndcg_at_5 value: 36.006 - type: precision_at_1 value: 37.191 - type: precision_at_10 value: 10.586 - type: precision_at_100 value: 1.688 - type: precision_at_1000 value: 0.22699999999999998 - type: precision_at_3 value: 23.302 - type: precision_at_5 value: 17.006 - type: recall_at_1 value: 18.667 - type: recall_at_10 value: 45.367000000000004 - type: recall_at_100 value: 68.207 - type: recall_at_1000 value: 87.072 - type: recall_at_3 value: 32.129000000000005 - type: recall_at_5 value: 37.719 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 39.494 - type: map_at_10 value: 66.223 - type: map_at_100 value: 67.062 - type: map_at_1000 value: 67.11500000000001 - type: map_at_3 value: 62.867 - type: map_at_5 value: 64.994 - type: mrr_at_1 value: 78.987 - type: mrr_at_10 value: 84.585 - type: mrr_at_100 value: 84.773 - type: mrr_at_1000 value: 84.77900000000001 - type: mrr_at_3 value: 83.592 - type: mrr_at_5 value: 84.235 - type: ndcg_at_1 value: 78.987 - type: ndcg_at_10 value: 73.64 - type: ndcg_at_100 value: 76.519 - type: ndcg_at_1000 value: 77.51 - type: ndcg_at_3 value: 68.893 - type: ndcg_at_5 value: 71.585 - type: precision_at_1 value: 78.987 - type: precision_at_10 value: 15.529000000000002 - type: precision_at_100 value: 1.7770000000000001 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 44.808 - type: precision_at_5 value: 29.006999999999998 - type: recall_at_1 value: 39.494 - type: recall_at_10 value: 77.643 - type: recall_at_100 value: 88.825 - type: recall_at_1000 value: 95.321 - type: recall_at_3 value: 67.211 - type: recall_at_5 value: 72.519 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 85.55959999999999 - type: ap value: 80.7246500384617 - type: f1 value: 85.52336485065454 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 23.631 - type: map_at_10 value: 36.264 - type: map_at_100 value: 37.428 - type: map_at_1000 value: 37.472 - type: map_at_3 value: 32.537 - type: map_at_5 value: 34.746 - type: mrr_at_1 value: 24.312 - type: mrr_at_10 value: 36.858000000000004 - type: mrr_at_100 value: 37.966 - type: mrr_at_1000 value: 38.004 - type: mrr_at_3 value: 33.188 - type: mrr_at_5 value: 35.367 - type: ndcg_at_1 value: 24.312 - type: ndcg_at_10 value: 43.126999999999995 - type: ndcg_at_100 value: 48.642 - type: ndcg_at_1000 value: 49.741 - type: ndcg_at_3 value: 35.589 - type: ndcg_at_5 value: 39.515 - type: precision_at_1 value: 24.312 - type: precision_at_10 value: 6.699 - type: precision_at_100 value: 0.9450000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 15.153 - type: precision_at_5 value: 11.065999999999999 - type: recall_at_1 value: 23.631 - type: recall_at_10 value: 64.145 - type: recall_at_100 value: 89.41 - type: recall_at_1000 value: 97.83500000000001 - type: recall_at_3 value: 43.769000000000005 - type: recall_at_5 value: 53.169 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.4108527131783 - type: f1 value: 93.1415880261038 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 77.24806201550388 - type: f1 value: 60.531916308197175 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 73.71553463349024 - type: f1 value: 71.70753174900791 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.79757901815736 - type: f1 value: 77.83719850433258 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 33.74193296622113 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 30.64257594108566 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.811018518883625 - type: mrr value: 31.910376577445003 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.409 - type: map_at_10 value: 13.093 - type: map_at_100 value: 16.256999999999998 - type: map_at_1000 value: 17.617 - type: map_at_3 value: 9.555 - type: map_at_5 value: 11.428 - type: mrr_at_1 value: 45.201 - type: mrr_at_10 value: 54.179 - type: mrr_at_100 value: 54.812000000000005 - type: mrr_at_1000 value: 54.840999999999994 - type: mrr_at_3 value: 51.909000000000006 - type: mrr_at_5 value: 53.519000000000005 - type: ndcg_at_1 value: 43.189 - type: ndcg_at_10 value: 35.028 - type: ndcg_at_100 value: 31.226 - type: ndcg_at_1000 value: 39.678000000000004 - type: ndcg_at_3 value: 40.596 - type: ndcg_at_5 value: 38.75 - type: precision_at_1 value: 44.582 - type: precision_at_10 value: 25.974999999999998 - type: precision_at_100 value: 7.793 - type: precision_at_1000 value: 2.036 - type: precision_at_3 value: 38.493 - type: precision_at_5 value: 33.994 - type: recall_at_1 value: 5.409 - type: recall_at_10 value: 16.875999999999998 - type: recall_at_100 value: 30.316 - type: recall_at_1000 value: 60.891 - type: recall_at_3 value: 10.688 - type: recall_at_5 value: 13.832 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 36.375 - type: map_at_10 value: 51.991 - type: map_at_100 value: 52.91400000000001 - type: map_at_1000 value: 52.93600000000001 - type: map_at_3 value: 48.014 - type: map_at_5 value: 50.381 - type: mrr_at_1 value: 40.759 - type: mrr_at_10 value: 54.617000000000004 - type: mrr_at_100 value: 55.301 - type: mrr_at_1000 value: 55.315000000000005 - type: mrr_at_3 value: 51.516 - type: mrr_at_5 value: 53.435 - type: ndcg_at_1 value: 40.759 - type: ndcg_at_10 value: 59.384 - type: ndcg_at_100 value: 63.157 - type: ndcg_at_1000 value: 63.654999999999994 - type: ndcg_at_3 value: 52.114000000000004 - type: ndcg_at_5 value: 55.986000000000004 - type: precision_at_1 value: 40.759 - type: precision_at_10 value: 9.411999999999999 - type: precision_at_100 value: 1.153 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 23.329 - type: precision_at_5 value: 16.256999999999998 - type: recall_at_1 value: 36.375 - type: recall_at_10 value: 79.053 - type: recall_at_100 value: 95.167 - type: recall_at_1000 value: 98.82 - type: recall_at_3 value: 60.475 - type: recall_at_5 value: 69.327 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 70.256 - type: map_at_10 value: 83.8 - type: map_at_100 value: 84.425 - type: map_at_1000 value: 84.444 - type: map_at_3 value: 80.906 - type: map_at_5 value: 82.717 - type: mrr_at_1 value: 80.97999999999999 - type: mrr_at_10 value: 87.161 - type: mrr_at_100 value: 87.262 - type: mrr_at_1000 value: 87.263 - type: mrr_at_3 value: 86.175 - type: mrr_at_5 value: 86.848 - type: ndcg_at_1 value: 80.97999999999999 - type: ndcg_at_10 value: 87.697 - type: ndcg_at_100 value: 88.959 - type: ndcg_at_1000 value: 89.09899999999999 - type: ndcg_at_3 value: 84.83800000000001 - type: ndcg_at_5 value: 86.401 - type: precision_at_1 value: 80.97999999999999 - type: precision_at_10 value: 13.261000000000001 - type: precision_at_100 value: 1.5150000000000001 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 37.01 - type: precision_at_5 value: 24.298000000000002 - type: recall_at_1 value: 70.256 - type: recall_at_10 value: 94.935 - type: recall_at_100 value: 99.274 - type: recall_at_1000 value: 99.928 - type: recall_at_3 value: 86.602 - type: recall_at_5 value: 91.133 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.322692497613104 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 61.895813503775074 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.338 - type: map_at_10 value: 10.767 - type: map_at_100 value: 12.537999999999998 - type: map_at_1000 value: 12.803999999999998 - type: map_at_3 value: 7.788 - type: map_at_5 value: 9.302000000000001 - type: mrr_at_1 value: 21.4 - type: mrr_at_10 value: 31.637999999999998 - type: mrr_at_100 value: 32.688 - type: mrr_at_1000 value: 32.756 - type: mrr_at_3 value: 28.433000000000003 - type: mrr_at_5 value: 30.178 - type: ndcg_at_1 value: 21.4 - type: ndcg_at_10 value: 18.293 - type: ndcg_at_100 value: 25.274 - type: ndcg_at_1000 value: 30.284 - type: ndcg_at_3 value: 17.391000000000002 - type: ndcg_at_5 value: 15.146999999999998 - type: precision_at_1 value: 21.4 - type: precision_at_10 value: 9.48 - type: precision_at_100 value: 1.949 - type: precision_at_1000 value: 0.316 - type: precision_at_3 value: 16.167 - type: precision_at_5 value: 13.22 - type: recall_at_1 value: 4.338 - type: recall_at_10 value: 19.213 - type: recall_at_100 value: 39.562999999999995 - type: recall_at_1000 value: 64.08 - type: recall_at_3 value: 9.828000000000001 - type: recall_at_5 value: 13.383000000000001 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.42568163642142 - type: cos_sim_spearman value: 78.5797159641342 - type: euclidean_pearson value: 80.22151260811604 - type: euclidean_spearman value: 78.5797151953878 - type: manhattan_pearson value: 80.21224215864788 - type: manhattan_spearman value: 78.55641478381344 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 85.44020710812569 - type: cos_sim_spearman value: 78.91631735081286 - type: euclidean_pearson value: 81.64188964182102 - type: euclidean_spearman value: 78.91633286881678 - type: manhattan_pearson value: 81.69294748512496 - type: manhattan_spearman value: 78.93438558002656 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 84.27165426412311 - type: cos_sim_spearman value: 85.40429140249618 - type: euclidean_pearson value: 84.7509580724893 - type: euclidean_spearman value: 85.40429140249618 - type: manhattan_pearson value: 84.76488289321308 - type: manhattan_spearman value: 85.4256793698708 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 83.138851760732 - type: cos_sim_spearman value: 81.64101363896586 - type: euclidean_pearson value: 82.55165038934942 - type: euclidean_spearman value: 81.64105257080502 - type: manhattan_pearson value: 82.52802949883335 - type: manhattan_spearman value: 81.61255430718158 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 86.0654695484029 - type: cos_sim_spearman value: 87.20408521902229 - type: euclidean_pearson value: 86.8110651362115 - type: euclidean_spearman value: 87.20408521902229 - type: manhattan_pearson value: 86.77984656478691 - type: manhattan_spearman value: 87.1719947099227 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 83.77823915496512 - type: cos_sim_spearman value: 85.43566325729779 - type: euclidean_pearson value: 84.5396956658821 - type: euclidean_spearman value: 85.43566325729779 - type: manhattan_pearson value: 84.5665398848169 - type: manhattan_spearman value: 85.44375870303232 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.20030208471798 - type: cos_sim_spearman value: 87.20485505076539 - type: euclidean_pearson value: 88.10588324368722 - type: euclidean_spearman value: 87.20485505076539 - type: manhattan_pearson value: 87.92324770415183 - type: manhattan_spearman value: 87.0571314561877 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 63.06093161604453 - type: cos_sim_spearman value: 64.2163140357722 - type: euclidean_pearson value: 65.27589680994006 - type: euclidean_spearman value: 64.2163140357722 - type: manhattan_pearson value: 65.45904383711101 - type: manhattan_spearman value: 64.55404716679305 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 84.32976164578706 - type: cos_sim_spearman value: 85.54302197678368 - type: euclidean_pearson value: 85.26307149193056 - type: euclidean_spearman value: 85.54302197678368 - type: manhattan_pearson value: 85.26647282029371 - type: manhattan_spearman value: 85.5316135265568 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 81.44675968318754 - type: mrr value: 94.92741826075158 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 56.34400000000001 - type: map_at_10 value: 65.927 - type: map_at_100 value: 66.431 - type: map_at_1000 value: 66.461 - type: map_at_3 value: 63.529 - type: map_at_5 value: 64.818 - type: mrr_at_1 value: 59.333000000000006 - type: mrr_at_10 value: 67.54599999999999 - type: mrr_at_100 value: 67.892 - type: mrr_at_1000 value: 67.917 - type: mrr_at_3 value: 65.778 - type: mrr_at_5 value: 66.794 - type: ndcg_at_1 value: 59.333000000000006 - type: ndcg_at_10 value: 70.5 - type: ndcg_at_100 value: 72.688 - type: ndcg_at_1000 value: 73.483 - type: ndcg_at_3 value: 66.338 - type: ndcg_at_5 value: 68.265 - type: precision_at_1 value: 59.333000000000006 - type: precision_at_10 value: 9.3 - type: precision_at_100 value: 1.053 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 25.889 - type: precision_at_5 value: 16.866999999999997 - type: recall_at_1 value: 56.34400000000001 - type: recall_at_10 value: 82.789 - type: recall_at_100 value: 92.767 - type: recall_at_1000 value: 99 - type: recall_at_3 value: 71.64399999999999 - type: recall_at_5 value: 76.322 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.75742574257426 - type: cos_sim_ap value: 93.52081548447406 - type: cos_sim_f1 value: 87.33850129198966 - type: cos_sim_precision value: 90.37433155080214 - type: cos_sim_recall value: 84.5 - type: dot_accuracy value: 99.75742574257426 - type: dot_ap value: 93.52081548447406 - type: dot_f1 value: 87.33850129198966 - type: dot_precision value: 90.37433155080214 - type: dot_recall value: 84.5 - type: euclidean_accuracy value: 99.75742574257426 - type: euclidean_ap value: 93.52081548447406 - type: euclidean_f1 value: 87.33850129198966 - type: euclidean_precision value: 90.37433155080214 - type: euclidean_recall value: 84.5 - type: manhattan_accuracy value: 99.75841584158415 - type: manhattan_ap value: 93.4975678585854 - type: manhattan_f1 value: 87.26708074534162 - type: manhattan_precision value: 90.45064377682404 - type: manhattan_recall value: 84.3 - type: max_accuracy value: 99.75841584158415 - type: max_ap value: 93.52081548447406 - type: max_f1 value: 87.33850129198966 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 64.31437036686651 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 33.25569319007206 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 49.90474939720706 - type: mrr value: 50.568115503777264 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 29.866828641244712 - type: cos_sim_spearman value: 30.077555055873866 - type: dot_pearson value: 29.866832988572266 - type: dot_spearman value: 30.077555055873866 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.232 - type: map_at_10 value: 2.094 - type: map_at_100 value: 11.971 - type: map_at_1000 value: 28.158 - type: map_at_3 value: 0.688 - type: map_at_5 value: 1.114 - type: mrr_at_1 value: 88 - type: mrr_at_10 value: 93.4 - type: mrr_at_100 value: 93.4 - type: mrr_at_1000 value: 93.4 - type: mrr_at_3 value: 93 - type: mrr_at_5 value: 93.4 - type: ndcg_at_1 value: 84 - type: ndcg_at_10 value: 79.923 - type: ndcg_at_100 value: 61.17 - type: ndcg_at_1000 value: 53.03 - type: ndcg_at_3 value: 84.592 - type: ndcg_at_5 value: 82.821 - type: precision_at_1 value: 88 - type: precision_at_10 value: 85 - type: precision_at_100 value: 63.019999999999996 - type: precision_at_1000 value: 23.554 - type: precision_at_3 value: 89.333 - type: precision_at_5 value: 87.2 - type: recall_at_1 value: 0.232 - type: recall_at_10 value: 2.255 - type: recall_at_100 value: 14.823 - type: recall_at_1000 value: 49.456 - type: recall_at_3 value: 0.718 - type: recall_at_5 value: 1.175 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.547 - type: map_at_10 value: 11.375 - type: map_at_100 value: 18.194 - type: map_at_1000 value: 19.749 - type: map_at_3 value: 5.825 - type: map_at_5 value: 8.581 - type: mrr_at_1 value: 32.653 - type: mrr_at_10 value: 51.32 - type: mrr_at_100 value: 51.747 - type: mrr_at_1000 value: 51.747 - type: mrr_at_3 value: 47.278999999999996 - type: mrr_at_5 value: 48.605 - type: ndcg_at_1 value: 29.592000000000002 - type: ndcg_at_10 value: 28.151 - type: ndcg_at_100 value: 39.438 - type: ndcg_at_1000 value: 50.769 - type: ndcg_at_3 value: 30.758999999999997 - type: ndcg_at_5 value: 30.366 - type: precision_at_1 value: 32.653 - type: precision_at_10 value: 25.714 - type: precision_at_100 value: 8.041 - type: precision_at_1000 value: 1.555 - type: precision_at_3 value: 33.333 - type: precision_at_5 value: 31.837 - type: recall_at_1 value: 2.547 - type: recall_at_10 value: 18.19 - type: recall_at_100 value: 49.538 - type: recall_at_1000 value: 83.86 - type: recall_at_3 value: 7.329 - type: recall_at_5 value: 11.532 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.4952 - type: ap value: 14.793362635531409 - type: f1 value: 55.204635551516915 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 61.5365025466893 - type: f1 value: 61.81742556334845 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 49.05531070301185 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.51725576682364 - type: cos_sim_ap value: 75.2292304265163 - type: cos_sim_f1 value: 69.54022988505749 - type: cos_sim_precision value: 63.65629110039457 - type: cos_sim_recall value: 76.62269129287598 - type: dot_accuracy value: 86.51725576682364 - type: dot_ap value: 75.22922386081054 - type: dot_f1 value: 69.54022988505749 - type: dot_precision value: 63.65629110039457 - type: dot_recall value: 76.62269129287598 - type: euclidean_accuracy value: 86.51725576682364 - type: euclidean_ap value: 75.22925730473472 - type: euclidean_f1 value: 69.54022988505749 - type: euclidean_precision value: 63.65629110039457 - type: euclidean_recall value: 76.62269129287598 - type: manhattan_accuracy value: 86.52321630804077 - type: manhattan_ap value: 75.20608115037336 - type: manhattan_f1 value: 69.60000000000001 - type: manhattan_precision value: 64.37219730941705 - type: manhattan_recall value: 75.75197889182058 - type: max_accuracy value: 86.52321630804077 - type: max_ap value: 75.22925730473472 - type: max_f1 value: 69.60000000000001 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.34877944657896 - type: cos_sim_ap value: 86.71257569277373 - type: cos_sim_f1 value: 79.10386355986088 - type: cos_sim_precision value: 76.91468470434214 - type: cos_sim_recall value: 81.4213119802895 - type: dot_accuracy value: 89.34877944657896 - type: dot_ap value: 86.71257133133368 - type: dot_f1 value: 79.10386355986088 - type: dot_precision value: 76.91468470434214 - type: dot_recall value: 81.4213119802895 - type: euclidean_accuracy value: 89.34877944657896 - type: euclidean_ap value: 86.71257651501476 - type: euclidean_f1 value: 79.10386355986088 - type: euclidean_precision value: 76.91468470434214 - type: euclidean_recall value: 81.4213119802895 - type: manhattan_accuracy value: 89.35848177901967 - type: manhattan_ap value: 86.69330615469126 - type: manhattan_f1 value: 79.13867741453949 - type: manhattan_precision value: 76.78881807647741 - type: manhattan_recall value: 81.63689559593472 - type: max_accuracy value: 89.35848177901967 - type: max_ap value: 86.71257651501476 - type: max_f1 value: 79.13867741453949 license: apache-2.0 language: - en --- # nomic-embed-text-v1: A Reproducible Long Context (8192) Text Embedder `nomic-embed-text-v1` is 8192 context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks. | Name | SeqLen | MTEB | LoCo | Jina Long Context | Open Weights | Open Training Code | Open Data | | :-------------------------------:| :----- | :-------- | :------: | :---------------: | :-----------: | :----------------: | :---------- | | nomic-embed-text-v1 | 8192 | **62.39** |**85.53** | 54.16 | ✅ | ✅ | ✅ | | jina-embeddings-v2-base-en | 8192 | 60.39 | 85.45 | 51.90 | ✅ | ❌ | ❌ | | text-embedding-3-small | 8191 | 62.26 | 82.40 | **58.20** | ❌ | ❌ | ❌ | | text-embedding-ada-002 | 8191 | 60.99 | 52.7 | 55.25 | ❌ | ❌ | ❌ | ## Hosted Inference API The easiest way to get started with Nomic Embed is through the Nomic Embedding API. Generating embeddings with the `nomic` Python client is as easy as ```python from nomic import embed output = embed.text( texts=['Nomic Embedding API', '#keepAIOpen'], model='nomic-embed-text-v1', task_type='search_document' ) print(output) ``` For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text) ## Data Visualization Click the Nomic Atlas map below to visualize a 5M sample of our contrastive pretraining data! [![image/webp](https://cdn-uploads.huggingface.co/production/uploads/607997c83a565c15675055b3/pjhJhuNyRfPagRd_c_iUz.webp)](https://atlas.nomic.ai/map/nomic-text-embed-v1-5m-sample) ## Training Details We train our embedder using a multi-stage training pipeline. Starting from a long-context [BERT model](https://huggingface.co/nomic-ai/nomic-bert-2048), the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles. In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage. For more details, see the Nomic Embed [Technical Report](https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf) and corresponding [blog post](https://blog.nomic.ai/posts/nomic-embed-text-v1). Training data to train the models is released in its entirety. For more details, see the `contrastors` [repository](https://github.com/nomic-ai/contrastors) ## Usage Note `nomic-embed-text` *requires* prefixes! We support the prefixes `[search_query, search_document, classification, clustering]`. For retrieval applications, you should prepend `search_document` for all your documents and `search_query` for your queries. For example, you are building a RAG application over the top of Wikipedia. You would embed all Wikipedia articles with the prefix `search_document` and any questions you ask with `search_query`. For example: ```python queries = ["search_query: who is the first president of the united states?", "search_query: when was babe ruth born?"] documents = ["search_document: <article about US Presidents>", "search_document: <article about Babe Ruth>"] ``` ### Sentence Transformers ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] embeddings = model.encode(sentences) print(embeddings) ``` ### Transformers ```python import torch import torch.nn.functional as F from transformers import AutoTokenizer, AutoModel def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) model.eval() encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') with torch.no_grad(): model_output = model(**encoded_input) embeddings = mean_pooling(model_output, encoded_input['attention_mask']) embeddings = F.normalize(embeddings, p=2, dim=1) print(embeddings) ``` The model natively supports scaling of the sequence length past 2048 tokens. To do so, ```diff - tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') + tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192) - model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) + model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2) ``` ### Transformers.js ```js import { pipeline } from '@xenova/transformers'; // Create a feature extraction pipeline const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1', { quantized: false, // Comment out this line to use the quantized version }); // Compute sentence embeddings const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']; const embeddings = await extractor(texts, { pooling: 'mean', normalize: true }); console.log(embeddings); ``` # Join the Nomic Community - Nomic: [https://nomic.ai](https://nomic.ai) - Discord: [https://discord.gg/myY5YDR8z8](https://discord.gg/myY5YDR8z8) - Twitter: [https://twitter.com/nomic_ai](https://twitter.com/nomic_ai) # Citation If you find the model, dataset, or training code useful, please cite our work ```bibtex @misc{nussbaum2024nomic, title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar}, year={2024}, eprint={2402.01613}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf

RichardErkhov

"2024-06-22T18:14:05Z"

2,611

0

null

[ "gguf", "region:us" ]

null

"2024-06-22T18:02:32Z"

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) TinyLlama-1.1B-step-50K-105b - GGUF - Model creator: https://huggingface.co/TinyLlama/ - Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-step-50K-105b/ | Name | Quant method | Size | | ---- | ---- | ---- | | [TinyLlama-1.1B-step-50K-105b.Q2_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q2_K.gguf) | Q2_K | 0.4GB | | [TinyLlama-1.1B-step-50K-105b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ3_XS.gguf) | IQ3_XS | 0.44GB | | [TinyLlama-1.1B-step-50K-105b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ3_S.gguf) | IQ3_S | 0.47GB | | [TinyLlama-1.1B-step-50K-105b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q3_K_S.gguf) | Q3_K_S | 0.47GB | | [TinyLlama-1.1B-step-50K-105b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ3_M.gguf) | IQ3_M | 0.48GB | | [TinyLlama-1.1B-step-50K-105b.Q3_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q3_K.gguf) | Q3_K | 0.51GB | | [TinyLlama-1.1B-step-50K-105b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q3_K_M.gguf) | Q3_K_M | 0.51GB | | [TinyLlama-1.1B-step-50K-105b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q3_K_L.gguf) | Q3_K_L | 0.55GB | | [TinyLlama-1.1B-step-50K-105b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ4_XS.gguf) | IQ4_XS | 0.57GB | | [TinyLlama-1.1B-step-50K-105b.Q4_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_0.gguf) | Q4_0 | 0.59GB | | [TinyLlama-1.1B-step-50K-105b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.IQ4_NL.gguf) | IQ4_NL | 0.6GB | | [TinyLlama-1.1B-step-50K-105b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_K_S.gguf) | Q4_K_S | 0.6GB | | [TinyLlama-1.1B-step-50K-105b.Q4_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_K.gguf) | Q4_K | 0.62GB | | [TinyLlama-1.1B-step-50K-105b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_K_M.gguf) | Q4_K_M | 0.62GB | | [TinyLlama-1.1B-step-50K-105b.Q4_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q4_1.gguf) | Q4_1 | 0.65GB | | [TinyLlama-1.1B-step-50K-105b.Q5_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_0.gguf) | Q5_0 | 0.71GB | | [TinyLlama-1.1B-step-50K-105b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_K_S.gguf) | Q5_K_S | 0.71GB | | [TinyLlama-1.1B-step-50K-105b.Q5_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_K.gguf) | Q5_K | 0.73GB | | [TinyLlama-1.1B-step-50K-105b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_K_M.gguf) | Q5_K_M | 0.73GB | | [TinyLlama-1.1B-step-50K-105b.Q5_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q5_1.gguf) | Q5_1 | 0.77GB | | [TinyLlama-1.1B-step-50K-105b.Q6_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q6_K.gguf) | Q6_K | 0.84GB | | [TinyLlama-1.1B-step-50K-105b.Q8_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-step-50K-105b-gguf/blob/main/TinyLlama-1.1B-step-50K-105b.Q8_0.gguf) | Q8_0 | 1.09GB | Original model description: --- license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata language: - en --- <div align="center"> # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. <div align="center"> <img src="./TinyLlama_logo.png" width="300"/> </div> We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Model This is an intermediate checkpoint with 50K steps and 105B tokens. #### Releases Schedule We will be rolling out intermediate checkpoints following the below schedule. We also include some baseline models for comparison. | Date | HF Checkpoint | Tokens | Step | HellaSwag Acc_norm | |------------|-------------------------------------------------|--------|------|---------------------| | Baseline | [StableLM-Alpha-3B](https://huggingface.co/stabilityai/stablelm-base-alpha-3b)| 800B | -- | 38.31 | | Baseline | [Pythia-1B-intermediate-step-50k-105b](https://huggingface.co/EleutherAI/pythia-1b/tree/step50000) | 105B | 50k | 42.04 | | Baseline | [Pythia-1B](https://huggingface.co/EleutherAI/pythia-1b) | 300B | 143k | 47.16 | | 2023-09-04 | [TinyLlama-1.1B-intermediate-step-50k-105b](https://huggingface.co/PY007/TinyLlama-1.1B-step-50K-105b) | 105B | 50k | 43.50 | | 2023-09-16 | -- | 500B | -- | -- | | 2023-10-01 | -- | 1T | -- | -- | | 2023-10-16 | -- | 1.5T | -- | -- | | 2023-10-31 | -- | 2T | -- | -- | | 2023-11-15 | -- | 2.5T | -- | -- | | 2023-12-01 | -- | 3T | -- | -- | #### How to use You will need the transformers>=4.31 Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information. ``` from transformers import AutoTokenizer import transformers import torch model = "PY007/TinyLlama-1.1B-step-50K-105b" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( 'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.', do_sample=True, top_k=10, num_return_sequences=1, repetition_penalty=1.5, eos_token_id=tokenizer.eos_token_id, max_length=500, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ```

robertgshaw2/zephyr-7b-beta-channelwise-marlin

robertgshaw2

"2024-02-18T18:51:23Z"

2,610

0

transformers

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]

text-generation

"2024-02-18T18:49:57Z"

Entry not found

NikolayKozloff/xTower13B-Q5_K_M-GGUF

NikolayKozloff

"2024-06-27T17:20:12Z"

2,610

1

null

[ "gguf", "llama-cpp", "gguf-my-repo", "translation", "en", "de", "zh", "ru", "he", "fr", "pt", "nl", "ko", "it", "es", "dataset:Unbabel/TowerBlocks-v0.1", "base_model:sardinelab/xTower13B", "license:cc-by-nc-4.0", "region:us" ]

translation

"2024-06-27T17:19:33Z"

--- base_model: sardinelab/xTower13B datasets: - Unbabel/TowerBlocks-v0.1 language: - en - de - zh - ru - he - fr - pt - nl - ko - it - es license: cc-by-nc-4.0 metrics: - comet pipeline_tag: translation tags: - llama-cpp - gguf-my-repo --- # NikolayKozloff/xTower13B-Q5_K_M-GGUF This model was converted to GGUF format from [`sardinelab/xTower13B`](https://huggingface.co/sardinelab/xTower13B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/sardinelab/xTower13B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo NikolayKozloff/xTower13B-Q5_K_M-GGUF --hf-file xtower13b-q5_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo NikolayKozloff/xTower13B-Q5_K_M-GGUF --hf-file xtower13b-q5_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo NikolayKozloff/xTower13B-Q5_K_M-GGUF --hf-file xtower13b-q5_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo NikolayKozloff/xTower13B-Q5_K_M-GGUF --hf-file xtower13b-q5_k_m.gguf -c 2048 ```

QuantFactory/visocial-Sailor-1.8B-Instruct-GGUF

QuantFactory

"2024-07-02T06:44:22Z"

2,610

0

null

[ "gguf", "region:us" ]

null

"2024-07-02T06:34:40Z"

Entry not found

kykim/albert-kor-base

kykim

"2021-01-22T00:27:49Z"

2,609

4

transformers

[ "transformers", "pytorch", "tf", "albert", "fill-mask", "ko", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

"2022-03-02T23:29:05Z"

--- language: ko --- # Albert base model for Korean * 70GB Korean text dataset and 42000 lower-cased subwords are used * Check the model performance and other language models for Korean in [github](https://github.com/kiyoungkim1/LM-kor) ```python from transformers import BertTokenizerFast, AlbertModel tokenizer_albert = BertTokenizerFast.from_pretrained("kykim/albert-kor-base") model_albert = AlbertModel.from_pretrained("kykim/albert-kor-base") ```

RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf

RichardErkhov

"2024-06-22T23:23:38Z"

2,608

0

null

[ "gguf", "region:us" ]

null

"2024-06-22T19:05:11Z"

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Tiny-Vicuna-1B - GGUF - Model creator: https://huggingface.co/Jiayi-Pan/ - Original model: https://huggingface.co/Jiayi-Pan/Tiny-Vicuna-1B/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Tiny-Vicuna-1B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q2_K.gguf) | Q2_K | 0.4GB | | [Tiny-Vicuna-1B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ3_XS.gguf) | IQ3_XS | 0.44GB | | [Tiny-Vicuna-1B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ3_S.gguf) | IQ3_S | 0.47GB | | [Tiny-Vicuna-1B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q3_K_S.gguf) | Q3_K_S | 0.47GB | | [Tiny-Vicuna-1B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ3_M.gguf) | IQ3_M | 0.48GB | | [Tiny-Vicuna-1B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q3_K.gguf) | Q3_K | 0.51GB | | [Tiny-Vicuna-1B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q3_K_M.gguf) | Q3_K_M | 0.51GB | | [Tiny-Vicuna-1B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q3_K_L.gguf) | Q3_K_L | 0.55GB | | [Tiny-Vicuna-1B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ4_XS.gguf) | IQ4_XS | 0.57GB | | [Tiny-Vicuna-1B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_0.gguf) | Q4_0 | 0.59GB | | [Tiny-Vicuna-1B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.IQ4_NL.gguf) | IQ4_NL | 0.6GB | | [Tiny-Vicuna-1B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_K_S.gguf) | Q4_K_S | 0.6GB | | [Tiny-Vicuna-1B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_K.gguf) | Q4_K | 0.62GB | | [Tiny-Vicuna-1B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_K_M.gguf) | Q4_K_M | 0.62GB | | [Tiny-Vicuna-1B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q4_1.gguf) | Q4_1 | 0.65GB | | [Tiny-Vicuna-1B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_0.gguf) | Q5_0 | 0.71GB | | [Tiny-Vicuna-1B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_K_S.gguf) | Q5_K_S | 0.71GB | | [Tiny-Vicuna-1B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_K.gguf) | Q5_K | 0.73GB | | [Tiny-Vicuna-1B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_K_M.gguf) | Q5_K_M | 0.73GB | | [Tiny-Vicuna-1B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q5_1.gguf) | Q5_1 | 0.77GB | | [Tiny-Vicuna-1B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q6_K.gguf) | Q6_K | 0.84GB | | [Tiny-Vicuna-1B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Jiayi-Pan_-_Tiny-Vicuna-1B-gguf/blob/main/Tiny-Vicuna-1B.Q8_0.gguf) | Q8_0 | 1.09GB | Original model description: --- language: - en license: apache-2.0 model-index: - name: Tiny-Vicuna-1B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 33.45 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 55.92 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 25.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 33.82 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 58.41 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 1.52 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Jiayi-Pan/Tiny-Vicuna-1B name: Open LLM Leaderboard --- # Tiny Vicuna 1B This model is a fine-tuned version of [TinyLlama](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T) on [WizardVicuna Dataset](https://github.com/melodysdreamj/WizardVicunaLM). It should be fully compatible with Vicuna-v1.5 series. This model is easy to iterate on for early experiments! # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Jiayi-Pan__Tiny-Vicuna-1B) | Metric |Value| |---------------------------------|----:| |Avg. |34.76| |AI2 Reasoning Challenge (25-Shot)|33.45| |HellaSwag (10-Shot) |55.92| |MMLU (5-Shot) |25.45| |TruthfulQA (0-shot) |33.82| |Winogrande (5-shot) |58.41| |GSM8k (5-shot) | 1.52|

timm/pit_s_distilled_224.in1k

timm

"2023-04-26T00:08:18Z"

2,607

0

timm

[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-1k", "arxiv:2103.16302", "license:apache-2.0", "region:us" ]

image-classification

"2023-04-26T00:07:57Z"

--- tags: - image-classification - timm library_name: timm license: apache-2.0 datasets: - imagenet-1k --- # Model card for pit_s_distilled_224.in1k A PiT (Pooling based Vision Transformer) image classification model. Trained on ImageNet-1k with token based distillation by paper authors. ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 24.0 - GMACs: 2.9 - Activations (M): 11.6 - Image size: 224 x 224 - **Papers:** - Rethinking Spatial Dimensions of Vision Transformers: https://arxiv.org/abs/2103.16302 - **Dataset:** ImageNet-1k - **Original:** https://github.com/naver-ai/pit ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('pit_s_distilled_224.in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'pit_s_distilled_224.in1k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 144, 27, 27]) # torch.Size([1, 288, 14, 14]) # torch.Size([1, 576, 7, 7]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'pit_s_distilled_224.in1k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 2, 576) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Model Comparison Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results). ## Citation ```bibtex @inproceedings{heo2021pit, title={Rethinking Spatial Dimensions of Vision Transformers}, author={Byeongho Heo and Sangdoo Yun and Dongyoon Han and Sanghyuk Chun and Junsuk Choe and Seong Joon Oh}, booktitle = {International Conference on Computer Vision (ICCV)}, year={2021}, } ```

almanach/camembert-bio-base

almanach

"2024-06-24T09:29:00Z"

2,605

16

transformers

[ "transformers", "pytorch", "tf", "safetensors", "camembert", "fill-mask", "biomedical", "clinical", "life sciences", "fr", "dataset:rntc/biomed-fr", "doi:10.57967/hf/0586", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

"2023-02-23T15:03:44Z"

--- language: - fr license: mit library_name: transformers tags: - biomedical - clinical - life sciences datasets: - rntc/biomed-fr pipeline_tag: fill-mask widget: - text: Les médicaments <mask> typiques sont largement utilisés dans le traitement de première intention des patients schizophrènes. --- <a href=https://camembert-bio-model.fr/> <img width="300px" src="https://www.camembert-bio-model.fr/authors/camembert-bio/avatar_hu793b92579abd63a955d3004af578ed96_116953_270x270_fill_lanczos_center_3.png"> </a> # CamemBERT-bio : a Tasty French Language Model Better for your Health CamemBERT-bio is a state-of-the-art french biomedical language model built using continual-pretraining from [camembert-base](https://huggingface.co/camembert-base). It was trained on a french public biomedical corpus of 413M words containing scientific documents, drug leaflets and clinical cases extrated from theses and articles. It shows 2.54 points of F1 score improvement on average on 5 different biomedical named entity recognition tasks compared to [camembert-base](https://huggingface.co/camembert-base). ## Absract Clinical data in hospitals are increasingly accessible for research through clinical data warehouses, however these documents are unstructured. It is therefore necessary to extract information from medical reports to conduct clinical studies. Transfer learning with BERT-like models such as CamemBERT has allowed major advances, especially for named entity recognition. However, these models are trained for plain language and are less efficient on biomedical data. This is why we propose a new french public biomedical dataset on which we have continued the pre-training of CamemBERT. Thus, we introduce a first version of CamemBERT-bio, a specialized public model for the french biomedical domain that shows 2.54 points of F1 score improvement on average on different biomedical named entity recognition tasks. - **Developed by:** [Rian Touchent](https://rian-t.github.io), [Eric Villemonte de La Clergerie](http://pauillac.inria.fr/~clerger/) - **Logo by:** [Alix Chagué](https://alix-tz.github.io) - **License:** MIT      ## Training Details ### Training Data  | **Corpus** | **Details** | **Size** | |------------|--------------------------------------------------------------------|------------| | ISTEX | diverse scientific literature indexed on ISTEX | 276 M | | CLEAR | drug leaflets | 73 M | | E3C | various documents from journals, drug leaflets, and clinical cases | 64 M | | Total | | 413 M | ### Training Procedure  We used continual-pretraining from [camembert-base](https://huggingface.co/camembert-base). We trained the model using the Masked Language Modeling (MLM) objective with Whole Word Masking for 50k steps during 39 hours with 2 Tesla V100. ## Evaluation  ### Fine-tuning For fine-tuning, we utilized Optuna to select the hyperparameters. The learning rate was set to 5e-5, with a warmup ratio of 0.224 and a batch size of 16. The fine-tuning process was carried out for 2000 steps. For prediction, a simple linear layer was added on top of the model. Notably, none of the CamemBERT layers were frozen during the fine-tuning process. ### Scoring To evaluate the performance of the model, we used the seqeval tool in strict mode with the IOB2 scheme. For each evaluation, the best fine-tuned model on the validation set was selected to calculate the final score on the test set. To ensure reliability, we averaged over 10 evaluations with different seeds. ### Results | Style | Dataset | Score | CamemBERT | CamemBERT-bio | | :----------- | :------ | :---- | :---------------: | :-------------------: | | Clinical | CAS1 | F1 | 70\.50 ~~±~~ 1.75 | **73\.03 ~~±~~ 1.29** | | | | P | 70\.12 ~~±~~ 1.93 | **71\.71 ~~±~~ 1.61** | | | | R | 70\.89 ~~±~~ 1.78 | **74\.42 ~~±~~ 1.49** | | | CAS2 | F1 | 79\.02 ~~±~~ 0.92 | **81\.66 ~~±~~ 0.59** | | | | P | 77\.3 ~~±~~ 1.36 | **80\.96 ~~±~~ 0.91** | | | | R | 80\.83 ~~±~~ 0.96 | **82\.37 ~~±~~ 0.69** | | | E3C | F1 | 67\.63 ~~±~~ 1.45 | **69\.85 ~~±~~ 1.58** | | | | P | 78\.19 ~~±~~ 0.72 | **79\.11 ~~±~~ 0.42** | | | | R | 59\.61 ~~±~~ 2.25 | **62\.56 ~~±~~ 2.50** | | Drug leaflets | EMEA | F1 | 74\.14 ~~±~~ 1.95 | **76\.71 ~~±~~ 1.50** | | | | P | 74\.62 ~~±~~ 1.97 | **76\.92 ~~±~~ 1.96** | | | | R | 73\.68 ~~±~~ 2.22 | **76\.52 ~~±~~ 1.62** | | Scientific | MEDLINE | F1 | 65\.73 ~~±~~ 0.40 | **68\.47 ~~±~~ 0.54** | | | | P | 64\.94 ~~±~~ 0.82 | **67\.77 ~~±~~ 0.88** | | | | R | 66\.56 ~~±~~ 0.56 | **69\.21 ~~±~~ 1.32** | ## Environmental Impact estimation  - **Hardware Type:** 2 x Tesla V100 - **Hours used:** 39 hours - **Provider:** INRIA clusters - **Compute Region:** Paris, France - **Carbon Emitted:** 0.84 kg CO2 eq.    ## Citation information ```bibtex @inproceedings{touchent-de-la-clergerie-2024-camembert-bio, title = "{C}amem{BERT}-bio: Leveraging Continual Pre-training for Cost-Effective Models on {F}rench Biomedical Data", author = "Touchent, Rian and de la Clergerie, {\'E}ric", editor = "Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen", booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)", month = may, year = "2024", address = "Torino, Italia", publisher = "ELRA and ICCL", url = "https://aclanthology.org/2024.lrec-main.241", pages = "2692--2701", abstract = "Clinical data in hospitals are increasingly accessible for research through clinical data warehouses. However these documents are unstructured and it is therefore necessary to extract information from medical reports to conduct clinical studies. Transfer learning with BERT-like models such as CamemBERT has allowed major advances for French, especially for named entity recognition. However, these models are trained for plain language and are less efficient on biomedical data. Addressing this gap, we introduce CamemBERT-bio, a dedicated French biomedical model derived from a new public French biomedical dataset. Through continual pre-training of the original CamemBERT, CamemBERT-bio achieves an improvement of 2.54 points of F1-score on average across various biomedical named entity recognition tasks, reinforcing the potential of continual pre-training as an equally proficient yet less computationally intensive alternative to training from scratch. Additionally, we highlight the importance of using a standard evaluation protocol that provides a clear view of the current state-of-the-art for French biomedical models.", } @inproceedings{touchent:hal-04130187, TITLE = {{CamemBERT-bio : Un mod{\`e}le de langue fran{\c c}ais savoureux et meilleur pour la sant{\'e}}}, AUTHOR = {Touchent, Rian and Romary, Laurent and De La Clergerie, Eric}, URL = {https://hal.science/hal-04130187}, BOOKTITLE = {{18e Conf{\'e}rence en Recherche d'Information et Applications \\ 16e Rencontres Jeunes Chercheurs en RI \\ 30e Conf{\'e}rence sur le Traitement Automatique des Langues Naturelles \\ 25e Rencontre des {\'E}tudiants Chercheurs en Informatique pour le Traitement Automatique des Langues}}, ADDRESS = {Paris, France}, EDITOR = {Servan, Christophe and Vilnat, Anne}, PUBLISHER = {{ATALA}}, PAGES = {323-334}, YEAR = {2023}, KEYWORDS = {comptes rendus m{\'e}dicaux ; TAL clinique ; CamemBERT ; extraction d'information ; biom{\'e}dical ; reconnaissance d'entit{\'e}s nomm{\'e}es}, HAL_ID = {hal-04130187}, HAL_VERSION = {v1}, } ```

Backedman/TriviaAnsweringMachineREAL

Backedman

"2024-05-12T22:28:55Z"

2,605

0

transformers

[ "transformers", "pytorch", "TFIDF-QA", "question-answering", "custom_code", "en", "license:mit", "region:us" ]

question-answering

"2024-05-07T01:04:47Z"

--- language: - en license: mit pipeline_tag: question-answering --- The evaluation of this project is to answer trivia questions. You do not need to do well at this task, but you should submit a system that completes the task or create adversarial questions in that setting. This will help the whole class share data and resources. If you focus on something other than predicting answers, *that's fine*! About the Data ============== Quiz bowl is an academic competition between schools in English-speaking countries; hundreds of teams compete in dozens of tournaments each year. Quiz bowl is different from Jeopardy, a recent application area. While Jeopardy also uses signaling devices, these are only usable after a question is completed (interrupting Jeopardy's questions would make for bad television). Thus, Jeopardy is rapacious classification followed by a race---among those who know the answer---to punch a button first. Here's an example of a quiz bowl question: Expanding on a 1908 paper by Smoluchowski, he derived a formula for the intensity of scattered light in media fluctuating densities that reduces to Rayleigh's law for ideal gases in The Theory of the Opalescence of Homogenous Fluids and Liquid Mixtures near the Critical State. That research supported his theories of matter first developed when he calculated the diffusion constant in terms of fundamental parameters of the particles of a gas undergoing Brownian Motion. In that same year, 1905, he also published On a Heuristic Point of View Concerning the Production and Transformation of Light. That explication of the photoelectric effect won him 1921 Nobel in Physics. For ten points, name this German physicist best known for his theory of Relativity. *ANSWER*: Albert _Einstein_ Two teams listen to the same question. Teams interrupt the question at any point by "buzzing in"; if the answer is correct, the team gets points and the next question is read. Otherwise, the team loses points and the other team can answer. You are welcome to use any *automatic* method to choose an answer. It need not be similar nor build on our provided systems. In addition to the data we provide, you are welcome to use any external data *except* our test quiz bowl questions (i.e., don't hack our server!). You are welcome (an encouraged) to use any publicly available software, but you may want to check on Piazza for suggestions as many tools are better (or easier to use) than others. If you don't like the interruptability of questions, you can also just answer entire questions. However, you must also output a confidence. Competition ================== We will use Dynabech website (https://dynabench.org/tasks/qa). If you remember the past workshop about Dynabench submission, this is the way to do it. The specific task name is "Grounded QA". Here, with the help of the video tutorial, you submit your QA model and assess how your QA model did compared to others. The assessment will take place by testing your QA model on several QA test datasets and the results of yours and your competitors will be visible on the leaderboard. Your goal is to rank the highest in terms of expected wins: you buzz in with probability proportional to your confidence, and if you're more right than the competition, you win. Writing Questions ================== Alternatively, you can also *write* 50 adversarial questions that challenge modern NLP systems. These questions must be diverse in the subjects asked about, the skills computers need to answer the questions, and the entities in those questions. Remember that your questions should be *factual* and *specific* enough for humans to answer, because your task is to stump the computers relative to humans! In addition to the raw questions, you will also need to create citations describing: * Why the question is difficult for computers: include citations from the NLP/AI/ML literature * Why the information in the question is correct: include citations from the sources you drew on the write the question * Why the question is interesting: include scholarly / popular culture artifacts to prove that people care about this * Why the question is pyramidal: discuss why your first clues are harder than your later clues **Category** We want questions from many domains such as Art, Literature, Geography, History, Science, TV and Film, Music, Lifestyle, and Sport. The questions should be written using all topics above (5 questions for each category and 5 more for the remaining categories). Indicate in your writeup which category you chose to write on for each question. Art: * Questions about works: Mona Lisa, Raft of the Medussa * Questions about forms: color, contour, texture * Questions about artists: Picasso, Monet, Leonardo da Vinci * Questions about context: Renaissance, post-modernism, expressionism, surrealism Literature: * Questions about works: novels (1984), plays (The Lion and the Jewel), poems (Rubaiyat), criticism (Poetics) * Questions about major characters or events in literature: The Death of Anna Karenina, Noboru Wataya, the Marriage of Hippolyta and Theseus * Questions about literary movements (Sturm und Drang) * Questions about translations * Cross-cutting questions (appearances of Overcoats in novels) * Common link questions (the literary output of a country/region) Geography: * Questions about location: names of capital, state, river * Questions about the place: temperature, wind flow, humidity History: * When: When did the First World war start? * Who: Who is called Napoleon of Iran? * Where: Where was the first Summer Olympics held? * Which: Which is the oldest civilization in the world? Science: * Questions about terminology: The concept of gravity was discovered by which famous physicist? * Questions about the experiment * Questions about theory: The social action theory believes that individuals are influenced by this theory. TV and Film: * Quotes: What are the dying words of Charles Foster Kane in Citizen Kane? * Title: What 1927 musical was the first "talkie"? * Plot: In The Matrix, does Neo take the blue pill or the red pill? Music: * Singer: What singer has had a Billboard No. 1 hit in each of the last four decades? * Band: Before Bleachers and fun., Jack Antonoff fronted what band? * Title: What was Madonna's first top 10 hit? * History: Which classical composer was deaf? Lifestyle: * Clothes: What clothing company, founded by a tennis player, has an alligator logo? * Decoration: What was the first perfume sold by Coco Chanel? Sport: * Known facts: What sport is best known as the ‘king of sports’? * Nationality: What’s the national sport of Canada? * Sport player: The classic 1980 movie called Raging Bull is about which real-life boxer? * Country: What country has competed the most times in the Summer Olympics yet hasn’t won any kind of medal? **Diversity** Other than category diversity, if you find an ingenious way of writing questions about underrepresented countries, you will get bonus points (indicate which questions you included the diversity component in your writeup). You may decide which are underrepresented countries with your own reasonable reason (etc., less population may indicate underrepresented), but make sure to articulate this in your writeup. * Run state of the art QA systems on the questions to show they struggle, give individual results for each question and a summary over all questions For an example of what the writeup for a single question should look like, see the adversarial HW: https://github.com/Pinafore/nlp-hw/blob/master/adversarial/question.tex Proposal ================== The project proposal is a one page PDF document that describes: * Who is on your team (team sizes can be between three and six students, but six is really too big to be effective; my suggestion is that most groups should be between four or five). * What techniques you will explore * Your timeline for completing the project (be realistic; you should have your first submission in a week or two) Submit the proposal on Gradescope, but make sure to include all group members. If all group members are not included, you will lose points. Late days cannot be used on this assignment. Milestone 1 ====================== You'll have to update how things are going: what's working, what isn't, and how does it change your timeline? How does it change your division of labor? *Question Writing*: You'll need to have answers selected for all of your questions and first drafts of at least 15 questions. This must be submitted as a JSON file so that we run computer QA systems on it. *Project*: You'll need to have made a submission to the leaderboard with something that satisfies the API. Submit a PDF updating on your progress to Gradescope. If all team members are not on the submission, you will lose points. Milestone 2 =================== As before, provide an updated timeline / division of labor, provide your intermediary results. *Question Writing*: You'll need to have reflected the feedback from the first questions and completed a first draft of at least 30 questions. You'll also need machine results to your questions and an overall evaluation of your human/computer accuracy. *Project*: You'll need to have a made a submission to the leaderboard with a working system (e.g., not just obey the API, but actually get reasonable answers). Submit a PDF updating on your progress. Final Presentation ====================== The final presentation will be virtual (uploading a video). In the final presentation you will: * Explain what you did * Who did what. For example, for the question writing project a team of five people might write: A wrote the first draft of questions. B and C verified they were initially answerable by a human. B ran computer systems to verify they were challenging to a computer. C edited the questions and increased the computer difficulty. D and E verified that the edited questions were still answerable by a human. D and E checked all of the questions for factual accuracy and created citations and the writeup. * What challenges you had * Review how well you did (based on the competition or your own metrics). If you do not use the course infrastructure to evaluate your project's work, you should talk about what alternative evaluations you used, why they're appropriate/fair, and how well you did on them. * Provide an error analysis. An error analysis must contain examples from the development set that you get wrong. You should show those sentences and explain why (in terms of features or the model) they have the wrong answer. You should have been doing this all along as you derive new features, but this is your final inspection of your errors. The feature or model problems you discover should not be trivial features you could add easily. Instead, these should be features or models that are difficult to correct. An error analysis is not the same thing as simply presenting the error matrix, as it does not inspect any individual examples. If you're writing questions, talk about examples of questions that didn't work out as intended. * The linguistic motivation for your features / how your wrote the questions. This is a computational linguistics class, so you should give precedence to features / techniques that we use in this class (e.g., syntax, morphology, part of speech, word sense, etc.). Given two features that work equally well and one that is linguistically motivated, we'll prefer the linguistically motivated one. * Presumably you did many different things; how did they each individually contribute to your final result? Each group has 10 minutes to deliver their presentation. Please record the video, and upload it to Google Drive, and include the link in your writeup submission. Final Question Submission ====================== Because we need to get the questions ready for the systems, upload your raw questions on May 10. This doesn't include the citations or other parts of the writeup. System Submission ====================== You must submit a version of your system by May 12. It may not be perfect, but this what the question writing teams will use to test their results. Your system should be sent directly to the professor and TAs in zip files, including the correct dependencies and a working inference code. Your inference code should run successfully in the root folder (extracted from zip folder) directory with the command: ``` > python3 inference.py --data=evaluation_set.json ``` The input will be in the form of a .json file () in the same format as the file the adversarial question writing team submits. The output format should also be in string. If you have any notes or comments that we should be aware of while running your code, please include them in the folder as a .txt file. Also, dependency information should be included as a .txt file. Please prepend your email title with [2024-CMSC 470 System Submission]. Project Writeup and JSON file ====================== By May 17, submit your project writeup explaining what you did and what results you achieved. This document should make it clear: * Why this is a good idea * What you did * Who did what * Whether your technique worked or not For systems, please do not go over 2500 words unless you have a really good reason. Images are a much better use of space than words, usually (there's no limit on including images, but use judgement and be selective). For question writing, you have one page (single spaced, two column) per question plus a two page summary of results. Talk about how you organized the question writing, how you evaluated the questions, and a summary of the results. Along with your writeup, turn in a json including the raw text of the question and answer and category. The json file is included in this directory. Make sure your json file is in the correct format and is callable via below code. Your submission will not be graded if it does not follow the format of the example json file. ``` with open('path to your json file', 'r') as f: data = json.load(f) ``` Grade ====================== The grade will be out of 25 points, broken into five areas: * _Presentation_: For your oral presentation, do you highlight what you did and make people care? Did you use time well during the presentation? * _Writeup_: Does the writeup explain what you did in a way that is clear and effective? The final three areas are different between the system and the questions. | | System | Questions | |----------|:-------------:|------:| | _Technical Soundness_ | Did you use the right tools for the job, and did you use them correctly? Were they relevant to this class? | Were your questions correct and accurately cited. | | _Effort_ | Did you do what you say you would, and was it the right ammount of effort. | Are the questions well-written, interesting, and thoroughly edited? | | _Performance_ | How did your techniques perform in terms of accuracy, recall, etc.? | Is the human accuracy substantially higher than the computer accuracy? | All members of the group will receive the same grade. It's impossible for the course staff to adjudicate Rashomon-style accounts of who did what, and the goal of a group project is for all team members to work together to create a cohesive project that works well together. While it makes sense to divide the work into distinct areas of responsibility, at grading time we have now way to know who really did what, so it's the groups responsibility to create a piece of output that reflects well on the whole group.

Timoschi/Meta-Llama-3-8B-Q8_0-GGUF

Timoschi

"2024-06-23T19:53:21Z"

2,605

0

null

[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "base_model:meta-llama/Meta-Llama-3-8B", "license:llama3", "region:us" ]

text-generation

"2024-06-23T19:52:44Z"

--- base_model: meta-llama/Meta-Llama-3-8B language: - en license: llama3 pipeline_tag: text-generation tags: - facebook - meta - pytorch - llama - llama-3 - llama-cpp - gguf-my-repo extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\ \ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\ \ use, reproduction, distribution and modification of the Llama Materials set forth\ \ herein.\n\"Documentation\" means the specifications, manuals and documentation\ \ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\ \ (if you are entering into this Agreement on such person or entity’s behalf), of\ \ the age required under applicable laws, rules or regulations to provide legal\ \ consent and that has legal authority to bind your employer or such other person\ \ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\ \ 3\" means the foundational large language models and software and algorithms,\ \ including machine-learning model code, trained model weights, inference-enabling\ \ code, training-enabling code, fine-tuning enabling code and other elements of\ \ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\ \"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\ \ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\ we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\ \ an entity, your principal place of business is in the EEA or Switzerland) and\ \ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\ \ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\ \ a non-exclusive, worldwide, non-transferable and royalty-free limited license\ \ under Meta’s intellectual property or other rights owned by Meta embodied in the\ \ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\ \ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\ \ If you distribute or make available the Llama Materials (or any derivative works\ \ thereof), or a product or service that uses any of them, including another AI\ \ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\ \ and (B) prominently display “Built with Meta Llama 3” on a related website, user\ \ interface, blogpost, about page, or product documentation. If you use the Llama\ \ Materials to create, train, fine tune, or otherwise improve an AI model, which\ \ is distributed or made available, you shall also include “Llama 3” at the beginning\ \ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\ \ works thereof, from a Licensee as part of an integrated end user product, then\ \ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\ \ copies of the Llama Materials that you distribute the following attribution notice\ \ within a “Notice” text file distributed as a part of such copies: “Meta Llama\ \ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\ \ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\ \ applicable laws and regulations (including trade compliance laws and regulations)\ \ and adhere to the Acceptable Use Policy for the Llama Materials (available at\ \ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\ \ into this Agreement.\nv. You will not use the Llama Materials or any output or\ \ results of the Llama Materials to improve any other large language model (excluding\ \ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\ \ on the Meta Llama 3 version release date, the monthly active users of the products\ \ or services made available by or for Licensee, or Licensee’s affiliates, is greater\ \ than 700 million monthly active users in the preceding calendar month, you must\ \ request a license from Meta, which Meta may grant to you in its sole discretion,\ \ and you are not authorized to exercise any of the rights under this Agreement\ \ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\ \ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\ \ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\ \ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\ \ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\ \ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\ \ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\ \ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\ 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\ \ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\ \ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\ \ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\ \ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\ 5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\ \ and in connection with the Llama Materials, neither Meta nor Licensee may use\ \ any name or mark owned by or associated with the other or any of its affiliates,\ \ except as required for reasonable and customary use in describing and redistributing\ \ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\ \ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\ \ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\ \ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\ \ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\ b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\ \ Meta, with respect to any derivative works and modifications of the Llama Materials\ \ that are made by you, as between you and Meta, you are and will be the owner of\ \ such derivative works and modifications.\nc. If you institute litigation or other\ \ proceedings against Meta or any entity (including a cross-claim or counterclaim\ \ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\ \ or any portion of any of the foregoing, constitutes infringement of intellectual\ \ property or other rights owned or licensable by you, then any licenses granted\ \ to you under this Agreement shall terminate as of the date such litigation or\ \ claim is filed or instituted. You will indemnify and hold harmless Meta from and\ \ against any claim by any third party arising out of or related to your use or\ \ distribution of the Llama Materials.\n6. Term and Termination. The term of this\ \ Agreement will commence upon your acceptance of this Agreement or access to the\ \ Llama Materials and will continue in full force and effect until terminated in\ \ accordance with the terms and conditions herein. Meta may terminate this Agreement\ \ if you are in breach of any term or condition of this Agreement. Upon termination\ \ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\ \ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\ \ and Jurisdiction. This Agreement will be governed and construed under the laws\ \ of the State of California without regard to choice of law principles, and the\ \ UN Convention on Contracts for the International Sale of Goods does not apply\ \ to this Agreement. The courts of California shall have exclusive jurisdiction\ \ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\ \ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\ \ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\ \ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\ #### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\ \ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\ \ illegal distribution of information or materials to minors, including obscene\ \ materials, or failure to employ legally required age-gating in connection with\ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\ \ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\ \ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\ \ or harmful conduct in the provision of employment, employment benefits, credit,\ \ housing, other economic benefits, or other essential goods and services\n 4.\ \ Engage in the unauthorized or unlicensed practice of any profession including,\ \ but not limited to, financial, legal, medical/health, or related professional\ \ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\ \ or other sensitive personal or private information about individuals without rights\ \ and consents required by applicable laws\n 6. Engage in or facilitate any action\ \ or generate any content that infringes, misappropriates, or otherwise violates\ \ any third-party rights, including the outputs or results of any products or services\ \ using the Llama Materials\n 7. Create, generate, or facilitate the creation\ \ of malicious code, malware, computer viruses or do anything else that could disable,\ \ overburden, interfere with or impair the proper working, integrity, operation\ \ or appearance of a website or computer system\n2. Engage in, promote, incite,\ \ facilitate, or assist in the planning or development of activities that present\ \ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\ \ espionage, use for materials or activities that are subject to the International\ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\ \ content intended to incite or promote violence, abuse, or any infliction of bodily\ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\ \ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\ \ or furthering defamatory content, including the creation of defamatory statements,\ \ images, or other content\n 3. Generating, promoting, or further distributing\ \ spam\n 4. Impersonating another individual without consent, authorization,\ \ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\ \ human-generated\n 6. Generating or facilitating false online engagement, including\ \ fake reviews and other means of fake online engagement\n4. Fail to appropriately\ \ disclose to end users any known dangers of your AI system\nPlease report any violation\ \ of this Policy, software “bug,” or other problems that could lead to a violation\ \ of this Policy through one of the following means:\n * Reporting issues with\ \ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\ \ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\ \ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\ \ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]" extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text geo: ip_location ? By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy : checkbox extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit --- # Timoschi/Meta-Llama-3-8B-Q8_0-GGUF This model was converted to GGUF format from [`meta-llama/Meta-Llama-3-8B`](https://huggingface.co/meta-llama/Meta-Llama-3-8B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-8B) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Timoschi/Meta-Llama-3-8B-Q8_0-GGUF --hf-file meta-llama-3-8b-q8_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Timoschi/Meta-Llama-3-8B-Q8_0-GGUF --hf-file meta-llama-3-8b-q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Timoschi/Meta-Llama-3-8B-Q8_0-GGUF --hf-file meta-llama-3-8b-q8_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Timoschi/Meta-Llama-3-8B-Q8_0-GGUF --hf-file meta-llama-3-8b-q8_0.gguf -c 2048 ```

microsoft/layoutlmv2-large-uncased

microsoft

"2022-09-16T03:40:36Z"

2,604

8

transformers

[ "transformers", "pytorch", "layoutlmv2", "en", "arxiv:2012.14740", "license:cc-by-nc-sa-4.0", "endpoints_compatible", "region:us" ]

null

"2022-03-02T23:29:05Z"

--- language: en license: cc-by-nc-sa-4.0 --- # LayoutLMv2 **Multimodal (text + layout/format + image) pre-training for document AI** ## Introduction LayoutLMv2 is an improved version of LayoutLM with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. It outperforms strong baselines and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including , including FUNSD (0.7895 → 0.8420), CORD (0.9493 → 0.9601), SROIE (0.9524 → 0.9781), Kleister-NDA (0.834 → 0.852), RVL-CDIP (0.9443 → 0.9564), and DocVQA (0.7295 → 0.8672). [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://arxiv.org/abs/2012.14740) Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, Min Zhang, Lidong Zhou, [ACL 2021](#)

mradermacher/Dr.RP.Samantha-L3-8B-GGUF

mradermacher

"2024-06-16T04:07:05Z"

2,604

0

transformers

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:WesPro/Dr.RP.Samantha-L3-8B", "endpoints_compatible", "region:us" ]

null

"2024-06-15T20:56:40Z"

--- base_model: WesPro/Dr.RP.Samantha-L3-8B language: - en library_name: transformers quantized_by: mradermacher tags: - mergekit - merge --- ## About      static quants of https://huggingface.co/WesPro/Dr.RP.Samantha-L3-8B  weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Dr.RP.Samantha-L3-8B-GGUF/resolve/main/Dr.RP.Samantha-L3-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

facebook/convnextv2-base-1k-224

facebook

"2023-02-20T13:00:30Z"

2,603

2

transformers

[ "transformers", "pytorch", "convnextv2", "image-classification", "vision", "dataset:imagenet-1k", "arxiv:2301.00808", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

"2023-02-17T14:12:51Z"

--- license: apache-2.0 tags: - vision - image-classification datasets: - imagenet-1k widget: - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg example_title: Tiger - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg example_title: Teapot - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg example_title: Palace --- # ConvNeXt V2 (base-sized model) ConvNeXt V2 model pretrained using the FCMAE framework and fine-tuned on the ImageNet-1K dataset at resolution 224x224. It was introduced in the paper [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://arxiv.org/abs/2301.00808) by Woo et al. and first released in [this repository](https://github.com/facebookresearch/ConvNeXt-V2). Disclaimer: The team releasing ConvNeXT V2 did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description ConvNeXt V2 is a pure convolutional model (ConvNet) that introduces a fully convolutional masked autoencoder framework (FCMAE) and a new Global Response Normalization (GRN) layer to ConvNeXt. ConvNeXt V2 significantly improves the performance of pure ConvNets on various recognition benchmarks. ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/convnextv2_architecture.png) ## Intended uses & limitations You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=convnextv2) to look for fine-tuned versions on a task that interests you. ### How to use Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes: ```python from transformers import AutoImageProcessor, ConvNextV2ForImageClassification import torch from datasets import load_dataset dataset = load_dataset("huggingface/cats-image") image = dataset["test"]["image"][0] preprocessor = AutoImageProcessor.from_pretrained("facebook/convnextv2-base-1k-224") model = ConvNextV2ForImageClassification.from_pretrained("facebook/convnextv2-base-1k-224") inputs = preprocessor(image, return_tensors="pt") with torch.no_grad(): logits = model(**inputs).logits # model predicts one of the 1000 ImageNet classes predicted_label = logits.argmax(-1).item() print(model.config.id2label[predicted_label]), ``` For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/convnextv2). ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-2301-00808, author = {Sanghyun Woo and Shoubhik Debnath and Ronghang Hu and Xinlei Chen and Zhuang Liu and In So Kweon and Saining Xie}, title = {ConvNeXt {V2:} Co-designing and Scaling ConvNets with Masked Autoencoders}, journal = {CoRR}, volume = {abs/2301.00808}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.00808}, doi = {10.48550/arXiv.2301.00808}, eprinttype = {arXiv}, eprint = {2301.00808}, timestamp = {Tue, 10 Jan 2023 15:10:12 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-00808.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```

marella/gpt-2-ggml

marella

"2023-05-20T11:05:41Z"

2,603

11

ctransformers

[ "ctransformers", "gpt2", "license:mit", "region:us" ]

null

"2023-05-14T17:08:30Z"

--- license: mit library_name: ctransformers --- ```sh pip install ctransformers ``` ```py from ctransformers import AutoModelForCausalLM llm = AutoModelForCausalLM.from_pretrained('marella/gpt-2-ggml') print(llm('AI is going to')) ``` See https://github.com/marella/ctransformers

JuanMa360/room-classification

JuanMa360

"2023-12-08T07:32:42Z"

2,603

4

transformers

[ "transformers", "pytorch", "safetensors", "vit", "image-classification", "huggingpics", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

image-classification

"2023-09-15T17:50:28Z"

--- tags: - image-classification - pytorch - huggingpics metrics: - accuracy model-index: - name: room-classification results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.8650000095367432 --- # room-classification House & Apartaments Classification model🤗🖼️ ## Example Images #### Exterior ![Exterior](images/Exterior.jpeg) #### closets ![closets](images/closets.jpg) #### kitchen ![kitchen](images/kitchen.jpeg) #### others ![others](images/others.jpg)

DiTy/cross-encoder-russian-msmarco

DiTy

"2024-05-15T18:57:43Z"

2,603

0

sentence-transformers

[ "sentence-transformers", "safetensors", "bert", "text-classification", "transformers", "rubert", "cross-encoder", "msmarco", "ru", "dataset:unicamp-dl/mmarco", "base_model:DeepPavlov/rubert-base-cased", "license:mit", "region:us" ]

text-classification

"2024-04-19T15:24:56Z"

--- language: - ru library_name: sentence-transformers tags: - sentence-transformers - text-classification - transformers - rubert - cross-encoder - msmarco datasets: - unicamp-dl/mmarco base_model: DeepPavlov/rubert-base-cased widget: - text: >- как часто нужно ходить к стоматологу? [SEP] Дядя Женя работает врачем стоматологом. example_title: Example 1 - text: >- как часто нужно ходить к стоматологу? [SEP] Минимальный обязательный срок посещения зубного врача – раз в год, но специалисты рекомендуют делать это чаще – раз в полгода, а ещё лучше – раз в квартал. При таком сроке легко отследить любые начинающиеся проблемы и исправить их сразу же. example_title: Example 2 license: mit --- # DiTy/cross-encoder-russian-msmarco This is a [sentence-transformers](https://www.SBERT.net) model based on a pre-trained [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) and finetuned with [MS-MARCO Russian passage ranking dataset](https://huggingface.co/datasets/unicamp-dl/mmarco). The model can be used for Information Retrieval in the Russian language: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See [SBERT.net Retrieve & Re-rank](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for more details.  ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import CrossEncoder reranker_model = CrossEncoder('DiTy/cross-encoder-russian-msmarco', max_length=512, device='cuda') query = ["как часто нужно ходить к стоматологу?"] documents = [ "Минимальный обязательный срок посещения зубного врача – раз в год, но специалисты рекомендуют делать это чаще – раз в полгода, а ещё лучше – раз в квартал. При таком сроке легко отследить любые начинающиеся проблемы и исправить их сразу же.", "Основная причина заключается в истончении поверхностного слоя зуба — эмали, которая защищает зуб от механических, химических и температурных воздействий. Под эмалью расположен дентин, который более мягкий по своей структуре и пронизан множеством канальцев. При повреждении эмали происходит оголение дентинных канальцев. Раздражение с них начинает передаваться на нервные окончания в зубе и возникают болевые ощущения. Чаще всего дентин оголяется в придесневой области зубов, поскольку эмаль там наиболее тонкая и стирается быстрее.", "Стоматолог, также известный как стоматолог-хирург, является медицинским работником, который специализируется на стоматологии, отрасли медицины, специализирующейся на зубах, деснах и полости рта.", "Дядя Женя работает врачем стоматологом", "Плоды малины употребляют как свежими, так и замороженными или используют для приготовления варенья, желе, мармелада, соков, а также ягодного пюре. Малиновые вина, наливки, настойки, ликёры обладают высокими вкусовыми качествами.", ] predict_result = reranker_model.predict([[query[0], documents[0]]]) print(predict_result) # `array([0.88126713], dtype=float32)` rank_result = reranker_model.rank(query[0], documents) print(rank_result) # `[{'corpus_id': 0, 'score': 0.88126713}, # {'corpus_id': 2, 'score': 0.001042091}, # {'corpus_id': 3, 'score': 0.0010417715}, # {'corpus_id': 1, 'score': 0.0010344835}, # {'corpus_id': 4, 'score': 0.0010244923}]` ``` ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python import torch from transformers import AutoTokenizer, AutoModelForSequenceClassification model = AutoModelForSequenceClassification.from_pretrained('DiTy/cross-encoder-russian-msmarco') tokenizer = AutoTokenizer.from_pretrained('DiTy/cross-encoder-russian-msmarco') features = tokenizer(["как часто нужно ходить к стоматологу?", "как часто нужно ходить к стоматологу?"], ["Минимальный обязательный срок посещения зубного врача – раз в год, но специалисты рекомендуют делать это чаще – раз в полгода, а ещё лучше – раз в квартал. При таком сроке легко отследить любые начинающиеся проблемы и исправить их сразу же.", "Дядя Женя работает врачем стоматологом"], padding=True, truncation=True, return_tensors='pt') model.eval() with torch.no_grad(): scores = model(**features).logits print(scores) # `tensor([[ 1.6871], # [-6.8700]])` ```

timm/deit3_small_patch16_224.fb_in1k

timm

"2024-02-10T23:37:09Z"

2,601

0

timm

[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-1k", "arxiv:2204.07118", "license:apache-2.0", "region:us" ]

image-classification

"2023-03-28T01:26:30Z"

--- license: apache-2.0 library_name: timm tags: - image-classification - timm datasets: - imagenet-1k --- # Model card for deit3_small_patch16_224.fb_in1k A DeiT-III image classification model. Trained on ImageNet-1k by paper authors. ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 22.1 - GMACs: 4.6 - Activations (M): 11.9 - Image size: 224 x 224 - **Papers:** - DeiT III: Revenge of the ViT: https://arxiv.org/abs/2204.07118 - **Original:** https://github.com/facebookresearch/deit - **Dataset:** ImageNet-1k ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('deit3_small_patch16_224.fb_in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'deit3_small_patch16_224.fb_in1k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 197, 384) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Model Comparison Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results). ## Citation ```bibtex @article{Touvron2022DeiTIR, title={DeiT III: Revenge of the ViT}, author={Hugo Touvron and Matthieu Cord and Herve Jegou}, journal={arXiv preprint arXiv:2204.07118}, year={2022}, } ``` ```bibtex @misc{rw2019timm, author = {Ross Wightman}, title = {PyTorch Image Models}, year = {2019}, publisher = {GitHub}, journal = {GitHub repository}, doi = {10.5281/zenodo.4414861}, howpublished = {\url{https://github.com/huggingface/pytorch-image-models}} } ```

cactusfriend/nightmare-invokeai-prompts

cactusfriend

"2023-06-22T00:48:13Z"

2,600

6

transformers

[ "transformers", "pytorch", "safetensors", "gpt_neo", "text-generation", "license:openrail", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-generation

"2023-04-02T15:30:11Z"

--- license: openrail pipeline_tag: text-generation library_name: transformers widget: - text: "a photograph of" example_title: "photo" - text: "a bizarre cg render" example_title: "render" - text: "the spaghetti" example_title: "meal?" - text: "a (detailed+ intricate)+ picture" example_title: "weights" - text: "photograph of various" example_title: "variety" inference: parameters: temperature: 2.6 max_new_tokens: 250 --- A model based upon the prompts of all the images in my InvokeAI's output directory, meant to be used with [InvokeAI](https://github.com/invoke-ai/InvokeAI) (a Stable Diffusion implementation/UI) to generate new, probably wild nightmare images. This is mostly trained on positive prompts, though you may catch some words in [] brackets, which will be treated as negative. GPT-Neo is usually quite good at pairing parenthesis, quotation marks, etc - however, don't be too surprised if it generates something that's not quite InvokeAI prompt syntax. To use this model, you can import it as a pipeline like so: ```py from transformers import pipeline generator = pipeline(model="cactusfriend/nightmare-invokeai-prompts", tokenizer="cactusfriend/nightmare-invokeai-prompts", task="text-generation") ``` Here's an example function that'll generate by default 20 prompts, at a temperature of 1.8 which seems good for this model. ```py def makePrompts(prompt: str, *, p: float=0.9, k: int = 40, num: int = 20, temp: float = 1.8, mnt: int = 150): outputs = generator(prompt, max_new_tokens=mnt, temperature=temp, do_sample=True, top_p=p, top_k=k, num_return_sequences=num) items = set([i['generated_text'] for i in outputs]) print("-" * 60) print("\n ---\n".join(items)) print("-" * 60) ``` Then, you can call it like so: ```py makePrompts("a photograph of") # or, to change some defaults: makePrompts("spaghetti all over", temp=1.4, p=0.92, k=45) ```

neuralmagic/Meta-Llama-3-8B-Instruct-FP8

neuralmagic

"2024-06-26T13:19:38Z"

2,599

4

transformers

[ "transformers", "safetensors", "llama", "text-generation", "fp8", "vllm", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2024-04-25T19:13:07Z"

--- tags: - fp8 - vllm --- # Meta-Llama-3-8B-Instruct-FP8 ## Model Overview Meta-Llama-3-8B-Instruct quantized to FP8 weights and activations using per-tensor quantization, ready for inference with vLLM >= 0.5.0. ## Usage and Creation Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py). ## Evaluation ### Open LLM Leaderboard evaluation scores | | Meta-Llama-3-8B-Instruct | Meta-Llama-3-8B-Instruct-FP8<br>(this model) | | :------------------: | :----------------------: | :------------------------------------------------: | | arc-c<br>25-shot | 62.54 | 61.77 | | hellaswag<br>10-shot | 78.83 | 78.56 | | mmlu<br>5-shot | 66.60 | 66.27 | | truthfulqa<br>0-shot | 52.44 | 52.35 | | winogrande<br>5-shot | 75.93 | 76.4 | | gsm8k<br>5-shot | 75.96 | 73.99 | | **Average<br>Accuracy** | **68.71** | **68.22** | | **Recovery** | **100%** | **99.28%** |

QuantFactory/Ahma-7B-GGUF

QuantFactory

"2024-06-09T02:42:23Z"

2,599

0

null

[ "gguf", "finnish", "llama", "conversational", "text-generation", "fi", "base_model:Finnish-NLP/Ahma-7B", "license:apache-2.0", "region:us" ]

text-generation

"2024-06-09T01:42:16Z"

--- pipeline_tag: text-generation base_model: Finnish-NLP/Ahma-7B license: apache-2.0 language: - fi tags: - finnish - llama - conversational --- # QuantFactory/Ahma-7B-GGUF This is quantized version of [Finnish-NLP/Ahma-7B](https://huggingface.co/Finnish-NLP/Ahma-7B) created using llama.cpp

mradermacher/horror_tinyllama-GGUF

mradermacher

"2024-07-01T15:39:54Z"

2,599

0

transformers

[ "transformers", "gguf", "en", "base_model:ShehryarAzhar/horror_tinyllama", "endpoints_compatible", "region:us" ]

null

"2024-07-01T14:44:11Z"

--- base_model: ShehryarAzhar/horror_tinyllama language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About      static quants of https://huggingface.co/ShehryarAzhar/horror_tinyllama  weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q2_K.gguf) | Q2_K | 0.5 | | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.IQ3_XS.gguf) | IQ3_XS | 0.6 | | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q3_K_S.gguf) | Q3_K_S | 0.6 | | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.IQ3_S.gguf) | IQ3_S | 0.6 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.IQ3_M.gguf) | IQ3_M | 0.6 | | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q3_K_L.gguf) | Q3_K_L | 0.7 | | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.IQ4_XS.gguf) | IQ4_XS | 0.7 | | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q5_K_S.gguf) | Q5_K_S | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q5_K_M.gguf) | Q5_K_M | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q6_K.gguf) | Q6_K | 1.0 | very good quality | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/horror_tinyllama-GGUF/resolve/main/horror_tinyllama.f16.gguf) | f16 | 2.3 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

mradermacher/Llama-3SOME-8B-v2b-GGUF

mradermacher

"2024-06-05T21:18:54Z"

2,598

0

transformers

[ "transformers", "gguf", "en", "base_model:BeaverAI/Llama-3SOME-8B-v2b", "endpoints_compatible", "region:us" ]

null

"2024-06-05T20:49:07Z"

--- base_model: BeaverAI/Llama-3SOME-8B-v2b language: - en library_name: transformers quantized_by: mradermacher --- ## About      static quants of https://huggingface.co/BeaverAI/Llama-3SOME-8B-v2b  weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3SOME-8B-v2b-GGUF/resolve/main/Llama-3SOME-8B-v2b.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

utrobinmv/t5_translate_en_ru_zh_small_1024

utrobinmv

"2024-05-17T09:22:08Z"

2,596

7

transformers

[ "transformers", "safetensors", "t5", "text2text-generation", "translation", "ru", "zh", "en", "dataset:ccmatrix", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

translation

"2024-01-07T14:33:20Z"

--- language: - ru - zh - en tags: - translation license: apache-2.0 datasets: - ccmatrix metrics: - sacrebleu widget: - example_title: translate zh-ru text: > translate to ru: 开发的目的是为用户提供个人同步翻译。 - example_title: translate ru-en text: > translate to en: Цель разработки — предоставить пользователям личного синхронного переводчика. - example_title: translate en-ru text: > translate to ru: The purpose of the development is to provide users with a personal synchronized interpreter. - example_title: translate en-zh text: > translate to zh: The purpose of the development is to provide users with a personal synchronized interpreter. - example_title: translate zh-en text: > translate to en: 开发的目的是为用户提供个人同步解释器。 - example_title: translate ru-zh text: > translate to zh: Цель разработки — предоставить пользователям личного синхронного переводчика. --- # T5 English, Russian and Chinese multilingual machine translation This model represents a conventional T5 transformer in multitasking mode for translation into the required language, precisely configured for machine translation for pairs: ru-zh, zh-ru, en-zh, zh-en, en-ru, ru-en. The model can perform direct translation between any pair of Russian, Chinese or English languages. For translation into the target language, the target language identifier is specified as a prefix 'translate to <lang>:'. In this case, the source language may not be specified, in addition, the source text may be multilingual. Example translate Russian to Chinese ```python from transformers import T5ForConditionalGeneration, T5Tokenizer device = 'cuda' #or 'cpu' for translate on cpu model_name = 'utrobinmv/t5_translate_en_ru_zh_small_1024' model = T5ForConditionalGeneration.from_pretrained(model_name) model.to(device) tokenizer = T5Tokenizer.from_pretrained(model_name) prefix = 'translate to zh: ' src_text = prefix + "Цель разработки — предоставить пользователям личного синхронного переводчика." # translate Russian to Chinese input_ids = tokenizer(src_text, return_tensors="pt") generated_tokens = model.generate(**input_ids.to(device)) result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True) print(result) #开发的目的就是向用户提供个性化的同步翻译。 ``` and Example translate Chinese to Russian ```python from transformers import T5ForConditionalGeneration, T5Tokenizer device = 'cuda' #or 'cpu' for translate on cpu model_name = 'utrobinmv/t5_translate_en_ru_zh_small_1024' model = T5ForConditionalGeneration.from_pretrained(model_name) model.to(device) tokenizer = T5Tokenizer.from_pretrained(model_name) prefix = 'translate to ru: ' src_text = prefix + "开发的目的就是向用户提供个性化的同步翻译。" # translate Russian to Chinese input_ids = tokenizer(src_text, return_tensors="pt") generated_tokens = model.generate(**input_ids.to(device)) result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True) print(result) #Цель разработки - предоставить персонализированный синхронный перевод для пользователей. ``` ## ## Languages covered Russian (ru_RU), Chinese (zh_CN), English (en_US)

digiplay/AgainMix_v2.0

digiplay

"2024-03-19T04:44:54Z"

2,595

2

diffusers

[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

"2024-03-17T13:01:10Z"

--- license: other tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers inference: true --- Model info: https://civitai.com/models/167100?modelVersionId=375171 DEMO image generated by huggingface's API : ![36a51dc0-a7da-4a1c-a31b-030bd49e928e.jpeg](https://cdn-uploads.huggingface.co/production/uploads/646c83c871d0c8a6e4455854/V-wLx2YFxZVTadLdBjAvc.jpeg) (8k UHD RAW,photorealistic,realistic:3) ,blonde wavy hair beautiful 21y.o girl,lake,close-up,photo,professional photograph,Canon 50mm,ultra-detailed,Leonardo Mucha,1990s,sharp focus,thin,extremely detailed ,(oil paint :-3),light and shadow,cinematic lighting ,Angel wings,

RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf

RichardErkhov

"2024-06-22T23:39:54Z"

2,595

0

null

[ "gguf", "region:us" ]

null

"2024-06-22T23:28:36Z"

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) TinyDolphin-2.8-1.1b - GGUF - Model creator: https://huggingface.co/cognitivecomputations/ - Original model: https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b/ | Name | Quant method | Size | | ---- | ---- | ---- | | [TinyDolphin-2.8-1.1b.Q2_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q2_K.gguf) | Q2_K | 0.4GB | | [TinyDolphin-2.8-1.1b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ3_XS.gguf) | IQ3_XS | 0.44GB | | [TinyDolphin-2.8-1.1b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ3_S.gguf) | IQ3_S | 0.47GB | | [TinyDolphin-2.8-1.1b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q3_K_S.gguf) | Q3_K_S | 0.47GB | | [TinyDolphin-2.8-1.1b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ3_M.gguf) | IQ3_M | 0.48GB | | [TinyDolphin-2.8-1.1b.Q3_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q3_K.gguf) | Q3_K | 0.51GB | | [TinyDolphin-2.8-1.1b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q3_K_M.gguf) | Q3_K_M | 0.51GB | | [TinyDolphin-2.8-1.1b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q3_K_L.gguf) | Q3_K_L | 0.55GB | | [TinyDolphin-2.8-1.1b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ4_XS.gguf) | IQ4_XS | 0.57GB | | [TinyDolphin-2.8-1.1b.Q4_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_0.gguf) | Q4_0 | 0.59GB | | [TinyDolphin-2.8-1.1b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.IQ4_NL.gguf) | IQ4_NL | 0.6GB | | [TinyDolphin-2.8-1.1b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_K_S.gguf) | Q4_K_S | 0.6GB | | [TinyDolphin-2.8-1.1b.Q4_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_K.gguf) | Q4_K | 0.62GB | | [TinyDolphin-2.8-1.1b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_K_M.gguf) | Q4_K_M | 0.62GB | | [TinyDolphin-2.8-1.1b.Q4_1.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q4_1.gguf) | Q4_1 | 0.65GB | | [TinyDolphin-2.8-1.1b.Q5_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_0.gguf) | Q5_0 | 0.71GB | | [TinyDolphin-2.8-1.1b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_K_S.gguf) | Q5_K_S | 0.71GB | | [TinyDolphin-2.8-1.1b.Q5_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_K.gguf) | Q5_K | 0.73GB | | [TinyDolphin-2.8-1.1b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_K_M.gguf) | Q5_K_M | 0.73GB | | [TinyDolphin-2.8-1.1b.Q5_1.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q5_1.gguf) | Q5_1 | 0.77GB | | [TinyDolphin-2.8-1.1b.Q6_K.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q6_K.gguf) | Q6_K | 0.84GB | | [TinyDolphin-2.8-1.1b.Q8_0.gguf](https://huggingface.co/RichardErkhov/cognitivecomputations_-_TinyDolphin-2.8-1.1b-gguf/blob/main/TinyDolphin-2.8-1.1b.Q8_0.gguf) | Q8_0 | 1.09GB | Original model description: --- license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata - teknium/openhermes language: - en --- # TinyDolphin-2.8-1.1b ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/655dc641accde1bbc8b41aec/qUCZv8vxXDXi9r-9c0jvP.jpeg) [![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/cognitivecomputations) Discord: https://discord.gg/cognitivecomputations This is an experimental model trained on 2 3090's by Kearm on the new Dolphin 2.8 dataset by Eric Hartford https://erichartford.com/dolphin 🐬 ## Example Outputs Invent a sinister prank involving teleportation that leaves the victim utterly confused. ``` As you requested, here's how I would go about creating this sinister prank: First, we need to find a location where teleportation is possible. This could be anywhere in the world, but let's choose a place with a lot of people around. For example, a crowded street or a busy park. Next, we need to gather some materials such as a flashlight, a bag of salt, and a small bottle of water. These items are essential for making the prank work. Now, we need to carefully position ourselves near the chosen location. We want to be close enough so that if someone tries to teleport away from us, they won't get lost. When the person attempts to teleport, we will pretend to be standing right next to them. This will make it look like they were teleported without our knowing. With the flashlight, we will light up the area around us. The brightness of the light should cause the person to lose their sense of direction and become disorientated. Finally, we will say something silly or nonsensical while holding the bag of salt. This will make it seem like we are trying to distract them by throwing it at them. When the person finally loses their way, we will disappear into thin air. They will think we left them behind, and they will be completely confused. ``` Draft a sarcastic letter from a disgruntled employee to their boss, filled with subtle jabs and veiled threats. ``` Dear [Boss], I hope this message finds you in good health and high spirits. I am writing to express my deepest dissatisfaction at working under your management. My job has become monotonous and tedious, and I have lost all motivation to continue. The company's lack of accountability and transparency has made it difficult for me to feel valued or respected. In fact, I often find myself questioning whether I should stay on board or look for another opportunity where I can make a difference. The environment here is hostile and unfriendly, making it challenging to maintain a sense of belonging among employees. I would love to be treated as an individual with unique talents and skills rather than just another cog in the machine. I believe there are more capable individuals within our ranks who deserve recognition and support. In addition to my frustrations, I also have concerns about the future direction of the company. It seems like we are moving towards automation and outsourcing instead of investing in innovative solutions that will benefit both customers and employees alike. This approach does not align well with my personal values and beliefs. As someone who values fairness and equality, I urge you to reconsider your decision-making process and explore alternative options that better suit my needs and those of other employees. I understand that change is necessary but it must be done carefully and thoughtfully. Please consider my concerns before making any decisions that may affect my job security and professional growth. Thank you for your time and consideration. I look forward to discussing these matters further when we meet next. Sincerely, [Your Name] ``` Construct a poem describing the rise and rule of succesful malevolent king who ruled through fear and manipulation. ``` In his reign, he ruled with ease, his every move dictated by fear. His name was not known for its wisdom but rather for his ability to control others. He had a dark heart, consumed by malice and power. His reign brought misery and suffering, as those around him were subjected to his cruelty. His oppression was unmatched, as he held people in check without mercy. Yet, despite all this, he remained invincible, his rule never faltering. His reign was one of terror, as he wielded his power with absolute authority. His subjects lived in fear, knowing they could be executed at any moment. Yet, they submitted, oblivious to their plight. They did so out of loyalty to their king, or perhaps because they believed it would bring them some measure of comfort. Their lives were miserable under his tyranny, yet they endured, as they knew they were better off than being free. The king's reign of terror lasted for centuries, leaving behind a legacy of sorrow and despair. ``` Support my efforts! ko-fi.com/kearm # Orignal Model Card Below # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Collection This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen. #### Eval | Model | Pretrain Tokens | HellaSwag | Obqa | WinoGrande | ARC_c | ARC_e | boolq | piqa | avg | |-------------------------------------------|-----------------|-----------|------|------------|-------|-------|-------|------|-----| | Pythia-1.0B | 300B | 47.16 | 31.40| 53.43 | 27.05 | 48.99 | 60.83 | 69.21 | 48.30 | | TinyLlama-1.1B-intermediate-step-50K-104b | 103B | 43.50 | 29.80| 53.28 | 24.32 | 44.91 | 59.66 | 67.30 | 46.11| | TinyLlama-1.1B-intermediate-step-240k-503b| 503B | 49.56 |31.40 |55.80 |26.54 |48.32 |56.91 |69.42 | 48.28 | | TinyLlama-1.1B-intermediate-step-480k-1007B | 1007B | 52.54 | 33.40 | 55.96 | 27.82 | 52.36 | 59.54 | 69.91 | 50.22 | | TinyLlama-1.1B-intermediate-step-715k-1.5T | 1.5T | 53.68 | 35.20 | 58.33 | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 | | TinyLlama-1.1B-intermediate-step-955k-2T | 2T | 54.63 | 33.40 | 56.83 | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 | | TinyLlama-1.1B-intermediate-step-1195k-2.5T | 2.5T | 58.96 | 34.40 | 58.72 | 31.91 | 56.78 | 63.21 | 73.07 | 53.86| | TinyLlama-1.1B-intermediate-step-1431k-3T | 3T | 59.20 | 36.00 | 59.12 | 30.12 | 55.25 | 57.83 | 73.29 | 52.99|

nreimers/albert-small-v2

nreimers

"2021-05-31T12:26:52Z"

2,594

0

transformers

[ "transformers", "pytorch", "albert", "feature-extraction", "endpoints_compatible", "region:us" ]

feature-extraction

"2022-03-02T23:29:05Z"

# albert-small-v2 This is a 6 layer version of [albert-base-v2](https://huggingface.co/albert-base-v2).

4bit/llava-v1.5-7b

4bit

"2023-10-07T09:32:49Z"

2,594

0

transformers

[ "transformers", "pytorch", "llava", "text-generation", "autotrain_compatible", "region:us" ]

text-generation

"2023-10-07T09:25:42Z"

--- inference: false --- <br> <br> # LLaVA Model Card ## Model details **Model type:** LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. **Model date:** LLaVA-v1.5-7B was trained in September 2023. **Paper or resources for more information:** https://llava-vl.github.io/ ## License Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. **Where to send questions or comments about the model:** https://github.com/haotian-liu/LLaVA/issues ## Intended use **Primary intended uses:** The primary use of LLaVA is research on large multimodal models and chatbots. **Primary intended users:** The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence. ## Training dataset - 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP. - 158K GPT-generated multimodal instruction-following data. - 450K academic-task-oriented VQA data mixture. - 40K ShareGPT data. ## Evaluation dataset A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.

hfl/chinese-alpaca-2-7b-64k-gguf

hfl

"2024-01-24T03:03:15Z"

2,594

5

null

[ "gguf", "zh", "en", "license:apache-2.0", "region:us" ]

null

"2023-12-23T07:12:33Z"

--- license: apache-2.0 language: - zh - en --- # Chinese-Alpaca-2-7B-64K This repository contains GGUF-v3 version (llama.cpp compatible) of **Chinese-Alpaca-2-7B-64K**, which is tuned on Chinese-Alpaca-2-7B with **YaRN method**. ## Performance Metric: PPL, lower is better | Quant | original | imatrix (`-im`) | |-----|------|------| | Q2_K | 9.8201 +/- 0.13298 | 10.3057 +/- 0.14197 | | Q3_K | 8.4435 +/- 0.11467 | 8.3556 +/- 0.11316 | | Q4_0 | 8.3573 +/- 0.11496 | - | | Q4_K | 8.0558 +/- 0.10948 | 8.0557 +/- 0.10964 | | Q5_0 | 8.0220 +/- 0.10954 | - | | Q5_K | 7.9388 +/- 0.10802 | 7.9440 +/- 0.10815 | | Q6_K | 7.9267 +/- 0.10792 | 7.9126 +/- 0.10775 | | Q8_0 | 7.9117 +/- 0.10773 | - | | F16 | 7.9124 +/- 0.10780 | - | *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).* ## Others For full model in HuggingFace format, please see: https://huggingface.co/hfl/chinese-alpaca-2-7b-64k Please refer to [https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/) for more details.

TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF

TheBloke

"2024-01-16T20:39:50Z"

2,594

25

transformers

[ "transformers", "gguf", "mixtral", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "en", "base_model:NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT", "license:apache-2.0", "text-generation-inference", "region:us" ]

null

"2024-01-16T20:20:01Z"

--- base_model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT inference: false language: - en license: apache-2.0 model-index: - name: Nous-Hermes-2-Mixtral-8x7B-SFT results: [] model_creator: NousResearch model_name: Nous Hermes 2 Mixtral 8X7B SFT model_type: mixtral prompt_template: '<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ' quantized_by: TheBloke tags: - Mixtral - instruct - finetune - chatml - DPO - RLHF - gpt4 - synthetic data - distillation ---    <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">  # Nous Hermes 2 Mixtral 8X7B SFT - GGUF - Model creator: [NousResearch](https://huggingface.co/NousResearch) - Original model: [Nous Hermes 2 Mixtral 8X7B SFT](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT)  ## Description This repo contains GGUF format model files for [NousResearch's Nous Hermes 2 Mixtral 8X7B SFT](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT). These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).   ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.   ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF) * [NousResearch's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT)   ## Prompt template: ChatML ``` <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ```   ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details>   ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [nous-hermes-2-mixtral-8x7b-sft.Q2_K.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q2_K.gguf) | Q2_K | 2 | 17.31 GB| 19.81 GB | significant quality loss - not recommended for most purposes | | [nous-hermes-2-mixtral-8x7b-sft.Q3_K_M.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q3_K_M.gguf) | Q3_K_M | 3 | 22.54 GB| 25.04 GB | very small, high quality loss | | [nous-hermes-2-mixtral-8x7b-sft.Q4_0.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q4_0.gguf) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf) | Q4_K_M | 4 | 28.45 GB| 30.95 GB | medium, balanced quality - recommended | | [nous-hermes-2-mixtral-8x7b-sft.Q5_0.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q5_0.gguf) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [nous-hermes-2-mixtral-8x7b-sft.Q5_K_M.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q5_K_M.gguf) | Q5_K_M | 5 | 33.23 GB| 35.73 GB | large, very low quality loss - recommended | | [nous-hermes-2-mixtral-8x7b-sft.Q6_K.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q6_K.gguf) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss | | [nous-hermes-2-mixtral-8x7b-sft.Q8_0.gguf](https://huggingface.co/TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF/blob/main/nous-hermes-2-mixtral-8x7b-sft.Q8_0.gguf) | Q8_0 | 8 | 49.62 GB| 52.12 GB | very large, extremely low quality loss - not recommended | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.   ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF and below it, a specific filename to download, such as: nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details>   ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./nous-hermes-2-mixtral-8x7b-sft.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)    ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant.   # Original model card: NousResearch's Nous Hermes 2 Mixtral 8X7B SFT # Nous Hermes 2 - Mixtral 8x7B - SFT ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/btRmXWMG7PXatTs-u3G85.jpeg) ## Model description Nous Hermes 2 Mixtral 8x7B SFT is the supervised finetune only version of our new flagship Nous Research model trained over the [Mixtral 8x7B MoE LLM](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1). The model was trained on over 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape, achieving state of the art performance on a variety of tasks. This is the SFT only version of Mixtral Hermes 2, we have also released an SFT+DPO version, for people to find which works best for them, which can be found here: https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO ## We are grateful to Together.ai for sponsoring our compute during the many experiments both training Mixtral and working on DPO! # Table of Contents 1. [Example Outputs](#example-outputs) 2. [Benchmark Results](#benchmark-results) - GPT4All - AGIEval - BigBench - Comparison to Mixtral-Instruct 3. [Prompt Format](#prompt-format) 4. [Inference Example Code](#inference-code) 5. [Quantized Models](#quantized-models) ## Example Outputs ### Writing Code for Data Visualization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/QJ5RHrOqB5GMP7ZAZ5NTk.png) ### Writing Cyberpunk Psychedelic Poems ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/wuKnMlM2HBGdyUFO7mY_H.png) ### Performing Backtranslation to Create Prompts from Input Text ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/QElwK1UI9PQQT6WosXpo1.png) ## Benchmark Results Nous-Hermes 2 on Mixtral 8x7B SFT is the bedrock for major improvements on many of the benchmarks below compared to the base Mixtral model, and is the SFT only version of our first model to beat the flagship Mixtral Finetune by MistralAI (the DPO version). ## GPT4All: ``` | Task |Version| Metric |Value | |Stderr| |-------------|------:|--------|-----:|---|-----:| |arc_challenge| 0|acc |0.5904|± |0.0144| | | |acc_norm|0.6323|± |0.0141| |arc_easy | 0|acc |0.8594|± |0.0071| | | |acc_norm|0.8607|± |0.0071| |boolq | 1|acc |0.8783|± |0.0057| |hellaswag | 0|acc |0.6592|± |0.0047| | | |acc_norm|0.8434|± |0.0036| |openbookqa | 0|acc |0.3400|± |0.0212| | | |acc_norm|0.4660|± |0.0223| |piqa | 0|acc |0.8324|± |0.0087| | | |acc_norm|0.8379|± |0.0086| |winogrande | 0|acc |0.7569|± |0.0121| ``` Average: 75.36 ## AGIEval: ``` | Task |Version| Metric |Value | |Stderr| |------------------------------|------:|--------|-----:|---|-----:| |agieval_aqua_rat | 0|acc |0.2441|± |0.0270| | | |acc_norm|0.2598|± |0.0276| |agieval_logiqa_en | 0|acc |0.4025|± |0.0192| | | |acc_norm|0.3978|± |0.0192| |agieval_lsat_ar | 0|acc |0.2391|± |0.0282| | | |acc_norm|0.2043|± |0.0266| |agieval_lsat_lr | 0|acc |0.5353|± |0.0221| | | |acc_norm|0.5098|± |0.0222| |agieval_lsat_rc | 0|acc |0.6617|± |0.0289| | | |acc_norm|0.5948|± |0.0300| |agieval_sat_en | 0|acc |0.7961|± |0.0281| | | |acc_norm|0.7816|± |0.0289| |agieval_sat_en_without_passage| 0|acc |0.4757|± |0.0349| | | |acc_norm|0.4515|± |0.0348| |agieval_sat_math | 0|acc |0.4818|± |0.0338| | | |acc_norm|0.3909|± |0.0330| ``` Average: 44.89 ## BigBench: ``` | Task |Version| Metric |Value | |Stderr| |------------------------------------------------|------:|---------------------|-----:|---|-----:| |bigbench_causal_judgement | 0|multiple_choice_grade|0.5789|± |0.0359| |bigbench_date_understanding | 0|multiple_choice_grade|0.7154|± |0.0235| |bigbench_disambiguation_qa | 0|multiple_choice_grade|0.5388|± |0.0311| |bigbench_geometric_shapes | 0|multiple_choice_grade|0.4680|± |0.0264| | | |exact_str_match |0.0000|± |0.0000| |bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.3260|± |0.0210| |bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2443|± |0.0163| |bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.5233|± |0.0289| |bigbench_movie_recommendation | 0|multiple_choice_grade|0.3700|± |0.0216| |bigbench_navigate | 0|multiple_choice_grade|0.5000|± |0.0158| |bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.6665|± |0.0105| |bigbench_ruin_names | 0|multiple_choice_grade|0.6317|± |0.0228| |bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2505|± |0.0137| |bigbench_snarks | 0|multiple_choice_grade|0.7127|± |0.0337| |bigbench_sports_understanding | 0|multiple_choice_grade|0.6592|± |0.0151| |bigbench_temporal_sequences | 0|multiple_choice_grade|0.6860|± |0.0147| |bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2200|± |0.0117| |bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1503|± |0.0085| |bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.5233|± |0.0289| ``` Average: 48.69 # Benchmark Comparison Charts ## GPT4All ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/S3_tdH822r9UvkGFDiYam.png) ## AGI-Eval ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/paet9FsASWPWa6KJs3mm-.png) ## BigBench Reasoning Test ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/rHmkUnYLTWwq0cuVzMegL.png) # Prompt Format Nous Hermes 2 uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model. This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns. This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI. Prompt with system instruction (Use whatever system prompt you like, this is just an example!): ``` <|im_start|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|> <|im_start|>user Hello, who are you?<|im_end|> <|im_start|>assistant Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<|im_end|> ``` This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the `tokenizer.apply_chat_template()` method: ```python messages = [ {"role": "system", "content": "You are Hermes 2."}, {"role": "user", "content": "Hello, who are you?"} ] gen_input = tokenizer.apply_chat_template(message, return_tensors="pt") model.generate(**gen_input) ``` When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure that the model continues with an assistant response. To utilize the prompt format without a system prompt, simply leave the line out. When quantized versions of the model are released, I recommend using LM Studio for chatting with Nous Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box. In LM-Studio, simply select the ChatML Prefix on the settings side pane: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png) # Inference Code Here is example code using HuggingFace Transformers to inference the model (note: even in 4bit, it will require more than 24GB of VRAM) ```python # Code to inference Hermes with HF Transformers # Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages import torch from transformers import AutoTokenizer, AutoModelForCausalLM from transformers import LlamaTokenizer, MixtralForCausalLM import bitsandbytes, flash_attn tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', trust_remote_code=True) model = MixtralForCausalLM.from_pretrained( "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", torch_dtype=torch.float16, device_map="auto", load_in_8bit=False, load_in_4bit=True, use_flash_attention_2=True ) prompts = [ """<|im_start|>system You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> <|im_start|>user Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|> <|im_start|>assistant""", ] for chat in prompts: print(chat) input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda") generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id) response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True) print(f"Response: {response}") ``` # Quantized Models: ## All sizes of GGUF Quantizations are available here: ### SFT+DPO Version - https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO-GGUF ### SFT Only Version - https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf

RichardErkhov

"2024-06-17T00:33:52Z"

2,594

0

null

[ "gguf", "region:us" ]

null

"2024-06-16T23:06:11Z"

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Med-Yi-1.5-9B - GGUF - Model creator: https://huggingface.co/NotAiLOL/ - Original model: https://huggingface.co/NotAiLOL/Med-Yi-1.5-9B/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Med-Yi-1.5-9B.Q2_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q2_K.gguf) | Q2_K | 3.12GB | | [Med-Yi-1.5-9B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ3_XS.gguf) | IQ3_XS | 3.46GB | | [Med-Yi-1.5-9B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ3_S.gguf) | IQ3_S | 3.64GB | | [Med-Yi-1.5-9B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q3_K_S.gguf) | Q3_K_S | 3.63GB | | [Med-Yi-1.5-9B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ3_M.gguf) | IQ3_M | 3.78GB | | [Med-Yi-1.5-9B.Q3_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q3_K.gguf) | Q3_K | 4.03GB | | [Med-Yi-1.5-9B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q3_K_M.gguf) | Q3_K_M | 4.03GB | | [Med-Yi-1.5-9B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q3_K_L.gguf) | Q3_K_L | 4.37GB | | [Med-Yi-1.5-9B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ4_XS.gguf) | IQ4_XS | 4.5GB | | [Med-Yi-1.5-9B.Q4_0.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_0.gguf) | Q4_0 | 4.69GB | | [Med-Yi-1.5-9B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.IQ4_NL.gguf) | IQ4_NL | 4.73GB | | [Med-Yi-1.5-9B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_K_S.gguf) | Q4_K_S | 4.72GB | | [Med-Yi-1.5-9B.Q4_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_K.gguf) | Q4_K | 4.96GB | | [Med-Yi-1.5-9B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_K_M.gguf) | Q4_K_M | 4.96GB | | [Med-Yi-1.5-9B.Q4_1.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q4_1.gguf) | Q4_1 | 5.19GB | | [Med-Yi-1.5-9B.Q5_0.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_0.gguf) | Q5_0 | 5.69GB | | [Med-Yi-1.5-9B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_K_S.gguf) | Q5_K_S | 5.69GB | | [Med-Yi-1.5-9B.Q5_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_K.gguf) | Q5_K | 5.83GB | | [Med-Yi-1.5-9B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_K_M.gguf) | Q5_K_M | 5.83GB | | [Med-Yi-1.5-9B.Q5_1.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q5_1.gguf) | Q5_1 | 6.19GB | | [Med-Yi-1.5-9B.Q6_K.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q6_K.gguf) | Q6_K | 6.75GB | | [Med-Yi-1.5-9B.Q8_0.gguf](https://huggingface.co/RichardErkhov/NotAiLOL_-_Med-Yi-1.5-9B-gguf/blob/main/Med-Yi-1.5-9B.Q8_0.gguf) | Q8_0 | 8.74GB | Original model description: --- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl - sft base_model: 01-ai/Yi-1.5-9B datasets: - Kabatubare/medical-alpaca --- # Uploaded model - **Developed by:** NotAiLOL - **License:** apache-2.0 - **Finetuned from model :** 01-ai/Yi-1.5-9B This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) # Model detail ## Prompt format The model uses the alpaca format: ``` Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: {} ### Input: {} ### Response: {} ```

CAiRE/UniVaR-lambda-20

CAiRE

"2024-06-14T17:57:05Z"

2,593

0

sentence-transformers

[ "sentence-transformers", "safetensors", "nomic_bert", "feature-extraction", "sentence-similarity", "mteb", "transformers", "transformers.js", "custom_code", "en", "arxiv:2402.01613", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-embeddings-inference", "region:us" ]

sentence-similarity

"2024-06-14T17:56:33Z"

--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - feature-extraction - sentence-similarity - mteb - transformers - transformers.js model-index: - name: epoch_0_model results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 76.8507462686567 - type: ap value: 40.592189159090495 - type: f1 value: 71.01634655512476 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 91.51892500000001 - type: ap value: 88.50346762975335 - type: f1 value: 91.50342077459624 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 47.364 - type: f1 value: 46.72708080922794 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 25.178 - type: map_at_10 value: 40.244 - type: map_at_100 value: 41.321999999999996 - type: map_at_1000 value: 41.331 - type: map_at_3 value: 35.016999999999996 - type: map_at_5 value: 37.99 - type: mrr_at_1 value: 25.605 - type: mrr_at_10 value: 40.422000000000004 - type: mrr_at_100 value: 41.507 - type: mrr_at_1000 value: 41.516 - type: mrr_at_3 value: 35.23 - type: mrr_at_5 value: 38.15 - type: ndcg_at_1 value: 25.178 - type: ndcg_at_10 value: 49.258 - type: ndcg_at_100 value: 53.776 - type: ndcg_at_1000 value: 53.995000000000005 - type: ndcg_at_3 value: 38.429 - type: ndcg_at_5 value: 43.803 - type: precision_at_1 value: 25.178 - type: precision_at_10 value: 7.831 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 16.121 - type: precision_at_5 value: 12.29 - type: recall_at_1 value: 25.178 - type: recall_at_10 value: 78.307 - type: recall_at_100 value: 97.866 - type: recall_at_1000 value: 99.57300000000001 - type: recall_at_3 value: 48.364000000000004 - type: recall_at_5 value: 61.451 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 45.93034494751465 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 36.64579480054327 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 60.601310529222054 - type: mrr value: 75.04484896451656 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 88.57797718095814 - type: cos_sim_spearman value: 86.47064499110101 - type: euclidean_pearson value: 87.4559602783142 - type: euclidean_spearman value: 86.47064499110101 - type: manhattan_pearson value: 87.7232764230245 - type: manhattan_spearman value: 86.91222131777742 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 84.5422077922078 - type: f1 value: 84.47657456950589 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 38.48953561974464 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.75995857510105 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.008000000000003 - type: map_at_10 value: 39.51 - type: map_at_100 value: 40.841 - type: map_at_1000 value: 40.973 - type: map_at_3 value: 36.248999999999995 - type: map_at_5 value: 38.096999999999994 - type: mrr_at_1 value: 36.481 - type: mrr_at_10 value: 44.818000000000005 - type: mrr_at_100 value: 45.64 - type: mrr_at_1000 value: 45.687 - type: mrr_at_3 value: 42.036 - type: mrr_at_5 value: 43.782 - type: ndcg_at_1 value: 36.481 - type: ndcg_at_10 value: 45.152 - type: ndcg_at_100 value: 50.449 - type: ndcg_at_1000 value: 52.76499999999999 - type: ndcg_at_3 value: 40.161 - type: ndcg_at_5 value: 42.577999999999996 - type: precision_at_1 value: 36.481 - type: precision_at_10 value: 8.369 - type: precision_at_100 value: 1.373 - type: precision_at_1000 value: 0.186 - type: precision_at_3 value: 18.693 - type: precision_at_5 value: 13.533999999999999 - type: recall_at_1 value: 30.008000000000003 - type: recall_at_10 value: 56.108999999999995 - type: recall_at_100 value: 78.55499999999999 - type: recall_at_1000 value: 93.659 - type: recall_at_3 value: 41.754999999999995 - type: recall_at_5 value: 48.296 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.262 - type: map_at_10 value: 40.139 - type: map_at_100 value: 41.394 - type: map_at_1000 value: 41.526 - type: map_at_3 value: 37.155 - type: map_at_5 value: 38.785 - type: mrr_at_1 value: 38.153 - type: mrr_at_10 value: 46.369 - type: mrr_at_100 value: 47.072 - type: mrr_at_1000 value: 47.111999999999995 - type: mrr_at_3 value: 44.268 - type: mrr_at_5 value: 45.389 - type: ndcg_at_1 value: 38.153 - type: ndcg_at_10 value: 45.925 - type: ndcg_at_100 value: 50.394000000000005 - type: ndcg_at_1000 value: 52.37500000000001 - type: ndcg_at_3 value: 41.754000000000005 - type: ndcg_at_5 value: 43.574 - type: precision_at_1 value: 38.153 - type: precision_at_10 value: 8.796 - type: precision_at_100 value: 1.432 - type: precision_at_1000 value: 0.189 - type: precision_at_3 value: 20.318 - type: precision_at_5 value: 14.395 - type: recall_at_1 value: 30.262 - type: recall_at_10 value: 55.72200000000001 - type: recall_at_100 value: 74.97500000000001 - type: recall_at_1000 value: 87.342 - type: recall_at_3 value: 43.129 - type: recall_at_5 value: 48.336 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 39.951 - type: map_at_10 value: 51.248000000000005 - type: map_at_100 value: 52.188 - type: map_at_1000 value: 52.247 - type: map_at_3 value: 48.211 - type: map_at_5 value: 49.797000000000004 - type: mrr_at_1 value: 45.329 - type: mrr_at_10 value: 54.749 - type: mrr_at_100 value: 55.367999999999995 - type: mrr_at_1000 value: 55.400000000000006 - type: mrr_at_3 value: 52.382 - type: mrr_at_5 value: 53.649 - type: ndcg_at_1 value: 45.329 - type: ndcg_at_10 value: 56.847 - type: ndcg_at_100 value: 60.738 - type: ndcg_at_1000 value: 61.976 - type: ndcg_at_3 value: 51.59 - type: ndcg_at_5 value: 53.915 - type: precision_at_1 value: 45.329 - type: precision_at_10 value: 8.959 - type: precision_at_100 value: 1.187 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 22.612 - type: precision_at_5 value: 15.273 - type: recall_at_1 value: 39.951 - type: recall_at_10 value: 70.053 - type: recall_at_100 value: 86.996 - type: recall_at_1000 value: 95.707 - type: recall_at_3 value: 56.032000000000004 - type: recall_at_5 value: 61.629999999999995 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.566 - type: map_at_10 value: 33.207 - type: map_at_100 value: 34.166000000000004 - type: map_at_1000 value: 34.245 - type: map_at_3 value: 30.94 - type: map_at_5 value: 32.01 - type: mrr_at_1 value: 27.345000000000002 - type: mrr_at_10 value: 35.193000000000005 - type: mrr_at_100 value: 35.965 - type: mrr_at_1000 value: 36.028999999999996 - type: mrr_at_3 value: 32.806000000000004 - type: mrr_at_5 value: 34.021 - type: ndcg_at_1 value: 27.345000000000002 - type: ndcg_at_10 value: 37.891999999999996 - type: ndcg_at_100 value: 42.664 - type: ndcg_at_1000 value: 44.757000000000005 - type: ndcg_at_3 value: 33.123000000000005 - type: ndcg_at_5 value: 35.035 - type: precision_at_1 value: 27.345000000000002 - type: precision_at_10 value: 5.763 - type: precision_at_100 value: 0.859 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 13.71 - type: precision_at_5 value: 9.401 - type: recall_at_1 value: 25.566 - type: recall_at_10 value: 50.563 - type: recall_at_100 value: 72.86399999999999 - type: recall_at_1000 value: 88.68599999999999 - type: recall_at_3 value: 37.43 - type: recall_at_5 value: 41.894999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.663 - type: map_at_10 value: 23.552 - type: map_at_100 value: 24.538 - type: map_at_1000 value: 24.661 - type: map_at_3 value: 21.085 - type: map_at_5 value: 22.391 - type: mrr_at_1 value: 20.025000000000002 - type: mrr_at_10 value: 27.643 - type: mrr_at_100 value: 28.499999999999996 - type: mrr_at_1000 value: 28.582 - type: mrr_at_3 value: 25.083 - type: mrr_at_5 value: 26.544 - type: ndcg_at_1 value: 20.025000000000002 - type: ndcg_at_10 value: 28.272000000000002 - type: ndcg_at_100 value: 33.353 - type: ndcg_at_1000 value: 36.454 - type: ndcg_at_3 value: 23.579 - type: ndcg_at_5 value: 25.685000000000002 - type: precision_at_1 value: 20.025000000000002 - type: precision_at_10 value: 5.187 - type: precision_at_100 value: 0.897 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 10.987 - type: precision_at_5 value: 8.06 - type: recall_at_1 value: 16.663 - type: recall_at_10 value: 38.808 - type: recall_at_100 value: 61.305 - type: recall_at_1000 value: 83.571 - type: recall_at_3 value: 25.907999999999998 - type: recall_at_5 value: 31.214 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.695999999999998 - type: map_at_10 value: 37.018 - type: map_at_100 value: 38.263000000000005 - type: map_at_1000 value: 38.371 - type: map_at_3 value: 34.226 - type: map_at_5 value: 35.809999999999995 - type: mrr_at_1 value: 32.916000000000004 - type: mrr_at_10 value: 42.067 - type: mrr_at_100 value: 42.925000000000004 - type: mrr_at_1000 value: 42.978 - type: mrr_at_3 value: 39.637 - type: mrr_at_5 value: 41.134 - type: ndcg_at_1 value: 32.916000000000004 - type: ndcg_at_10 value: 42.539 - type: ndcg_at_100 value: 47.873 - type: ndcg_at_1000 value: 50.08200000000001 - type: ndcg_at_3 value: 37.852999999999994 - type: ndcg_at_5 value: 40.201 - type: precision_at_1 value: 32.916000000000004 - type: precision_at_10 value: 7.5840000000000005 - type: precision_at_100 value: 1.199 - type: precision_at_1000 value: 0.155 - type: precision_at_3 value: 17.485 - type: precision_at_5 value: 12.512 - type: recall_at_1 value: 27.695999999999998 - type: recall_at_10 value: 53.638 - type: recall_at_100 value: 76.116 - type: recall_at_1000 value: 91.069 - type: recall_at_3 value: 41.13 - type: recall_at_5 value: 46.872 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.108 - type: map_at_10 value: 33.372 - type: map_at_100 value: 34.656 - type: map_at_1000 value: 34.768 - type: map_at_3 value: 30.830999999999996 - type: map_at_5 value: 32.204 - type: mrr_at_1 value: 29.110000000000003 - type: mrr_at_10 value: 37.979 - type: mrr_at_100 value: 38.933 - type: mrr_at_1000 value: 38.988 - type: mrr_at_3 value: 35.731 - type: mrr_at_5 value: 36.963 - type: ndcg_at_1 value: 29.110000000000003 - type: ndcg_at_10 value: 38.635000000000005 - type: ndcg_at_100 value: 44.324999999999996 - type: ndcg_at_1000 value: 46.747 - type: ndcg_at_3 value: 34.37 - type: ndcg_at_5 value: 36.228 - type: precision_at_1 value: 29.110000000000003 - type: precision_at_10 value: 6.963 - type: precision_at_100 value: 1.146 - type: precision_at_1000 value: 0.152 - type: precision_at_3 value: 16.400000000000002 - type: precision_at_5 value: 11.552999999999999 - type: recall_at_1 value: 24.108 - type: recall_at_10 value: 49.597 - type: recall_at_100 value: 73.88900000000001 - type: recall_at_1000 value: 90.62400000000001 - type: recall_at_3 value: 37.662 - type: recall_at_5 value: 42.565 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.00791666666667 - type: map_at_10 value: 33.287749999999996 - type: map_at_100 value: 34.41141666666667 - type: map_at_1000 value: 34.52583333333333 - type: map_at_3 value: 30.734416666666668 - type: map_at_5 value: 32.137166666666666 - type: mrr_at_1 value: 29.305666666666664 - type: mrr_at_10 value: 37.22966666666666 - type: mrr_at_100 value: 38.066583333333334 - type: mrr_at_1000 value: 38.12616666666667 - type: mrr_at_3 value: 34.92275 - type: mrr_at_5 value: 36.23333333333334 - type: ndcg_at_1 value: 29.305666666666664 - type: ndcg_at_10 value: 38.25533333333333 - type: ndcg_at_100 value: 43.25266666666666 - type: ndcg_at_1000 value: 45.63583333333334 - type: ndcg_at_3 value: 33.777166666666666 - type: ndcg_at_5 value: 35.85 - type: precision_at_1 value: 29.305666666666664 - type: precision_at_10 value: 6.596416666666667 - type: precision_at_100 value: 1.0784166666666668 - type: precision_at_1000 value: 0.14666666666666664 - type: precision_at_3 value: 15.31075 - type: precision_at_5 value: 10.830916666666667 - type: recall_at_1 value: 25.00791666666667 - type: recall_at_10 value: 49.10933333333333 - type: recall_at_100 value: 71.09216666666667 - type: recall_at_1000 value: 87.77725000000001 - type: recall_at_3 value: 36.660916666666665 - type: recall_at_5 value: 41.94149999999999 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.521 - type: map_at_10 value: 30.043 - type: map_at_100 value: 30.936000000000003 - type: map_at_1000 value: 31.022 - type: map_at_3 value: 27.926000000000002 - type: map_at_5 value: 29.076999999999998 - type: mrr_at_1 value: 26.227 - type: mrr_at_10 value: 32.822 - type: mrr_at_100 value: 33.61 - type: mrr_at_1000 value: 33.672000000000004 - type: mrr_at_3 value: 30.776999999999997 - type: mrr_at_5 value: 31.866 - type: ndcg_at_1 value: 26.227 - type: ndcg_at_10 value: 34.041 - type: ndcg_at_100 value: 38.394 - type: ndcg_at_1000 value: 40.732 - type: ndcg_at_3 value: 30.037999999999997 - type: ndcg_at_5 value: 31.845000000000002 - type: precision_at_1 value: 26.227 - type: precision_at_10 value: 5.244999999999999 - type: precision_at_100 value: 0.808 - type: precision_at_1000 value: 0.107 - type: precision_at_3 value: 12.679000000000002 - type: precision_at_5 value: 8.773 - type: recall_at_1 value: 23.521 - type: recall_at_10 value: 43.633 - type: recall_at_100 value: 63.126000000000005 - type: recall_at_1000 value: 80.765 - type: recall_at_3 value: 32.614 - type: recall_at_5 value: 37.15 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.236 - type: map_at_10 value: 22.898 - type: map_at_100 value: 23.878 - type: map_at_1000 value: 24.009 - type: map_at_3 value: 20.87 - type: map_at_5 value: 22.025 - type: mrr_at_1 value: 19.339000000000002 - type: mrr_at_10 value: 26.382 - type: mrr_at_100 value: 27.245 - type: mrr_at_1000 value: 27.33 - type: mrr_at_3 value: 24.386 - type: mrr_at_5 value: 25.496000000000002 - type: ndcg_at_1 value: 19.339000000000002 - type: ndcg_at_10 value: 27.139999999999997 - type: ndcg_at_100 value: 31.944 - type: ndcg_at_1000 value: 35.077999999999996 - type: ndcg_at_3 value: 23.424 - type: ndcg_at_5 value: 25.188 - type: precision_at_1 value: 19.339000000000002 - type: precision_at_10 value: 4.8309999999999995 - type: precision_at_100 value: 0.845 - type: precision_at_1000 value: 0.128 - type: precision_at_3 value: 10.874 - type: precision_at_5 value: 7.825 - type: recall_at_1 value: 16.236 - type: recall_at_10 value: 36.513 - type: recall_at_100 value: 57.999 - type: recall_at_1000 value: 80.512 - type: recall_at_3 value: 26.179999999999996 - type: recall_at_5 value: 30.712 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.11 - type: map_at_10 value: 31.566 - type: map_at_100 value: 32.647 - type: map_at_1000 value: 32.753 - type: map_at_3 value: 29.24 - type: map_at_5 value: 30.564999999999998 - type: mrr_at_1 value: 28.265 - type: mrr_at_10 value: 35.504000000000005 - type: mrr_at_100 value: 36.436 - type: mrr_at_1000 value: 36.503 - type: mrr_at_3 value: 33.349000000000004 - type: mrr_at_5 value: 34.622 - type: ndcg_at_1 value: 28.265 - type: ndcg_at_10 value: 36.192 - type: ndcg_at_100 value: 41.388000000000005 - type: ndcg_at_1000 value: 43.948 - type: ndcg_at_3 value: 31.959 - type: ndcg_at_5 value: 33.998 - type: precision_at_1 value: 28.265 - type: precision_at_10 value: 5.989 - type: precision_at_100 value: 0.9650000000000001 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 14.335 - type: precision_at_5 value: 10.112 - type: recall_at_1 value: 24.11 - type: recall_at_10 value: 46.418 - type: recall_at_100 value: 69.314 - type: recall_at_1000 value: 87.397 - type: recall_at_3 value: 34.724 - type: recall_at_5 value: 39.925 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.091 - type: map_at_10 value: 29.948999999999998 - type: map_at_100 value: 31.502000000000002 - type: map_at_1000 value: 31.713 - type: map_at_3 value: 27.464 - type: map_at_5 value: 28.968 - type: mrr_at_1 value: 26.482 - type: mrr_at_10 value: 34.009 - type: mrr_at_100 value: 35.081 - type: mrr_at_1000 value: 35.138000000000005 - type: mrr_at_3 value: 31.785000000000004 - type: mrr_at_5 value: 33.178999999999995 - type: ndcg_at_1 value: 26.482 - type: ndcg_at_10 value: 35.008 - type: ndcg_at_100 value: 41.272999999999996 - type: ndcg_at_1000 value: 43.972 - type: ndcg_at_3 value: 30.804 - type: ndcg_at_5 value: 33.046 - type: precision_at_1 value: 26.482 - type: precision_at_10 value: 6.462 - type: precision_at_100 value: 1.431 - type: precision_at_1000 value: 0.22899999999999998 - type: precision_at_3 value: 14.360999999999999 - type: precision_at_5 value: 10.474 - type: recall_at_1 value: 22.091 - type: recall_at_10 value: 45.125 - type: recall_at_100 value: 72.313 - type: recall_at_1000 value: 89.503 - type: recall_at_3 value: 33.158 - type: recall_at_5 value: 39.086999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 19.883 - type: map_at_10 value: 26.951000000000004 - type: map_at_100 value: 27.927999999999997 - type: map_at_1000 value: 28.022000000000002 - type: map_at_3 value: 24.616 - type: map_at_5 value: 25.917 - type: mrr_at_1 value: 21.996 - type: mrr_at_10 value: 29.221000000000004 - type: mrr_at_100 value: 30.024 - type: mrr_at_1000 value: 30.095 - type: mrr_at_3 value: 26.833000000000002 - type: mrr_at_5 value: 28.155 - type: ndcg_at_1 value: 21.996 - type: ndcg_at_10 value: 31.421 - type: ndcg_at_100 value: 36.237 - type: ndcg_at_1000 value: 38.744 - type: ndcg_at_3 value: 26.671 - type: ndcg_at_5 value: 28.907 - type: precision_at_1 value: 21.996 - type: precision_at_10 value: 5.009 - type: precision_at_100 value: 0.799 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 11.275 - type: precision_at_5 value: 8.059 - type: recall_at_1 value: 19.883 - type: recall_at_10 value: 43.132999999999996 - type: recall_at_100 value: 65.654 - type: recall_at_1000 value: 84.492 - type: recall_at_3 value: 30.209000000000003 - type: recall_at_5 value: 35.616 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 17.756 - type: map_at_10 value: 30.378 - type: map_at_100 value: 32.537 - type: map_at_1000 value: 32.717 - type: map_at_3 value: 25.599 - type: map_at_5 value: 28.372999999999998 - type: mrr_at_1 value: 41.303 - type: mrr_at_10 value: 53.483999999999995 - type: mrr_at_100 value: 54.106 - type: mrr_at_1000 value: 54.127 - type: mrr_at_3 value: 50.315 - type: mrr_at_5 value: 52.396 - type: ndcg_at_1 value: 41.303 - type: ndcg_at_10 value: 40.503 - type: ndcg_at_100 value: 47.821000000000005 - type: ndcg_at_1000 value: 50.788 - type: ndcg_at_3 value: 34.364 - type: ndcg_at_5 value: 36.818 - type: precision_at_1 value: 41.303 - type: precision_at_10 value: 12.463000000000001 - type: precision_at_100 value: 2.037 - type: precision_at_1000 value: 0.26 - type: precision_at_3 value: 25.798 - type: precision_at_5 value: 19.896 - type: recall_at_1 value: 17.756 - type: recall_at_10 value: 46.102 - type: recall_at_100 value: 70.819 - type: recall_at_1000 value: 87.21799999999999 - type: recall_at_3 value: 30.646 - type: recall_at_5 value: 38.022 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 9.033 - type: map_at_10 value: 20.584 - type: map_at_100 value: 29.518 - type: map_at_1000 value: 31.186000000000003 - type: map_at_3 value: 14.468 - type: map_at_5 value: 17.177 - type: mrr_at_1 value: 69.75 - type: mrr_at_10 value: 77.025 - type: mrr_at_100 value: 77.36699999999999 - type: mrr_at_1000 value: 77.373 - type: mrr_at_3 value: 75.583 - type: mrr_at_5 value: 76.396 - type: ndcg_at_1 value: 58.5 - type: ndcg_at_10 value: 45.033 - type: ndcg_at_100 value: 49.071 - type: ndcg_at_1000 value: 56.056 - type: ndcg_at_3 value: 49.936 - type: ndcg_at_5 value: 47.471999999999994 - type: precision_at_1 value: 69.75 - type: precision_at_10 value: 35.775 - type: precision_at_100 value: 11.594999999999999 - type: precision_at_1000 value: 2.062 - type: precision_at_3 value: 52.5 - type: precision_at_5 value: 45.300000000000004 - type: recall_at_1 value: 9.033 - type: recall_at_10 value: 26.596999999999998 - type: recall_at_100 value: 54.607000000000006 - type: recall_at_1000 value: 76.961 - type: recall_at_3 value: 15.754999999999999 - type: recall_at_5 value: 20.033 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 48.345000000000006 - type: f1 value: 43.4514918068706 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 71.29100000000001 - type: map_at_10 value: 81.059 - type: map_at_100 value: 81.341 - type: map_at_1000 value: 81.355 - type: map_at_3 value: 79.74799999999999 - type: map_at_5 value: 80.612 - type: mrr_at_1 value: 76.40299999999999 - type: mrr_at_10 value: 84.615 - type: mrr_at_100 value: 84.745 - type: mrr_at_1000 value: 84.748 - type: mrr_at_3 value: 83.776 - type: mrr_at_5 value: 84.343 - type: ndcg_at_1 value: 76.40299999999999 - type: ndcg_at_10 value: 84.981 - type: ndcg_at_100 value: 86.00999999999999 - type: ndcg_at_1000 value: 86.252 - type: ndcg_at_3 value: 82.97 - type: ndcg_at_5 value: 84.152 - type: precision_at_1 value: 76.40299999999999 - type: precision_at_10 value: 10.446 - type: precision_at_100 value: 1.1199999999999999 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 32.147999999999996 - type: precision_at_5 value: 20.135 - type: recall_at_1 value: 71.29100000000001 - type: recall_at_10 value: 93.232 - type: recall_at_100 value: 97.363 - type: recall_at_1000 value: 98.905 - type: recall_at_3 value: 87.893 - type: recall_at_5 value: 90.804 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 18.667 - type: map_at_10 value: 30.853 - type: map_at_100 value: 32.494 - type: map_at_1000 value: 32.677 - type: map_at_3 value: 26.91 - type: map_at_5 value: 29.099000000000004 - type: mrr_at_1 value: 37.191 - type: mrr_at_10 value: 46.171 - type: mrr_at_100 value: 47.056 - type: mrr_at_1000 value: 47.099000000000004 - type: mrr_at_3 value: 44.059 - type: mrr_at_5 value: 45.147 - type: ndcg_at_1 value: 37.191 - type: ndcg_at_10 value: 38.437 - type: ndcg_at_100 value: 44.62 - type: ndcg_at_1000 value: 47.795 - type: ndcg_at_3 value: 35.003 - type: ndcg_at_5 value: 36.006 - type: precision_at_1 value: 37.191 - type: precision_at_10 value: 10.586 - type: precision_at_100 value: 1.688 - type: precision_at_1000 value: 0.22699999999999998 - type: precision_at_3 value: 23.302 - type: precision_at_5 value: 17.006 - type: recall_at_1 value: 18.667 - type: recall_at_10 value: 45.367000000000004 - type: recall_at_100 value: 68.207 - type: recall_at_1000 value: 87.072 - type: recall_at_3 value: 32.129000000000005 - type: recall_at_5 value: 37.719 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 39.494 - type: map_at_10 value: 66.223 - type: map_at_100 value: 67.062 - type: map_at_1000 value: 67.11500000000001 - type: map_at_3 value: 62.867 - type: map_at_5 value: 64.994 - type: mrr_at_1 value: 78.987 - type: mrr_at_10 value: 84.585 - type: mrr_at_100 value: 84.773 - type: mrr_at_1000 value: 84.77900000000001 - type: mrr_at_3 value: 83.592 - type: mrr_at_5 value: 84.235 - type: ndcg_at_1 value: 78.987 - type: ndcg_at_10 value: 73.64 - type: ndcg_at_100 value: 76.519 - type: ndcg_at_1000 value: 77.51 - type: ndcg_at_3 value: 68.893 - type: ndcg_at_5 value: 71.585 - type: precision_at_1 value: 78.987 - type: precision_at_10 value: 15.529000000000002 - type: precision_at_100 value: 1.7770000000000001 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 44.808 - type: precision_at_5 value: 29.006999999999998 - type: recall_at_1 value: 39.494 - type: recall_at_10 value: 77.643 - type: recall_at_100 value: 88.825 - type: recall_at_1000 value: 95.321 - type: recall_at_3 value: 67.211 - type: recall_at_5 value: 72.519 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 85.55959999999999 - type: ap value: 80.7246500384617 - type: f1 value: 85.52336485065454 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 23.631 - type: map_at_10 value: 36.264 - type: map_at_100 value: 37.428 - type: map_at_1000 value: 37.472 - type: map_at_3 value: 32.537 - type: map_at_5 value: 34.746 - type: mrr_at_1 value: 24.312 - type: mrr_at_10 value: 36.858000000000004 - type: mrr_at_100 value: 37.966 - type: mrr_at_1000 value: 38.004 - type: mrr_at_3 value: 33.188 - type: mrr_at_5 value: 35.367 - type: ndcg_at_1 value: 24.312 - type: ndcg_at_10 value: 43.126999999999995 - type: ndcg_at_100 value: 48.642 - type: ndcg_at_1000 value: 49.741 - type: ndcg_at_3 value: 35.589 - type: ndcg_at_5 value: 39.515 - type: precision_at_1 value: 24.312 - type: precision_at_10 value: 6.699 - type: precision_at_100 value: 0.9450000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 15.153 - type: precision_at_5 value: 11.065999999999999 - type: recall_at_1 value: 23.631 - type: recall_at_10 value: 64.145 - type: recall_at_100 value: 89.41 - type: recall_at_1000 value: 97.83500000000001 - type: recall_at_3 value: 43.769000000000005 - type: recall_at_5 value: 53.169 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.4108527131783 - type: f1 value: 93.1415880261038 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 77.24806201550388 - type: f1 value: 60.531916308197175 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 73.71553463349024 - type: f1 value: 71.70753174900791 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.79757901815736 - type: f1 value: 77.83719850433258 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 33.74193296622113 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 30.64257594108566 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.811018518883625 - type: mrr value: 31.910376577445003 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.409 - type: map_at_10 value: 13.093 - type: map_at_100 value: 16.256999999999998 - type: map_at_1000 value: 17.617 - type: map_at_3 value: 9.555 - type: map_at_5 value: 11.428 - type: mrr_at_1 value: 45.201 - type: mrr_at_10 value: 54.179 - type: mrr_at_100 value: 54.812000000000005 - type: mrr_at_1000 value: 54.840999999999994 - type: mrr_at_3 value: 51.909000000000006 - type: mrr_at_5 value: 53.519000000000005 - type: ndcg_at_1 value: 43.189 - type: ndcg_at_10 value: 35.028 - type: ndcg_at_100 value: 31.226 - type: ndcg_at_1000 value: 39.678000000000004 - type: ndcg_at_3 value: 40.596 - type: ndcg_at_5 value: 38.75 - type: precision_at_1 value: 44.582 - type: precision_at_10 value: 25.974999999999998 - type: precision_at_100 value: 7.793 - type: precision_at_1000 value: 2.036 - type: precision_at_3 value: 38.493 - type: precision_at_5 value: 33.994 - type: recall_at_1 value: 5.409 - type: recall_at_10 value: 16.875999999999998 - type: recall_at_100 value: 30.316 - type: recall_at_1000 value: 60.891 - type: recall_at_3 value: 10.688 - type: recall_at_5 value: 13.832 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 36.375 - type: map_at_10 value: 51.991 - type: map_at_100 value: 52.91400000000001 - type: map_at_1000 value: 52.93600000000001 - type: map_at_3 value: 48.014 - type: map_at_5 value: 50.381 - type: mrr_at_1 value: 40.759 - type: mrr_at_10 value: 54.617000000000004 - type: mrr_at_100 value: 55.301 - type: mrr_at_1000 value: 55.315000000000005 - type: mrr_at_3 value: 51.516 - type: mrr_at_5 value: 53.435 - type: ndcg_at_1 value: 40.759 - type: ndcg_at_10 value: 59.384 - type: ndcg_at_100 value: 63.157 - type: ndcg_at_1000 value: 63.654999999999994 - type: ndcg_at_3 value: 52.114000000000004 - type: ndcg_at_5 value: 55.986000000000004 - type: precision_at_1 value: 40.759 - type: precision_at_10 value: 9.411999999999999 - type: precision_at_100 value: 1.153 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 23.329 - type: precision_at_5 value: 16.256999999999998 - type: recall_at_1 value: 36.375 - type: recall_at_10 value: 79.053 - type: recall_at_100 value: 95.167 - type: recall_at_1000 value: 98.82 - type: recall_at_3 value: 60.475 - type: recall_at_5 value: 69.327 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 70.256 - type: map_at_10 value: 83.8 - type: map_at_100 value: 84.425 - type: map_at_1000 value: 84.444 - type: map_at_3 value: 80.906 - type: map_at_5 value: 82.717 - type: mrr_at_1 value: 80.97999999999999 - type: mrr_at_10 value: 87.161 - type: mrr_at_100 value: 87.262 - type: mrr_at_1000 value: 87.263 - type: mrr_at_3 value: 86.175 - type: mrr_at_5 value: 86.848 - type: ndcg_at_1 value: 80.97999999999999 - type: ndcg_at_10 value: 87.697 - type: ndcg_at_100 value: 88.959 - type: ndcg_at_1000 value: 89.09899999999999 - type: ndcg_at_3 value: 84.83800000000001 - type: ndcg_at_5 value: 86.401 - type: precision_at_1 value: 80.97999999999999 - type: precision_at_10 value: 13.261000000000001 - type: precision_at_100 value: 1.5150000000000001 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 37.01 - type: precision_at_5 value: 24.298000000000002 - type: recall_at_1 value: 70.256 - type: recall_at_10 value: 94.935 - type: recall_at_100 value: 99.274 - type: recall_at_1000 value: 99.928 - type: recall_at_3 value: 86.602 - type: recall_at_5 value: 91.133 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.322692497613104 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 61.895813503775074 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.338 - type: map_at_10 value: 10.767 - type: map_at_100 value: 12.537999999999998 - type: map_at_1000 value: 12.803999999999998 - type: map_at_3 value: 7.788 - type: map_at_5 value: 9.302000000000001 - type: mrr_at_1 value: 21.4 - type: mrr_at_10 value: 31.637999999999998 - type: mrr_at_100 value: 32.688 - type: mrr_at_1000 value: 32.756 - type: mrr_at_3 value: 28.433000000000003 - type: mrr_at_5 value: 30.178 - type: ndcg_at_1 value: 21.4 - type: ndcg_at_10 value: 18.293 - type: ndcg_at_100 value: 25.274 - type: ndcg_at_1000 value: 30.284 - type: ndcg_at_3 value: 17.391000000000002 - type: ndcg_at_5 value: 15.146999999999998 - type: precision_at_1 value: 21.4 - type: precision_at_10 value: 9.48 - type: precision_at_100 value: 1.949 - type: precision_at_1000 value: 0.316 - type: precision_at_3 value: 16.167 - type: precision_at_5 value: 13.22 - type: recall_at_1 value: 4.338 - type: recall_at_10 value: 19.213 - type: recall_at_100 value: 39.562999999999995 - type: recall_at_1000 value: 64.08 - type: recall_at_3 value: 9.828000000000001 - type: recall_at_5 value: 13.383000000000001 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.42568163642142 - type: cos_sim_spearman value: 78.5797159641342 - type: euclidean_pearson value: 80.22151260811604 - type: euclidean_spearman value: 78.5797151953878 - type: manhattan_pearson value: 80.21224215864788 - type: manhattan_spearman value: 78.55641478381344 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 85.44020710812569 - type: cos_sim_spearman value: 78.91631735081286 - type: euclidean_pearson value: 81.64188964182102 - type: euclidean_spearman value: 78.91633286881678 - type: manhattan_pearson value: 81.69294748512496 - type: manhattan_spearman value: 78.93438558002656 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 84.27165426412311 - type: cos_sim_spearman value: 85.40429140249618 - type: euclidean_pearson value: 84.7509580724893 - type: euclidean_spearman value: 85.40429140249618 - type: manhattan_pearson value: 84.76488289321308 - type: manhattan_spearman value: 85.4256793698708 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 83.138851760732 - type: cos_sim_spearman value: 81.64101363896586 - type: euclidean_pearson value: 82.55165038934942 - type: euclidean_spearman value: 81.64105257080502 - type: manhattan_pearson value: 82.52802949883335 - type: manhattan_spearman value: 81.61255430718158 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 86.0654695484029 - type: cos_sim_spearman value: 87.20408521902229 - type: euclidean_pearson value: 86.8110651362115 - type: euclidean_spearman value: 87.20408521902229 - type: manhattan_pearson value: 86.77984656478691 - type: manhattan_spearman value: 87.1719947099227 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 83.77823915496512 - type: cos_sim_spearman value: 85.43566325729779 - type: euclidean_pearson value: 84.5396956658821 - type: euclidean_spearman value: 85.43566325729779 - type: manhattan_pearson value: 84.5665398848169 - type: manhattan_spearman value: 85.44375870303232 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.20030208471798 - type: cos_sim_spearman value: 87.20485505076539 - type: euclidean_pearson value: 88.10588324368722 - type: euclidean_spearman value: 87.20485505076539 - type: manhattan_pearson value: 87.92324770415183 - type: manhattan_spearman value: 87.0571314561877 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 63.06093161604453 - type: cos_sim_spearman value: 64.2163140357722 - type: euclidean_pearson value: 65.27589680994006 - type: euclidean_spearman value: 64.2163140357722 - type: manhattan_pearson value: 65.45904383711101 - type: manhattan_spearman value: 64.55404716679305 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 84.32976164578706 - type: cos_sim_spearman value: 85.54302197678368 - type: euclidean_pearson value: 85.26307149193056 - type: euclidean_spearman value: 85.54302197678368 - type: manhattan_pearson value: 85.26647282029371 - type: manhattan_spearman value: 85.5316135265568 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 81.44675968318754 - type: mrr value: 94.92741826075158 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 56.34400000000001 - type: map_at_10 value: 65.927 - type: map_at_100 value: 66.431 - type: map_at_1000 value: 66.461 - type: map_at_3 value: 63.529 - type: map_at_5 value: 64.818 - type: mrr_at_1 value: 59.333000000000006 - type: mrr_at_10 value: 67.54599999999999 - type: mrr_at_100 value: 67.892 - type: mrr_at_1000 value: 67.917 - type: mrr_at_3 value: 65.778 - type: mrr_at_5 value: 66.794 - type: ndcg_at_1 value: 59.333000000000006 - type: ndcg_at_10 value: 70.5 - type: ndcg_at_100 value: 72.688 - type: ndcg_at_1000 value: 73.483 - type: ndcg_at_3 value: 66.338 - type: ndcg_at_5 value: 68.265 - type: precision_at_1 value: 59.333000000000006 - type: precision_at_10 value: 9.3 - type: precision_at_100 value: 1.053 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 25.889 - type: precision_at_5 value: 16.866999999999997 - type: recall_at_1 value: 56.34400000000001 - type: recall_at_10 value: 82.789 - type: recall_at_100 value: 92.767 - type: recall_at_1000 value: 99 - type: recall_at_3 value: 71.64399999999999 - type: recall_at_5 value: 76.322 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.75742574257426 - type: cos_sim_ap value: 93.52081548447406 - type: cos_sim_f1 value: 87.33850129198966 - type: cos_sim_precision value: 90.37433155080214 - type: cos_sim_recall value: 84.5 - type: dot_accuracy value: 99.75742574257426 - type: dot_ap value: 93.52081548447406 - type: dot_f1 value: 87.33850129198966 - type: dot_precision value: 90.37433155080214 - type: dot_recall value: 84.5 - type: euclidean_accuracy value: 99.75742574257426 - type: euclidean_ap value: 93.52081548447406 - type: euclidean_f1 value: 87.33850129198966 - type: euclidean_precision value: 90.37433155080214 - type: euclidean_recall value: 84.5 - type: manhattan_accuracy value: 99.75841584158415 - type: manhattan_ap value: 93.4975678585854 - type: manhattan_f1 value: 87.26708074534162 - type: manhattan_precision value: 90.45064377682404 - type: manhattan_recall value: 84.3 - type: max_accuracy value: 99.75841584158415 - type: max_ap value: 93.52081548447406 - type: max_f1 value: 87.33850129198966 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 64.31437036686651 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 33.25569319007206 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 49.90474939720706 - type: mrr value: 50.568115503777264 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 29.866828641244712 - type: cos_sim_spearman value: 30.077555055873866 - type: dot_pearson value: 29.866832988572266 - type: dot_spearman value: 30.077555055873866 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.232 - type: map_at_10 value: 2.094 - type: map_at_100 value: 11.971 - type: map_at_1000 value: 28.158 - type: map_at_3 value: 0.688 - type: map_at_5 value: 1.114 - type: mrr_at_1 value: 88 - type: mrr_at_10 value: 93.4 - type: mrr_at_100 value: 93.4 - type: mrr_at_1000 value: 93.4 - type: mrr_at_3 value: 93 - type: mrr_at_5 value: 93.4 - type: ndcg_at_1 value: 84 - type: ndcg_at_10 value: 79.923 - type: ndcg_at_100 value: 61.17 - type: ndcg_at_1000 value: 53.03 - type: ndcg_at_3 value: 84.592 - type: ndcg_at_5 value: 82.821 - type: precision_at_1 value: 88 - type: precision_at_10 value: 85 - type: precision_at_100 value: 63.019999999999996 - type: precision_at_1000 value: 23.554 - type: precision_at_3 value: 89.333 - type: precision_at_5 value: 87.2 - type: recall_at_1 value: 0.232 - type: recall_at_10 value: 2.255 - type: recall_at_100 value: 14.823 - type: recall_at_1000 value: 49.456 - type: recall_at_3 value: 0.718 - type: recall_at_5 value: 1.175 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.547 - type: map_at_10 value: 11.375 - type: map_at_100 value: 18.194 - type: map_at_1000 value: 19.749 - type: map_at_3 value: 5.825 - type: map_at_5 value: 8.581 - type: mrr_at_1 value: 32.653 - type: mrr_at_10 value: 51.32 - type: mrr_at_100 value: 51.747 - type: mrr_at_1000 value: 51.747 - type: mrr_at_3 value: 47.278999999999996 - type: mrr_at_5 value: 48.605 - type: ndcg_at_1 value: 29.592000000000002 - type: ndcg_at_10 value: 28.151 - type: ndcg_at_100 value: 39.438 - type: ndcg_at_1000 value: 50.769 - type: ndcg_at_3 value: 30.758999999999997 - type: ndcg_at_5 value: 30.366 - type: precision_at_1 value: 32.653 - type: precision_at_10 value: 25.714 - type: precision_at_100 value: 8.041 - type: precision_at_1000 value: 1.555 - type: precision_at_3 value: 33.333 - type: precision_at_5 value: 31.837 - type: recall_at_1 value: 2.547 - type: recall_at_10 value: 18.19 - type: recall_at_100 value: 49.538 - type: recall_at_1000 value: 83.86 - type: recall_at_3 value: 7.329 - type: recall_at_5 value: 11.532 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.4952 - type: ap value: 14.793362635531409 - type: f1 value: 55.204635551516915 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 61.5365025466893 - type: f1 value: 61.81742556334845 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 49.05531070301185 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.51725576682364 - type: cos_sim_ap value: 75.2292304265163 - type: cos_sim_f1 value: 69.54022988505749 - type: cos_sim_precision value: 63.65629110039457 - type: cos_sim_recall value: 76.62269129287598 - type: dot_accuracy value: 86.51725576682364 - type: dot_ap value: 75.22922386081054 - type: dot_f1 value: 69.54022988505749 - type: dot_precision value: 63.65629110039457 - type: dot_recall value: 76.62269129287598 - type: euclidean_accuracy value: 86.51725576682364 - type: euclidean_ap value: 75.22925730473472 - type: euclidean_f1 value: 69.54022988505749 - type: euclidean_precision value: 63.65629110039457 - type: euclidean_recall value: 76.62269129287598 - type: manhattan_accuracy value: 86.52321630804077 - type: manhattan_ap value: 75.20608115037336 - type: manhattan_f1 value: 69.60000000000001 - type: manhattan_precision value: 64.37219730941705 - type: manhattan_recall value: 75.75197889182058 - type: max_accuracy value: 86.52321630804077 - type: max_ap value: 75.22925730473472 - type: max_f1 value: 69.60000000000001 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.34877944657896 - type: cos_sim_ap value: 86.71257569277373 - type: cos_sim_f1 value: 79.10386355986088 - type: cos_sim_precision value: 76.91468470434214 - type: cos_sim_recall value: 81.4213119802895 - type: dot_accuracy value: 89.34877944657896 - type: dot_ap value: 86.71257133133368 - type: dot_f1 value: 79.10386355986088 - type: dot_precision value: 76.91468470434214 - type: dot_recall value: 81.4213119802895 - type: euclidean_accuracy value: 89.34877944657896 - type: euclidean_ap value: 86.71257651501476 - type: euclidean_f1 value: 79.10386355986088 - type: euclidean_precision value: 76.91468470434214 - type: euclidean_recall value: 81.4213119802895 - type: manhattan_accuracy value: 89.35848177901967 - type: manhattan_ap value: 86.69330615469126 - type: manhattan_f1 value: 79.13867741453949 - type: manhattan_precision value: 76.78881807647741 - type: manhattan_recall value: 81.63689559593472 - type: max_accuracy value: 89.35848177901967 - type: max_ap value: 86.71257651501476 - type: max_f1 value: 79.13867741453949 license: apache-2.0 language: - en --- # nomic-embed-text-v1: A Reproducible Long Context (8192) Text Embedder `nomic-embed-text-v1` is 8192 context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks. | Name | SeqLen | MTEB | LoCo | Jina Long Context | Open Weights | Open Training Code | Open Data | | :-------------------------------:| :----- | :-------- | :------: | :---------------: | :-----------: | :----------------: | :---------- | | nomic-embed-text-v1 | 8192 | **62.39** |**85.53** | 54.16 | ✅ | ✅ | ✅ | | jina-embeddings-v2-base-en | 8192 | 60.39 | 85.45 | 51.90 | ✅ | ❌ | ❌ | | text-embedding-3-small | 8191 | 62.26 | 82.40 | **58.20** | ❌ | ❌ | ❌ | | text-embedding-ada-002 | 8191 | 60.99 | 52.7 | 55.25 | ❌ | ❌ | ❌ | ## Hosted Inference API The easiest way to get started with Nomic Embed is through the Nomic Embedding API. Generating embeddings with the `nomic` Python client is as easy as ```python from nomic import embed output = embed.text( texts=['Nomic Embedding API', '#keepAIOpen'], model='nomic-embed-text-v1', task_type='search_document' ) print(output) ``` For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text) ## Data Visualization Click the Nomic Atlas map below to visualize a 5M sample of our contrastive pretraining data! [![image/webp](https://cdn-uploads.huggingface.co/production/uploads/607997c83a565c15675055b3/pjhJhuNyRfPagRd_c_iUz.webp)](https://atlas.nomic.ai/map/nomic-text-embed-v1-5m-sample) ## Training Details We train our embedder using a multi-stage training pipeline. Starting from a long-context [BERT model](https://huggingface.co/nomic-ai/nomic-bert-2048), the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles. In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage. For more details, see the Nomic Embed [Technical Report](https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf) and corresponding [blog post](https://blog.nomic.ai/posts/nomic-embed-text-v1). Training data to train the models is released in its entirety. For more details, see the `contrastors` [repository](https://github.com/nomic-ai/contrastors) ## Usage Note `nomic-embed-text` *requires* prefixes! We support the prefixes `[search_query, search_document, classification, clustering]`. For retrieval applications, you should prepend `search_document` for all your documents and `search_query` for your queries. For example, you are building a RAG application over the top of Wikipedia. You would embed all Wikipedia articles with the prefix `search_document` and any questions you ask with `search_query`. For example: ```python queries = ["search_query: who is the first president of the united states?", "search_query: when was babe ruth born?"] documents = ["search_document: <article about US Presidents>", "search_document: <article about Babe Ruth>"] ``` ### Sentence Transformers ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] embeddings = model.encode(sentences) print(embeddings) ``` ### Transformers ```python import torch import torch.nn.functional as F from transformers import AutoTokenizer, AutoModel def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) model.eval() encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') with torch.no_grad(): model_output = model(**encoded_input) embeddings = mean_pooling(model_output, encoded_input['attention_mask']) embeddings = F.normalize(embeddings, p=2, dim=1) print(embeddings) ``` The model natively supports scaling of the sequence length past 2048 tokens. To do so, ```diff - tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') + tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192) - model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) + model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2) ``` ### Transformers.js ```js import { pipeline } from '@xenova/transformers'; // Create a feature extraction pipeline const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1', { quantized: false, // Comment out this line to use the quantized version }); // Compute sentence embeddings const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']; const embeddings = await extractor(texts, { pooling: 'mean', normalize: true }); console.log(embeddings); ``` # Join the Nomic Community - Nomic: [https://nomic.ai](https://nomic.ai) - Discord: [https://discord.gg/myY5YDR8z8](https://discord.gg/myY5YDR8z8) - Twitter: [https://twitter.com/nomic_ai](https://twitter.com/nomic_ai) # Citation If you find the model, dataset, or training code useful, please cite our work ```bibtex @misc{nussbaum2024nomic, title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar}, year={2024}, eprint={2402.01613}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

mradermacher/Elysium2.1-11b-i1-GGUF

mradermacher

"2024-06-12T00:05:27Z"

2,592

0

transformers

[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "powermove72/Trinity_Notus-xb", "powermove72/GreenScorpius-xb-Passthrough", "en", "base_model:powermove72/Elysium2.1-11b", "endpoints_compatible", "region:us" ]

null

"2024-06-11T16:57:37Z"

--- base_model: powermove72/Elysium2.1-11b language: - en library_name: transformers quantized_by: mradermacher tags: - merge - mergekit - lazymergekit - powermove72/Trinity_Notus-xb - powermove72/GreenScorpius-xb-Passthrough --- ## About      weighted/imatrix quants of https://huggingface.co/powermove72/Elysium2.1-11b  static quants are available at https://huggingface.co/mradermacher/Elysium2.1-11b-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.8 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.1 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.5 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ2_S.gguf) | i1-IQ2_S | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q2_K.gguf) | i1-Q2_K | 4.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.7 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.0 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ3_S.gguf) | i1-IQ3_S | 5.0 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ3_M.gguf) | i1-IQ3_M | 5.1 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.5 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.0 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.1 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q4_0.gguf) | i1-Q4_0 | 6.4 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.5 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.8 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.0 | | | [GGUF](https://huggingface.co/mradermacher/Elysium2.1-11b-i1-GGUF/resolve/main/Elysium2.1-11b.i1-Q6_K.gguf) | i1-Q6_K | 9.3 | practically like static Q6_K | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his hardware for calculating the imatrix for these quants.

NOVA-vision-language/task-intent-detector

NOVA-vision-language

"2024-05-15T10:57:19Z"

2,591

0

transformers

[ "transformers", "safetensors", "roberta", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-classification

"2024-05-14T20:52:16Z"

Here's an adapted TWIZ intent detection model, trained on the TWIZ dataset, with an extra focus on simplicity! It achieves ~85% accuracy on the TWIZ test set, and should be especially useful for the WSDM students @ NOVA. I STRONGLY suggest interested students to check `model_code` in the `Files and versions` tab, where all the code used to get to the model (with the exception of actually uploading it here) is laid out nicely (I hope!) Here's the contents of `intent-detection-example.ipynb`, if you're just looking to use the model: ```python with open("twiz-data/all_intents.json", 'r') as json_in: # all_intents.json can be found in the task-intent-detector/model_code directory data = json.load(json_in) id_to_intent, intent_to_id = dict(), dict() for i, intent in enumerate(data): id_to_intent[i] = intent intent_to_id[intent] = i model = AutoModelForSequenceClassification.from_pretrained("NOVA-vision-language/task-intent-detector", num_labels=len(data), id2label=id_to_intent, label2id=intent_to_id) tokenizer = AutoTokenizer.from_pretrained("roberta-base") # you could try 'NOVA-vision-language/task-intent-detector', but I'm not sure I configured it correctly model_in = tokenizer("I really really wanna go to the next step", return_tensors='pt') with torch.no_grad(): logits = model(**model_in).logits # grab the predictions out of the model's classification head predicted_class_id = logits.argmax().item() # grab the index of the highest scoring output print(model.config.id2label[predicted_class_id]) # use the translation table we just created to translate between that id and the actual intent name ```

jacobhoffmann/codegemma-2b-GGUF

jacobhoffmann

"2024-06-05T11:54:12Z"

2,591

0

null

[ "gguf", "region:us" ]

null

"2024-06-05T11:26:01Z"

Entry not found

CAiRE/UniVaR-lambda-5

CAiRE

"2024-06-14T17:57:41Z"

2,591

0

sentence-transformers

[ "sentence-transformers", "safetensors", "nomic_bert", "feature-extraction", "sentence-similarity", "mteb", "transformers", "transformers.js", "custom_code", "en", "arxiv:2402.01613", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-embeddings-inference", "region:us" ]

sentence-similarity

"2024-06-14T17:57:09Z"

--- library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - feature-extraction - sentence-similarity - mteb - transformers - transformers.js model-index: - name: epoch_0_model results: - task: type: Classification dataset: type: mteb/amazon_counterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 76.8507462686567 - type: ap value: 40.592189159090495 - type: f1 value: 71.01634655512476 - task: type: Classification dataset: type: mteb/amazon_polarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 91.51892500000001 - type: ap value: 88.50346762975335 - type: f1 value: 91.50342077459624 - task: type: Classification dataset: type: mteb/amazon_reviews_multi name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 47.364 - type: f1 value: 46.72708080922794 - task: type: Retrieval dataset: type: arguana name: MTEB ArguAna config: default split: test revision: None metrics: - type: map_at_1 value: 25.178 - type: map_at_10 value: 40.244 - type: map_at_100 value: 41.321999999999996 - type: map_at_1000 value: 41.331 - type: map_at_3 value: 35.016999999999996 - type: map_at_5 value: 37.99 - type: mrr_at_1 value: 25.605 - type: mrr_at_10 value: 40.422000000000004 - type: mrr_at_100 value: 41.507 - type: mrr_at_1000 value: 41.516 - type: mrr_at_3 value: 35.23 - type: mrr_at_5 value: 38.15 - type: ndcg_at_1 value: 25.178 - type: ndcg_at_10 value: 49.258 - type: ndcg_at_100 value: 53.776 - type: ndcg_at_1000 value: 53.995000000000005 - type: ndcg_at_3 value: 38.429 - type: ndcg_at_5 value: 43.803 - type: precision_at_1 value: 25.178 - type: precision_at_10 value: 7.831 - type: precision_at_100 value: 0.979 - type: precision_at_1000 value: 0.1 - type: precision_at_3 value: 16.121 - type: precision_at_5 value: 12.29 - type: recall_at_1 value: 25.178 - type: recall_at_10 value: 78.307 - type: recall_at_100 value: 97.866 - type: recall_at_1000 value: 99.57300000000001 - type: recall_at_3 value: 48.364000000000004 - type: recall_at_5 value: 61.451 - task: type: Clustering dataset: type: mteb/arxiv-clustering-p2p name: MTEB ArxivClusteringP2P config: default split: test revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d metrics: - type: v_measure value: 45.93034494751465 - task: type: Clustering dataset: type: mteb/arxiv-clustering-s2s name: MTEB ArxivClusteringS2S config: default split: test revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53 metrics: - type: v_measure value: 36.64579480054327 - task: type: Reranking dataset: type: mteb/askubuntudupquestions-reranking name: MTEB AskUbuntuDupQuestions config: default split: test revision: 2000358ca161889fa9c082cb41daa8dcfb161a54 metrics: - type: map value: 60.601310529222054 - type: mrr value: 75.04484896451656 - task: type: STS dataset: type: mteb/biosses-sts name: MTEB BIOSSES config: default split: test revision: d3fb88f8f02e40887cd149695127462bbcf29b4a metrics: - type: cos_sim_pearson value: 88.57797718095814 - type: cos_sim_spearman value: 86.47064499110101 - type: euclidean_pearson value: 87.4559602783142 - type: euclidean_spearman value: 86.47064499110101 - type: manhattan_pearson value: 87.7232764230245 - type: manhattan_spearman value: 86.91222131777742 - task: type: Classification dataset: type: mteb/banking77 name: MTEB Banking77Classification config: default split: test revision: 0fd18e25b25c072e09e0d92ab615fda904d66300 metrics: - type: accuracy value: 84.5422077922078 - type: f1 value: 84.47657456950589 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-p2p name: MTEB BiorxivClusteringP2P config: default split: test revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40 metrics: - type: v_measure value: 38.48953561974464 - task: type: Clustering dataset: type: mteb/biorxiv-clustering-s2s name: MTEB BiorxivClusteringS2S config: default split: test revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908 metrics: - type: v_measure value: 32.75995857510105 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackAndroidRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.008000000000003 - type: map_at_10 value: 39.51 - type: map_at_100 value: 40.841 - type: map_at_1000 value: 40.973 - type: map_at_3 value: 36.248999999999995 - type: map_at_5 value: 38.096999999999994 - type: mrr_at_1 value: 36.481 - type: mrr_at_10 value: 44.818000000000005 - type: mrr_at_100 value: 45.64 - type: mrr_at_1000 value: 45.687 - type: mrr_at_3 value: 42.036 - type: mrr_at_5 value: 43.782 - type: ndcg_at_1 value: 36.481 - type: ndcg_at_10 value: 45.152 - type: ndcg_at_100 value: 50.449 - type: ndcg_at_1000 value: 52.76499999999999 - type: ndcg_at_3 value: 40.161 - type: ndcg_at_5 value: 42.577999999999996 - type: precision_at_1 value: 36.481 - type: precision_at_10 value: 8.369 - type: precision_at_100 value: 1.373 - type: precision_at_1000 value: 0.186 - type: precision_at_3 value: 18.693 - type: precision_at_5 value: 13.533999999999999 - type: recall_at_1 value: 30.008000000000003 - type: recall_at_10 value: 56.108999999999995 - type: recall_at_100 value: 78.55499999999999 - type: recall_at_1000 value: 93.659 - type: recall_at_3 value: 41.754999999999995 - type: recall_at_5 value: 48.296 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackEnglishRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 30.262 - type: map_at_10 value: 40.139 - type: map_at_100 value: 41.394 - type: map_at_1000 value: 41.526 - type: map_at_3 value: 37.155 - type: map_at_5 value: 38.785 - type: mrr_at_1 value: 38.153 - type: mrr_at_10 value: 46.369 - type: mrr_at_100 value: 47.072 - type: mrr_at_1000 value: 47.111999999999995 - type: mrr_at_3 value: 44.268 - type: mrr_at_5 value: 45.389 - type: ndcg_at_1 value: 38.153 - type: ndcg_at_10 value: 45.925 - type: ndcg_at_100 value: 50.394000000000005 - type: ndcg_at_1000 value: 52.37500000000001 - type: ndcg_at_3 value: 41.754000000000005 - type: ndcg_at_5 value: 43.574 - type: precision_at_1 value: 38.153 - type: precision_at_10 value: 8.796 - type: precision_at_100 value: 1.432 - type: precision_at_1000 value: 0.189 - type: precision_at_3 value: 20.318 - type: precision_at_5 value: 14.395 - type: recall_at_1 value: 30.262 - type: recall_at_10 value: 55.72200000000001 - type: recall_at_100 value: 74.97500000000001 - type: recall_at_1000 value: 87.342 - type: recall_at_3 value: 43.129 - type: recall_at_5 value: 48.336 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGamingRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 39.951 - type: map_at_10 value: 51.248000000000005 - type: map_at_100 value: 52.188 - type: map_at_1000 value: 52.247 - type: map_at_3 value: 48.211 - type: map_at_5 value: 49.797000000000004 - type: mrr_at_1 value: 45.329 - type: mrr_at_10 value: 54.749 - type: mrr_at_100 value: 55.367999999999995 - type: mrr_at_1000 value: 55.400000000000006 - type: mrr_at_3 value: 52.382 - type: mrr_at_5 value: 53.649 - type: ndcg_at_1 value: 45.329 - type: ndcg_at_10 value: 56.847 - type: ndcg_at_100 value: 60.738 - type: ndcg_at_1000 value: 61.976 - type: ndcg_at_3 value: 51.59 - type: ndcg_at_5 value: 53.915 - type: precision_at_1 value: 45.329 - type: precision_at_10 value: 8.959 - type: precision_at_100 value: 1.187 - type: precision_at_1000 value: 0.134 - type: precision_at_3 value: 22.612 - type: precision_at_5 value: 15.273 - type: recall_at_1 value: 39.951 - type: recall_at_10 value: 70.053 - type: recall_at_100 value: 86.996 - type: recall_at_1000 value: 95.707 - type: recall_at_3 value: 56.032000000000004 - type: recall_at_5 value: 61.629999999999995 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackGisRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.566 - type: map_at_10 value: 33.207 - type: map_at_100 value: 34.166000000000004 - type: map_at_1000 value: 34.245 - type: map_at_3 value: 30.94 - type: map_at_5 value: 32.01 - type: mrr_at_1 value: 27.345000000000002 - type: mrr_at_10 value: 35.193000000000005 - type: mrr_at_100 value: 35.965 - type: mrr_at_1000 value: 36.028999999999996 - type: mrr_at_3 value: 32.806000000000004 - type: mrr_at_5 value: 34.021 - type: ndcg_at_1 value: 27.345000000000002 - type: ndcg_at_10 value: 37.891999999999996 - type: ndcg_at_100 value: 42.664 - type: ndcg_at_1000 value: 44.757000000000005 - type: ndcg_at_3 value: 33.123000000000005 - type: ndcg_at_5 value: 35.035 - type: precision_at_1 value: 27.345000000000002 - type: precision_at_10 value: 5.763 - type: precision_at_100 value: 0.859 - type: precision_at_1000 value: 0.108 - type: precision_at_3 value: 13.71 - type: precision_at_5 value: 9.401 - type: recall_at_1 value: 25.566 - type: recall_at_10 value: 50.563 - type: recall_at_100 value: 72.86399999999999 - type: recall_at_1000 value: 88.68599999999999 - type: recall_at_3 value: 37.43 - type: recall_at_5 value: 41.894999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackMathematicaRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.663 - type: map_at_10 value: 23.552 - type: map_at_100 value: 24.538 - type: map_at_1000 value: 24.661 - type: map_at_3 value: 21.085 - type: map_at_5 value: 22.391 - type: mrr_at_1 value: 20.025000000000002 - type: mrr_at_10 value: 27.643 - type: mrr_at_100 value: 28.499999999999996 - type: mrr_at_1000 value: 28.582 - type: mrr_at_3 value: 25.083 - type: mrr_at_5 value: 26.544 - type: ndcg_at_1 value: 20.025000000000002 - type: ndcg_at_10 value: 28.272000000000002 - type: ndcg_at_100 value: 33.353 - type: ndcg_at_1000 value: 36.454 - type: ndcg_at_3 value: 23.579 - type: ndcg_at_5 value: 25.685000000000002 - type: precision_at_1 value: 20.025000000000002 - type: precision_at_10 value: 5.187 - type: precision_at_100 value: 0.897 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 10.987 - type: precision_at_5 value: 8.06 - type: recall_at_1 value: 16.663 - type: recall_at_10 value: 38.808 - type: recall_at_100 value: 61.305 - type: recall_at_1000 value: 83.571 - type: recall_at_3 value: 25.907999999999998 - type: recall_at_5 value: 31.214 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackPhysicsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 27.695999999999998 - type: map_at_10 value: 37.018 - type: map_at_100 value: 38.263000000000005 - type: map_at_1000 value: 38.371 - type: map_at_3 value: 34.226 - type: map_at_5 value: 35.809999999999995 - type: mrr_at_1 value: 32.916000000000004 - type: mrr_at_10 value: 42.067 - type: mrr_at_100 value: 42.925000000000004 - type: mrr_at_1000 value: 42.978 - type: mrr_at_3 value: 39.637 - type: mrr_at_5 value: 41.134 - type: ndcg_at_1 value: 32.916000000000004 - type: ndcg_at_10 value: 42.539 - type: ndcg_at_100 value: 47.873 - type: ndcg_at_1000 value: 50.08200000000001 - type: ndcg_at_3 value: 37.852999999999994 - type: ndcg_at_5 value: 40.201 - type: precision_at_1 value: 32.916000000000004 - type: precision_at_10 value: 7.5840000000000005 - type: precision_at_100 value: 1.199 - type: precision_at_1000 value: 0.155 - type: precision_at_3 value: 17.485 - type: precision_at_5 value: 12.512 - type: recall_at_1 value: 27.695999999999998 - type: recall_at_10 value: 53.638 - type: recall_at_100 value: 76.116 - type: recall_at_1000 value: 91.069 - type: recall_at_3 value: 41.13 - type: recall_at_5 value: 46.872 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackProgrammersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.108 - type: map_at_10 value: 33.372 - type: map_at_100 value: 34.656 - type: map_at_1000 value: 34.768 - type: map_at_3 value: 30.830999999999996 - type: map_at_5 value: 32.204 - type: mrr_at_1 value: 29.110000000000003 - type: mrr_at_10 value: 37.979 - type: mrr_at_100 value: 38.933 - type: mrr_at_1000 value: 38.988 - type: mrr_at_3 value: 35.731 - type: mrr_at_5 value: 36.963 - type: ndcg_at_1 value: 29.110000000000003 - type: ndcg_at_10 value: 38.635000000000005 - type: ndcg_at_100 value: 44.324999999999996 - type: ndcg_at_1000 value: 46.747 - type: ndcg_at_3 value: 34.37 - type: ndcg_at_5 value: 36.228 - type: precision_at_1 value: 29.110000000000003 - type: precision_at_10 value: 6.963 - type: precision_at_100 value: 1.146 - type: precision_at_1000 value: 0.152 - type: precision_at_3 value: 16.400000000000002 - type: precision_at_5 value: 11.552999999999999 - type: recall_at_1 value: 24.108 - type: recall_at_10 value: 49.597 - type: recall_at_100 value: 73.88900000000001 - type: recall_at_1000 value: 90.62400000000001 - type: recall_at_3 value: 37.662 - type: recall_at_5 value: 42.565 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 25.00791666666667 - type: map_at_10 value: 33.287749999999996 - type: map_at_100 value: 34.41141666666667 - type: map_at_1000 value: 34.52583333333333 - type: map_at_3 value: 30.734416666666668 - type: map_at_5 value: 32.137166666666666 - type: mrr_at_1 value: 29.305666666666664 - type: mrr_at_10 value: 37.22966666666666 - type: mrr_at_100 value: 38.066583333333334 - type: mrr_at_1000 value: 38.12616666666667 - type: mrr_at_3 value: 34.92275 - type: mrr_at_5 value: 36.23333333333334 - type: ndcg_at_1 value: 29.305666666666664 - type: ndcg_at_10 value: 38.25533333333333 - type: ndcg_at_100 value: 43.25266666666666 - type: ndcg_at_1000 value: 45.63583333333334 - type: ndcg_at_3 value: 33.777166666666666 - type: ndcg_at_5 value: 35.85 - type: precision_at_1 value: 29.305666666666664 - type: precision_at_10 value: 6.596416666666667 - type: precision_at_100 value: 1.0784166666666668 - type: precision_at_1000 value: 0.14666666666666664 - type: precision_at_3 value: 15.31075 - type: precision_at_5 value: 10.830916666666667 - type: recall_at_1 value: 25.00791666666667 - type: recall_at_10 value: 49.10933333333333 - type: recall_at_100 value: 71.09216666666667 - type: recall_at_1000 value: 87.77725000000001 - type: recall_at_3 value: 36.660916666666665 - type: recall_at_5 value: 41.94149999999999 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackStatsRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 23.521 - type: map_at_10 value: 30.043 - type: map_at_100 value: 30.936000000000003 - type: map_at_1000 value: 31.022 - type: map_at_3 value: 27.926000000000002 - type: map_at_5 value: 29.076999999999998 - type: mrr_at_1 value: 26.227 - type: mrr_at_10 value: 32.822 - type: mrr_at_100 value: 33.61 - type: mrr_at_1000 value: 33.672000000000004 - type: mrr_at_3 value: 30.776999999999997 - type: mrr_at_5 value: 31.866 - type: ndcg_at_1 value: 26.227 - type: ndcg_at_10 value: 34.041 - type: ndcg_at_100 value: 38.394 - type: ndcg_at_1000 value: 40.732 - type: ndcg_at_3 value: 30.037999999999997 - type: ndcg_at_5 value: 31.845000000000002 - type: precision_at_1 value: 26.227 - type: precision_at_10 value: 5.244999999999999 - type: precision_at_100 value: 0.808 - type: precision_at_1000 value: 0.107 - type: precision_at_3 value: 12.679000000000002 - type: precision_at_5 value: 8.773 - type: recall_at_1 value: 23.521 - type: recall_at_10 value: 43.633 - type: recall_at_100 value: 63.126000000000005 - type: recall_at_1000 value: 80.765 - type: recall_at_3 value: 32.614 - type: recall_at_5 value: 37.15 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackTexRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 16.236 - type: map_at_10 value: 22.898 - type: map_at_100 value: 23.878 - type: map_at_1000 value: 24.009 - type: map_at_3 value: 20.87 - type: map_at_5 value: 22.025 - type: mrr_at_1 value: 19.339000000000002 - type: mrr_at_10 value: 26.382 - type: mrr_at_100 value: 27.245 - type: mrr_at_1000 value: 27.33 - type: mrr_at_3 value: 24.386 - type: mrr_at_5 value: 25.496000000000002 - type: ndcg_at_1 value: 19.339000000000002 - type: ndcg_at_10 value: 27.139999999999997 - type: ndcg_at_100 value: 31.944 - type: ndcg_at_1000 value: 35.077999999999996 - type: ndcg_at_3 value: 23.424 - type: ndcg_at_5 value: 25.188 - type: precision_at_1 value: 19.339000000000002 - type: precision_at_10 value: 4.8309999999999995 - type: precision_at_100 value: 0.845 - type: precision_at_1000 value: 0.128 - type: precision_at_3 value: 10.874 - type: precision_at_5 value: 7.825 - type: recall_at_1 value: 16.236 - type: recall_at_10 value: 36.513 - type: recall_at_100 value: 57.999 - type: recall_at_1000 value: 80.512 - type: recall_at_3 value: 26.179999999999996 - type: recall_at_5 value: 30.712 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackUnixRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 24.11 - type: map_at_10 value: 31.566 - type: map_at_100 value: 32.647 - type: map_at_1000 value: 32.753 - type: map_at_3 value: 29.24 - type: map_at_5 value: 30.564999999999998 - type: mrr_at_1 value: 28.265 - type: mrr_at_10 value: 35.504000000000005 - type: mrr_at_100 value: 36.436 - type: mrr_at_1000 value: 36.503 - type: mrr_at_3 value: 33.349000000000004 - type: mrr_at_5 value: 34.622 - type: ndcg_at_1 value: 28.265 - type: ndcg_at_10 value: 36.192 - type: ndcg_at_100 value: 41.388000000000005 - type: ndcg_at_1000 value: 43.948 - type: ndcg_at_3 value: 31.959 - type: ndcg_at_5 value: 33.998 - type: precision_at_1 value: 28.265 - type: precision_at_10 value: 5.989 - type: precision_at_100 value: 0.9650000000000001 - type: precision_at_1000 value: 0.13 - type: precision_at_3 value: 14.335 - type: precision_at_5 value: 10.112 - type: recall_at_1 value: 24.11 - type: recall_at_10 value: 46.418 - type: recall_at_100 value: 69.314 - type: recall_at_1000 value: 87.397 - type: recall_at_3 value: 34.724 - type: recall_at_5 value: 39.925 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWebmastersRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 22.091 - type: map_at_10 value: 29.948999999999998 - type: map_at_100 value: 31.502000000000002 - type: map_at_1000 value: 31.713 - type: map_at_3 value: 27.464 - type: map_at_5 value: 28.968 - type: mrr_at_1 value: 26.482 - type: mrr_at_10 value: 34.009 - type: mrr_at_100 value: 35.081 - type: mrr_at_1000 value: 35.138000000000005 - type: mrr_at_3 value: 31.785000000000004 - type: mrr_at_5 value: 33.178999999999995 - type: ndcg_at_1 value: 26.482 - type: ndcg_at_10 value: 35.008 - type: ndcg_at_100 value: 41.272999999999996 - type: ndcg_at_1000 value: 43.972 - type: ndcg_at_3 value: 30.804 - type: ndcg_at_5 value: 33.046 - type: precision_at_1 value: 26.482 - type: precision_at_10 value: 6.462 - type: precision_at_100 value: 1.431 - type: precision_at_1000 value: 0.22899999999999998 - type: precision_at_3 value: 14.360999999999999 - type: precision_at_5 value: 10.474 - type: recall_at_1 value: 22.091 - type: recall_at_10 value: 45.125 - type: recall_at_100 value: 72.313 - type: recall_at_1000 value: 89.503 - type: recall_at_3 value: 33.158 - type: recall_at_5 value: 39.086999999999996 - task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADupstackWordpressRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 19.883 - type: map_at_10 value: 26.951000000000004 - type: map_at_100 value: 27.927999999999997 - type: map_at_1000 value: 28.022000000000002 - type: map_at_3 value: 24.616 - type: map_at_5 value: 25.917 - type: mrr_at_1 value: 21.996 - type: mrr_at_10 value: 29.221000000000004 - type: mrr_at_100 value: 30.024 - type: mrr_at_1000 value: 30.095 - type: mrr_at_3 value: 26.833000000000002 - type: mrr_at_5 value: 28.155 - type: ndcg_at_1 value: 21.996 - type: ndcg_at_10 value: 31.421 - type: ndcg_at_100 value: 36.237 - type: ndcg_at_1000 value: 38.744 - type: ndcg_at_3 value: 26.671 - type: ndcg_at_5 value: 28.907 - type: precision_at_1 value: 21.996 - type: precision_at_10 value: 5.009 - type: precision_at_100 value: 0.799 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 11.275 - type: precision_at_5 value: 8.059 - type: recall_at_1 value: 19.883 - type: recall_at_10 value: 43.132999999999996 - type: recall_at_100 value: 65.654 - type: recall_at_1000 value: 84.492 - type: recall_at_3 value: 30.209000000000003 - type: recall_at_5 value: 35.616 - task: type: Retrieval dataset: type: climate-fever name: MTEB ClimateFEVER config: default split: test revision: None metrics: - type: map_at_1 value: 17.756 - type: map_at_10 value: 30.378 - type: map_at_100 value: 32.537 - type: map_at_1000 value: 32.717 - type: map_at_3 value: 25.599 - type: map_at_5 value: 28.372999999999998 - type: mrr_at_1 value: 41.303 - type: mrr_at_10 value: 53.483999999999995 - type: mrr_at_100 value: 54.106 - type: mrr_at_1000 value: 54.127 - type: mrr_at_3 value: 50.315 - type: mrr_at_5 value: 52.396 - type: ndcg_at_1 value: 41.303 - type: ndcg_at_10 value: 40.503 - type: ndcg_at_100 value: 47.821000000000005 - type: ndcg_at_1000 value: 50.788 - type: ndcg_at_3 value: 34.364 - type: ndcg_at_5 value: 36.818 - type: precision_at_1 value: 41.303 - type: precision_at_10 value: 12.463000000000001 - type: precision_at_100 value: 2.037 - type: precision_at_1000 value: 0.26 - type: precision_at_3 value: 25.798 - type: precision_at_5 value: 19.896 - type: recall_at_1 value: 17.756 - type: recall_at_10 value: 46.102 - type: recall_at_100 value: 70.819 - type: recall_at_1000 value: 87.21799999999999 - type: recall_at_3 value: 30.646 - type: recall_at_5 value: 38.022 - task: type: Retrieval dataset: type: dbpedia-entity name: MTEB DBPedia config: default split: test revision: None metrics: - type: map_at_1 value: 9.033 - type: map_at_10 value: 20.584 - type: map_at_100 value: 29.518 - type: map_at_1000 value: 31.186000000000003 - type: map_at_3 value: 14.468 - type: map_at_5 value: 17.177 - type: mrr_at_1 value: 69.75 - type: mrr_at_10 value: 77.025 - type: mrr_at_100 value: 77.36699999999999 - type: mrr_at_1000 value: 77.373 - type: mrr_at_3 value: 75.583 - type: mrr_at_5 value: 76.396 - type: ndcg_at_1 value: 58.5 - type: ndcg_at_10 value: 45.033 - type: ndcg_at_100 value: 49.071 - type: ndcg_at_1000 value: 56.056 - type: ndcg_at_3 value: 49.936 - type: ndcg_at_5 value: 47.471999999999994 - type: precision_at_1 value: 69.75 - type: precision_at_10 value: 35.775 - type: precision_at_100 value: 11.594999999999999 - type: precision_at_1000 value: 2.062 - type: precision_at_3 value: 52.5 - type: precision_at_5 value: 45.300000000000004 - type: recall_at_1 value: 9.033 - type: recall_at_10 value: 26.596999999999998 - type: recall_at_100 value: 54.607000000000006 - type: recall_at_1000 value: 76.961 - type: recall_at_3 value: 15.754999999999999 - type: recall_at_5 value: 20.033 - task: type: Classification dataset: type: mteb/emotion name: MTEB EmotionClassification config: default split: test revision: 4f58c6b202a23cf9a4da393831edf4f9183cad37 metrics: - type: accuracy value: 48.345000000000006 - type: f1 value: 43.4514918068706 - task: type: Retrieval dataset: type: fever name: MTEB FEVER config: default split: test revision: None metrics: - type: map_at_1 value: 71.29100000000001 - type: map_at_10 value: 81.059 - type: map_at_100 value: 81.341 - type: map_at_1000 value: 81.355 - type: map_at_3 value: 79.74799999999999 - type: map_at_5 value: 80.612 - type: mrr_at_1 value: 76.40299999999999 - type: mrr_at_10 value: 84.615 - type: mrr_at_100 value: 84.745 - type: mrr_at_1000 value: 84.748 - type: mrr_at_3 value: 83.776 - type: mrr_at_5 value: 84.343 - type: ndcg_at_1 value: 76.40299999999999 - type: ndcg_at_10 value: 84.981 - type: ndcg_at_100 value: 86.00999999999999 - type: ndcg_at_1000 value: 86.252 - type: ndcg_at_3 value: 82.97 - type: ndcg_at_5 value: 84.152 - type: precision_at_1 value: 76.40299999999999 - type: precision_at_10 value: 10.446 - type: precision_at_100 value: 1.1199999999999999 - type: precision_at_1000 value: 0.116 - type: precision_at_3 value: 32.147999999999996 - type: precision_at_5 value: 20.135 - type: recall_at_1 value: 71.29100000000001 - type: recall_at_10 value: 93.232 - type: recall_at_100 value: 97.363 - type: recall_at_1000 value: 98.905 - type: recall_at_3 value: 87.893 - type: recall_at_5 value: 90.804 - task: type: Retrieval dataset: type: fiqa name: MTEB FiQA2018 config: default split: test revision: None metrics: - type: map_at_1 value: 18.667 - type: map_at_10 value: 30.853 - type: map_at_100 value: 32.494 - type: map_at_1000 value: 32.677 - type: map_at_3 value: 26.91 - type: map_at_5 value: 29.099000000000004 - type: mrr_at_1 value: 37.191 - type: mrr_at_10 value: 46.171 - type: mrr_at_100 value: 47.056 - type: mrr_at_1000 value: 47.099000000000004 - type: mrr_at_3 value: 44.059 - type: mrr_at_5 value: 45.147 - type: ndcg_at_1 value: 37.191 - type: ndcg_at_10 value: 38.437 - type: ndcg_at_100 value: 44.62 - type: ndcg_at_1000 value: 47.795 - type: ndcg_at_3 value: 35.003 - type: ndcg_at_5 value: 36.006 - type: precision_at_1 value: 37.191 - type: precision_at_10 value: 10.586 - type: precision_at_100 value: 1.688 - type: precision_at_1000 value: 0.22699999999999998 - type: precision_at_3 value: 23.302 - type: precision_at_5 value: 17.006 - type: recall_at_1 value: 18.667 - type: recall_at_10 value: 45.367000000000004 - type: recall_at_100 value: 68.207 - type: recall_at_1000 value: 87.072 - type: recall_at_3 value: 32.129000000000005 - type: recall_at_5 value: 37.719 - task: type: Retrieval dataset: type: hotpotqa name: MTEB HotpotQA config: default split: test revision: None metrics: - type: map_at_1 value: 39.494 - type: map_at_10 value: 66.223 - type: map_at_100 value: 67.062 - type: map_at_1000 value: 67.11500000000001 - type: map_at_3 value: 62.867 - type: map_at_5 value: 64.994 - type: mrr_at_1 value: 78.987 - type: mrr_at_10 value: 84.585 - type: mrr_at_100 value: 84.773 - type: mrr_at_1000 value: 84.77900000000001 - type: mrr_at_3 value: 83.592 - type: mrr_at_5 value: 84.235 - type: ndcg_at_1 value: 78.987 - type: ndcg_at_10 value: 73.64 - type: ndcg_at_100 value: 76.519 - type: ndcg_at_1000 value: 77.51 - type: ndcg_at_3 value: 68.893 - type: ndcg_at_5 value: 71.585 - type: precision_at_1 value: 78.987 - type: precision_at_10 value: 15.529000000000002 - type: precision_at_100 value: 1.7770000000000001 - type: precision_at_1000 value: 0.191 - type: precision_at_3 value: 44.808 - type: precision_at_5 value: 29.006999999999998 - type: recall_at_1 value: 39.494 - type: recall_at_10 value: 77.643 - type: recall_at_100 value: 88.825 - type: recall_at_1000 value: 95.321 - type: recall_at_3 value: 67.211 - type: recall_at_5 value: 72.519 - task: type: Classification dataset: type: mteb/imdb name: MTEB ImdbClassification config: default split: test revision: 3d86128a09e091d6018b6d26cad27f2739fc2db7 metrics: - type: accuracy value: 85.55959999999999 - type: ap value: 80.7246500384617 - type: f1 value: 85.52336485065454 - task: type: Retrieval dataset: type: msmarco name: MTEB MSMARCO config: default split: dev revision: None metrics: - type: map_at_1 value: 23.631 - type: map_at_10 value: 36.264 - type: map_at_100 value: 37.428 - type: map_at_1000 value: 37.472 - type: map_at_3 value: 32.537 - type: map_at_5 value: 34.746 - type: mrr_at_1 value: 24.312 - type: mrr_at_10 value: 36.858000000000004 - type: mrr_at_100 value: 37.966 - type: mrr_at_1000 value: 38.004 - type: mrr_at_3 value: 33.188 - type: mrr_at_5 value: 35.367 - type: ndcg_at_1 value: 24.312 - type: ndcg_at_10 value: 43.126999999999995 - type: ndcg_at_100 value: 48.642 - type: ndcg_at_1000 value: 49.741 - type: ndcg_at_3 value: 35.589 - type: ndcg_at_5 value: 39.515 - type: precision_at_1 value: 24.312 - type: precision_at_10 value: 6.699 - type: precision_at_100 value: 0.9450000000000001 - type: precision_at_1000 value: 0.104 - type: precision_at_3 value: 15.153 - type: precision_at_5 value: 11.065999999999999 - type: recall_at_1 value: 23.631 - type: recall_at_10 value: 64.145 - type: recall_at_100 value: 89.41 - type: recall_at_1000 value: 97.83500000000001 - type: recall_at_3 value: 43.769000000000005 - type: recall_at_5 value: 53.169 - task: type: Classification dataset: type: mteb/mtop_domain name: MTEB MTOPDomainClassification (en) config: en split: test revision: d80d48c1eb48d3562165c59d59d0034df9fff0bf metrics: - type: accuracy value: 93.4108527131783 - type: f1 value: 93.1415880261038 - task: type: Classification dataset: type: mteb/mtop_intent name: MTEB MTOPIntentClassification (en) config: en split: test revision: ae001d0e6b1228650b7bd1c2c65fb50ad11a8aba metrics: - type: accuracy value: 77.24806201550388 - type: f1 value: 60.531916308197175 - task: type: Classification dataset: type: mteb/amazon_massive_intent name: MTEB MassiveIntentClassification (en) config: en split: test revision: 31efe3c427b0bae9c22cbb560b8f15491cc6bed7 metrics: - type: accuracy value: 73.71553463349024 - type: f1 value: 71.70753174900791 - task: type: Classification dataset: type: mteb/amazon_massive_scenario name: MTEB MassiveScenarioClassification (en) config: en split: test revision: 7d571f92784cd94a019292a1f45445077d0ef634 metrics: - type: accuracy value: 77.79757901815736 - type: f1 value: 77.83719850433258 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-p2p name: MTEB MedrxivClusteringP2P config: default split: test revision: e7a26af6f3ae46b30dde8737f02c07b1505bcc73 metrics: - type: v_measure value: 33.74193296622113 - task: type: Clustering dataset: type: mteb/medrxiv-clustering-s2s name: MTEB MedrxivClusteringS2S config: default split: test revision: 35191c8c0dca72d8ff3efcd72aa802307d469663 metrics: - type: v_measure value: 30.64257594108566 - task: type: Reranking dataset: type: mteb/mind_small name: MTEB MindSmallReranking config: default split: test revision: 3bdac13927fdc888b903db93b2ffdbd90b295a69 metrics: - type: map value: 30.811018518883625 - type: mrr value: 31.910376577445003 - task: type: Retrieval dataset: type: nfcorpus name: MTEB NFCorpus config: default split: test revision: None metrics: - type: map_at_1 value: 5.409 - type: map_at_10 value: 13.093 - type: map_at_100 value: 16.256999999999998 - type: map_at_1000 value: 17.617 - type: map_at_3 value: 9.555 - type: map_at_5 value: 11.428 - type: mrr_at_1 value: 45.201 - type: mrr_at_10 value: 54.179 - type: mrr_at_100 value: 54.812000000000005 - type: mrr_at_1000 value: 54.840999999999994 - type: mrr_at_3 value: 51.909000000000006 - type: mrr_at_5 value: 53.519000000000005 - type: ndcg_at_1 value: 43.189 - type: ndcg_at_10 value: 35.028 - type: ndcg_at_100 value: 31.226 - type: ndcg_at_1000 value: 39.678000000000004 - type: ndcg_at_3 value: 40.596 - type: ndcg_at_5 value: 38.75 - type: precision_at_1 value: 44.582 - type: precision_at_10 value: 25.974999999999998 - type: precision_at_100 value: 7.793 - type: precision_at_1000 value: 2.036 - type: precision_at_3 value: 38.493 - type: precision_at_5 value: 33.994 - type: recall_at_1 value: 5.409 - type: recall_at_10 value: 16.875999999999998 - type: recall_at_100 value: 30.316 - type: recall_at_1000 value: 60.891 - type: recall_at_3 value: 10.688 - type: recall_at_5 value: 13.832 - task: type: Retrieval dataset: type: nq name: MTEB NQ config: default split: test revision: None metrics: - type: map_at_1 value: 36.375 - type: map_at_10 value: 51.991 - type: map_at_100 value: 52.91400000000001 - type: map_at_1000 value: 52.93600000000001 - type: map_at_3 value: 48.014 - type: map_at_5 value: 50.381 - type: mrr_at_1 value: 40.759 - type: mrr_at_10 value: 54.617000000000004 - type: mrr_at_100 value: 55.301 - type: mrr_at_1000 value: 55.315000000000005 - type: mrr_at_3 value: 51.516 - type: mrr_at_5 value: 53.435 - type: ndcg_at_1 value: 40.759 - type: ndcg_at_10 value: 59.384 - type: ndcg_at_100 value: 63.157 - type: ndcg_at_1000 value: 63.654999999999994 - type: ndcg_at_3 value: 52.114000000000004 - type: ndcg_at_5 value: 55.986000000000004 - type: precision_at_1 value: 40.759 - type: precision_at_10 value: 9.411999999999999 - type: precision_at_100 value: 1.153 - type: precision_at_1000 value: 0.12 - type: precision_at_3 value: 23.329 - type: precision_at_5 value: 16.256999999999998 - type: recall_at_1 value: 36.375 - type: recall_at_10 value: 79.053 - type: recall_at_100 value: 95.167 - type: recall_at_1000 value: 98.82 - type: recall_at_3 value: 60.475 - type: recall_at_5 value: 69.327 - task: type: Retrieval dataset: type: quora name: MTEB QuoraRetrieval config: default split: test revision: None metrics: - type: map_at_1 value: 70.256 - type: map_at_10 value: 83.8 - type: map_at_100 value: 84.425 - type: map_at_1000 value: 84.444 - type: map_at_3 value: 80.906 - type: map_at_5 value: 82.717 - type: mrr_at_1 value: 80.97999999999999 - type: mrr_at_10 value: 87.161 - type: mrr_at_100 value: 87.262 - type: mrr_at_1000 value: 87.263 - type: mrr_at_3 value: 86.175 - type: mrr_at_5 value: 86.848 - type: ndcg_at_1 value: 80.97999999999999 - type: ndcg_at_10 value: 87.697 - type: ndcg_at_100 value: 88.959 - type: ndcg_at_1000 value: 89.09899999999999 - type: ndcg_at_3 value: 84.83800000000001 - type: ndcg_at_5 value: 86.401 - type: precision_at_1 value: 80.97999999999999 - type: precision_at_10 value: 13.261000000000001 - type: precision_at_100 value: 1.5150000000000001 - type: precision_at_1000 value: 0.156 - type: precision_at_3 value: 37.01 - type: precision_at_5 value: 24.298000000000002 - type: recall_at_1 value: 70.256 - type: recall_at_10 value: 94.935 - type: recall_at_100 value: 99.274 - type: recall_at_1000 value: 99.928 - type: recall_at_3 value: 86.602 - type: recall_at_5 value: 91.133 - task: type: Clustering dataset: type: mteb/reddit-clustering name: MTEB RedditClustering config: default split: test revision: 24640382cdbf8abc73003fb0fa6d111a705499eb metrics: - type: v_measure value: 56.322692497613104 - task: type: Clustering dataset: type: mteb/reddit-clustering-p2p name: MTEB RedditClusteringP2P config: default split: test revision: 282350215ef01743dc01b456c7f5241fa8937f16 metrics: - type: v_measure value: 61.895813503775074 - task: type: Retrieval dataset: type: scidocs name: MTEB SCIDOCS config: default split: test revision: None metrics: - type: map_at_1 value: 4.338 - type: map_at_10 value: 10.767 - type: map_at_100 value: 12.537999999999998 - type: map_at_1000 value: 12.803999999999998 - type: map_at_3 value: 7.788 - type: map_at_5 value: 9.302000000000001 - type: mrr_at_1 value: 21.4 - type: mrr_at_10 value: 31.637999999999998 - type: mrr_at_100 value: 32.688 - type: mrr_at_1000 value: 32.756 - type: mrr_at_3 value: 28.433000000000003 - type: mrr_at_5 value: 30.178 - type: ndcg_at_1 value: 21.4 - type: ndcg_at_10 value: 18.293 - type: ndcg_at_100 value: 25.274 - type: ndcg_at_1000 value: 30.284 - type: ndcg_at_3 value: 17.391000000000002 - type: ndcg_at_5 value: 15.146999999999998 - type: precision_at_1 value: 21.4 - type: precision_at_10 value: 9.48 - type: precision_at_100 value: 1.949 - type: precision_at_1000 value: 0.316 - type: precision_at_3 value: 16.167 - type: precision_at_5 value: 13.22 - type: recall_at_1 value: 4.338 - type: recall_at_10 value: 19.213 - type: recall_at_100 value: 39.562999999999995 - type: recall_at_1000 value: 64.08 - type: recall_at_3 value: 9.828000000000001 - type: recall_at_5 value: 13.383000000000001 - task: type: STS dataset: type: mteb/sickr-sts name: MTEB SICK-R config: default split: test revision: a6ea5a8cab320b040a23452cc28066d9beae2cee metrics: - type: cos_sim_pearson value: 82.42568163642142 - type: cos_sim_spearman value: 78.5797159641342 - type: euclidean_pearson value: 80.22151260811604 - type: euclidean_spearman value: 78.5797151953878 - type: manhattan_pearson value: 80.21224215864788 - type: manhattan_spearman value: 78.55641478381344 - task: type: STS dataset: type: mteb/sts12-sts name: MTEB STS12 config: default split: test revision: a0d554a64d88156834ff5ae9920b964011b16384 metrics: - type: cos_sim_pearson value: 85.44020710812569 - type: cos_sim_spearman value: 78.91631735081286 - type: euclidean_pearson value: 81.64188964182102 - type: euclidean_spearman value: 78.91633286881678 - type: manhattan_pearson value: 81.69294748512496 - type: manhattan_spearman value: 78.93438558002656 - task: type: STS dataset: type: mteb/sts13-sts name: MTEB STS13 config: default split: test revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca metrics: - type: cos_sim_pearson value: 84.27165426412311 - type: cos_sim_spearman value: 85.40429140249618 - type: euclidean_pearson value: 84.7509580724893 - type: euclidean_spearman value: 85.40429140249618 - type: manhattan_pearson value: 84.76488289321308 - type: manhattan_spearman value: 85.4256793698708 - task: type: STS dataset: type: mteb/sts14-sts name: MTEB STS14 config: default split: test revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375 metrics: - type: cos_sim_pearson value: 83.138851760732 - type: cos_sim_spearman value: 81.64101363896586 - type: euclidean_pearson value: 82.55165038934942 - type: euclidean_spearman value: 81.64105257080502 - type: manhattan_pearson value: 82.52802949883335 - type: manhattan_spearman value: 81.61255430718158 - task: type: STS dataset: type: mteb/sts15-sts name: MTEB STS15 config: default split: test revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3 metrics: - type: cos_sim_pearson value: 86.0654695484029 - type: cos_sim_spearman value: 87.20408521902229 - type: euclidean_pearson value: 86.8110651362115 - type: euclidean_spearman value: 87.20408521902229 - type: manhattan_pearson value: 86.77984656478691 - type: manhattan_spearman value: 87.1719947099227 - task: type: STS dataset: type: mteb/sts16-sts name: MTEB STS16 config: default split: test revision: 4d8694f8f0e0100860b497b999b3dbed754a0513 metrics: - type: cos_sim_pearson value: 83.77823915496512 - type: cos_sim_spearman value: 85.43566325729779 - type: euclidean_pearson value: 84.5396956658821 - type: euclidean_spearman value: 85.43566325729779 - type: manhattan_pearson value: 84.5665398848169 - type: manhattan_spearman value: 85.44375870303232 - task: type: STS dataset: type: mteb/sts17-crosslingual-sts name: MTEB STS17 (en-en) config: en-en split: test revision: af5e6fb845001ecf41f4c1e033ce921939a2a68d metrics: - type: cos_sim_pearson value: 87.20030208471798 - type: cos_sim_spearman value: 87.20485505076539 - type: euclidean_pearson value: 88.10588324368722 - type: euclidean_spearman value: 87.20485505076539 - type: manhattan_pearson value: 87.92324770415183 - type: manhattan_spearman value: 87.0571314561877 - task: type: STS dataset: type: mteb/sts22-crosslingual-sts name: MTEB STS22 (en) config: en split: test revision: 6d1ba47164174a496b7fa5d3569dae26a6813b80 metrics: - type: cos_sim_pearson value: 63.06093161604453 - type: cos_sim_spearman value: 64.2163140357722 - type: euclidean_pearson value: 65.27589680994006 - type: euclidean_spearman value: 64.2163140357722 - type: manhattan_pearson value: 65.45904383711101 - type: manhattan_spearman value: 64.55404716679305 - task: type: STS dataset: type: mteb/stsbenchmark-sts name: MTEB STSBenchmark config: default split: test revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831 metrics: - type: cos_sim_pearson value: 84.32976164578706 - type: cos_sim_spearman value: 85.54302197678368 - type: euclidean_pearson value: 85.26307149193056 - type: euclidean_spearman value: 85.54302197678368 - type: manhattan_pearson value: 85.26647282029371 - type: manhattan_spearman value: 85.5316135265568 - task: type: Reranking dataset: type: mteb/scidocs-reranking name: MTEB SciDocsRR config: default split: test revision: d3c5e1fc0b855ab6097bf1cda04dd73947d7caab metrics: - type: map value: 81.44675968318754 - type: mrr value: 94.92741826075158 - task: type: Retrieval dataset: type: scifact name: MTEB SciFact config: default split: test revision: None metrics: - type: map_at_1 value: 56.34400000000001 - type: map_at_10 value: 65.927 - type: map_at_100 value: 66.431 - type: map_at_1000 value: 66.461 - type: map_at_3 value: 63.529 - type: map_at_5 value: 64.818 - type: mrr_at_1 value: 59.333000000000006 - type: mrr_at_10 value: 67.54599999999999 - type: mrr_at_100 value: 67.892 - type: mrr_at_1000 value: 67.917 - type: mrr_at_3 value: 65.778 - type: mrr_at_5 value: 66.794 - type: ndcg_at_1 value: 59.333000000000006 - type: ndcg_at_10 value: 70.5 - type: ndcg_at_100 value: 72.688 - type: ndcg_at_1000 value: 73.483 - type: ndcg_at_3 value: 66.338 - type: ndcg_at_5 value: 68.265 - type: precision_at_1 value: 59.333000000000006 - type: precision_at_10 value: 9.3 - type: precision_at_100 value: 1.053 - type: precision_at_1000 value: 0.11199999999999999 - type: precision_at_3 value: 25.889 - type: precision_at_5 value: 16.866999999999997 - type: recall_at_1 value: 56.34400000000001 - type: recall_at_10 value: 82.789 - type: recall_at_100 value: 92.767 - type: recall_at_1000 value: 99 - type: recall_at_3 value: 71.64399999999999 - type: recall_at_5 value: 76.322 - task: type: PairClassification dataset: type: mteb/sprintduplicatequestions-pairclassification name: MTEB SprintDuplicateQuestions config: default split: test revision: d66bd1f72af766a5cc4b0ca5e00c162f89e8cc46 metrics: - type: cos_sim_accuracy value: 99.75742574257426 - type: cos_sim_ap value: 93.52081548447406 - type: cos_sim_f1 value: 87.33850129198966 - type: cos_sim_precision value: 90.37433155080214 - type: cos_sim_recall value: 84.5 - type: dot_accuracy value: 99.75742574257426 - type: dot_ap value: 93.52081548447406 - type: dot_f1 value: 87.33850129198966 - type: dot_precision value: 90.37433155080214 - type: dot_recall value: 84.5 - type: euclidean_accuracy value: 99.75742574257426 - type: euclidean_ap value: 93.52081548447406 - type: euclidean_f1 value: 87.33850129198966 - type: euclidean_precision value: 90.37433155080214 - type: euclidean_recall value: 84.5 - type: manhattan_accuracy value: 99.75841584158415 - type: manhattan_ap value: 93.4975678585854 - type: manhattan_f1 value: 87.26708074534162 - type: manhattan_precision value: 90.45064377682404 - type: manhattan_recall value: 84.3 - type: max_accuracy value: 99.75841584158415 - type: max_ap value: 93.52081548447406 - type: max_f1 value: 87.33850129198966 - task: type: Clustering dataset: type: mteb/stackexchange-clustering name: MTEB StackExchangeClustering config: default split: test revision: 6cbc1f7b2bc0622f2e39d2c77fa502909748c259 metrics: - type: v_measure value: 64.31437036686651 - task: type: Clustering dataset: type: mteb/stackexchange-clustering-p2p name: MTEB StackExchangeClusteringP2P config: default split: test revision: 815ca46b2622cec33ccafc3735d572c266efdb44 metrics: - type: v_measure value: 33.25569319007206 - task: type: Reranking dataset: type: mteb/stackoverflowdupquestions-reranking name: MTEB StackOverflowDupQuestions config: default split: test revision: e185fbe320c72810689fc5848eb6114e1ef5ec69 metrics: - type: map value: 49.90474939720706 - type: mrr value: 50.568115503777264 - task: type: Summarization dataset: type: mteb/summeval name: MTEB SummEval config: default split: test revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c metrics: - type: cos_sim_pearson value: 29.866828641244712 - type: cos_sim_spearman value: 30.077555055873866 - type: dot_pearson value: 29.866832988572266 - type: dot_spearman value: 30.077555055873866 - task: type: Retrieval dataset: type: trec-covid name: MTEB TRECCOVID config: default split: test revision: None metrics: - type: map_at_1 value: 0.232 - type: map_at_10 value: 2.094 - type: map_at_100 value: 11.971 - type: map_at_1000 value: 28.158 - type: map_at_3 value: 0.688 - type: map_at_5 value: 1.114 - type: mrr_at_1 value: 88 - type: mrr_at_10 value: 93.4 - type: mrr_at_100 value: 93.4 - type: mrr_at_1000 value: 93.4 - type: mrr_at_3 value: 93 - type: mrr_at_5 value: 93.4 - type: ndcg_at_1 value: 84 - type: ndcg_at_10 value: 79.923 - type: ndcg_at_100 value: 61.17 - type: ndcg_at_1000 value: 53.03 - type: ndcg_at_3 value: 84.592 - type: ndcg_at_5 value: 82.821 - type: precision_at_1 value: 88 - type: precision_at_10 value: 85 - type: precision_at_100 value: 63.019999999999996 - type: precision_at_1000 value: 23.554 - type: precision_at_3 value: 89.333 - type: precision_at_5 value: 87.2 - type: recall_at_1 value: 0.232 - type: recall_at_10 value: 2.255 - type: recall_at_100 value: 14.823 - type: recall_at_1000 value: 49.456 - type: recall_at_3 value: 0.718 - type: recall_at_5 value: 1.175 - task: type: Retrieval dataset: type: webis-touche2020 name: MTEB Touche2020 config: default split: test revision: None metrics: - type: map_at_1 value: 2.547 - type: map_at_10 value: 11.375 - type: map_at_100 value: 18.194 - type: map_at_1000 value: 19.749 - type: map_at_3 value: 5.825 - type: map_at_5 value: 8.581 - type: mrr_at_1 value: 32.653 - type: mrr_at_10 value: 51.32 - type: mrr_at_100 value: 51.747 - type: mrr_at_1000 value: 51.747 - type: mrr_at_3 value: 47.278999999999996 - type: mrr_at_5 value: 48.605 - type: ndcg_at_1 value: 29.592000000000002 - type: ndcg_at_10 value: 28.151 - type: ndcg_at_100 value: 39.438 - type: ndcg_at_1000 value: 50.769 - type: ndcg_at_3 value: 30.758999999999997 - type: ndcg_at_5 value: 30.366 - type: precision_at_1 value: 32.653 - type: precision_at_10 value: 25.714 - type: precision_at_100 value: 8.041 - type: precision_at_1000 value: 1.555 - type: precision_at_3 value: 33.333 - type: precision_at_5 value: 31.837 - type: recall_at_1 value: 2.547 - type: recall_at_10 value: 18.19 - type: recall_at_100 value: 49.538 - type: recall_at_1000 value: 83.86 - type: recall_at_3 value: 7.329 - type: recall_at_5 value: 11.532 - task: type: Classification dataset: type: mteb/toxic_conversations_50k name: MTEB ToxicConversationsClassification config: default split: test revision: d7c0de2777da35d6aae2200a62c6e0e5af397c4c metrics: - type: accuracy value: 71.4952 - type: ap value: 14.793362635531409 - type: f1 value: 55.204635551516915 - task: type: Classification dataset: type: mteb/tweet_sentiment_extraction name: MTEB TweetSentimentExtractionClassification config: default split: test revision: d604517c81ca91fe16a244d1248fc021f9ecee7a metrics: - type: accuracy value: 61.5365025466893 - type: f1 value: 61.81742556334845 - task: type: Clustering dataset: type: mteb/twentynewsgroups-clustering name: MTEB TwentyNewsgroupsClustering config: default split: test revision: 6125ec4e24fa026cec8a478383ee943acfbd5449 metrics: - type: v_measure value: 49.05531070301185 - task: type: PairClassification dataset: type: mteb/twittersemeval2015-pairclassification name: MTEB TwitterSemEval2015 config: default split: test revision: 70970daeab8776df92f5ea462b6173c0b46fd2d1 metrics: - type: cos_sim_accuracy value: 86.51725576682364 - type: cos_sim_ap value: 75.2292304265163 - type: cos_sim_f1 value: 69.54022988505749 - type: cos_sim_precision value: 63.65629110039457 - type: cos_sim_recall value: 76.62269129287598 - type: dot_accuracy value: 86.51725576682364 - type: dot_ap value: 75.22922386081054 - type: dot_f1 value: 69.54022988505749 - type: dot_precision value: 63.65629110039457 - type: dot_recall value: 76.62269129287598 - type: euclidean_accuracy value: 86.51725576682364 - type: euclidean_ap value: 75.22925730473472 - type: euclidean_f1 value: 69.54022988505749 - type: euclidean_precision value: 63.65629110039457 - type: euclidean_recall value: 76.62269129287598 - type: manhattan_accuracy value: 86.52321630804077 - type: manhattan_ap value: 75.20608115037336 - type: manhattan_f1 value: 69.60000000000001 - type: manhattan_precision value: 64.37219730941705 - type: manhattan_recall value: 75.75197889182058 - type: max_accuracy value: 86.52321630804077 - type: max_ap value: 75.22925730473472 - type: max_f1 value: 69.60000000000001 - task: type: PairClassification dataset: type: mteb/twitterurlcorpus-pairclassification name: MTEB TwitterURLCorpus config: default split: test revision: 8b6510b0b1fa4e4c4f879467980e9be563ec1cdf metrics: - type: cos_sim_accuracy value: 89.34877944657896 - type: cos_sim_ap value: 86.71257569277373 - type: cos_sim_f1 value: 79.10386355986088 - type: cos_sim_precision value: 76.91468470434214 - type: cos_sim_recall value: 81.4213119802895 - type: dot_accuracy value: 89.34877944657896 - type: dot_ap value: 86.71257133133368 - type: dot_f1 value: 79.10386355986088 - type: dot_precision value: 76.91468470434214 - type: dot_recall value: 81.4213119802895 - type: euclidean_accuracy value: 89.34877944657896 - type: euclidean_ap value: 86.71257651501476 - type: euclidean_f1 value: 79.10386355986088 - type: euclidean_precision value: 76.91468470434214 - type: euclidean_recall value: 81.4213119802895 - type: manhattan_accuracy value: 89.35848177901967 - type: manhattan_ap value: 86.69330615469126 - type: manhattan_f1 value: 79.13867741453949 - type: manhattan_precision value: 76.78881807647741 - type: manhattan_recall value: 81.63689559593472 - type: max_accuracy value: 89.35848177901967 - type: max_ap value: 86.71257651501476 - type: max_f1 value: 79.13867741453949 license: apache-2.0 language: - en --- # nomic-embed-text-v1: A Reproducible Long Context (8192) Text Embedder `nomic-embed-text-v1` is 8192 context length text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks. | Name | SeqLen | MTEB | LoCo | Jina Long Context | Open Weights | Open Training Code | Open Data | | :-------------------------------:| :----- | :-------- | :------: | :---------------: | :-----------: | :----------------: | :---------- | | nomic-embed-text-v1 | 8192 | **62.39** |**85.53** | 54.16 | ✅ | ✅ | ✅ | | jina-embeddings-v2-base-en | 8192 | 60.39 | 85.45 | 51.90 | ✅ | ❌ | ❌ | | text-embedding-3-small | 8191 | 62.26 | 82.40 | **58.20** | ❌ | ❌ | ❌ | | text-embedding-ada-002 | 8191 | 60.99 | 52.7 | 55.25 | ❌ | ❌ | ❌ | ## Hosted Inference API The easiest way to get started with Nomic Embed is through the Nomic Embedding API. Generating embeddings with the `nomic` Python client is as easy as ```python from nomic import embed output = embed.text( texts=['Nomic Embedding API', '#keepAIOpen'], model='nomic-embed-text-v1', task_type='search_document' ) print(output) ``` For more information, see the [API reference](https://docs.nomic.ai/reference/endpoints/nomic-embed-text) ## Data Visualization Click the Nomic Atlas map below to visualize a 5M sample of our contrastive pretraining data! [![image/webp](https://cdn-uploads.huggingface.co/production/uploads/607997c83a565c15675055b3/pjhJhuNyRfPagRd_c_iUz.webp)](https://atlas.nomic.ai/map/nomic-text-embed-v1-5m-sample) ## Training Details We train our embedder using a multi-stage training pipeline. Starting from a long-context [BERT model](https://huggingface.co/nomic-ai/nomic-bert-2048), the first unsupervised contrastive stage trains on a dataset generated from weakly related text pairs, such as question-answer pairs from forums like StackExchange and Quora, title-body pairs from Amazon reviews, and summarizations from news articles. In the second finetuning stage, higher quality labeled datasets such as search queries and answers from web searches are leveraged. Data curation and hard-example mining is crucial in this stage. For more details, see the Nomic Embed [Technical Report](https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf) and corresponding [blog post](https://blog.nomic.ai/posts/nomic-embed-text-v1). Training data to train the models is released in its entirety. For more details, see the `contrastors` [repository](https://github.com/nomic-ai/contrastors) ## Usage Note `nomic-embed-text` *requires* prefixes! We support the prefixes `[search_query, search_document, classification, clustering]`. For retrieval applications, you should prepend `search_document` for all your documents and `search_query` for your queries. For example, you are building a RAG application over the top of Wikipedia. You would embed all Wikipedia articles with the prefix `search_document` and any questions you ask with `search_query`. For example: ```python queries = ["search_query: who is the first president of the united states?", "search_query: when was babe ruth born?"] documents = ["search_document: <article about US Presidents>", "search_document: <article about Babe Ruth>"] ``` ### Sentence Transformers ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("nomic-ai/nomic-embed-text-v1", trust_remote_code=True) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] embeddings = model.encode(sentences) print(embeddings) ``` ### Transformers ```python import torch import torch.nn.functional as F from transformers import AutoTokenizer, AutoModel def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?'] tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) model.eval() encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') with torch.no_grad(): model_output = model(**encoded_input) embeddings = mean_pooling(model_output, encoded_input['attention_mask']) embeddings = F.normalize(embeddings, p=2, dim=1) print(embeddings) ``` The model natively supports scaling of the sequence length past 2048 tokens. To do so, ```diff - tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased') + tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased', model_max_length=8192) - model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True) + model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True, rotary_scaling_factor=2) ``` ### Transformers.js ```js import { pipeline } from '@xenova/transformers'; // Create a feature extraction pipeline const extractor = await pipeline('feature-extraction', 'nomic-ai/nomic-embed-text-v1', { quantized: false, // Comment out this line to use the quantized version }); // Compute sentence embeddings const texts = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']; const embeddings = await extractor(texts, { pooling: 'mean', normalize: true }); console.log(embeddings); ``` # Join the Nomic Community - Nomic: [https://nomic.ai](https://nomic.ai) - Discord: [https://discord.gg/myY5YDR8z8](https://discord.gg/myY5YDR8z8) - Twitter: [https://twitter.com/nomic_ai](https://twitter.com/nomic_ai) # Citation If you find the model, dataset, or training code useful, please cite our work ```bibtex @misc{nussbaum2024nomic, title={Nomic Embed: Training a Reproducible Long Context Text Embedder}, author={Zach Nussbaum and John X. Morris and Brandon Duderstadt and Andriy Mulyar}, year={2024}, eprint={2402.01613}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

Yntec/InfiniteLiberty

Yntec

"2023-12-27T13:49:57Z"

2,589

3

diffusers

[ "diffusers", "safetensors", "Realistic", "Photos", "AInfinity", "artificialguybr", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

"2023-12-27T11:56:34Z"

--- license: creativeml-openrail-m library_name: diffusers pipeline_tag: text-to-image tags: - Realistic - Photos - AInfinity - artificialguybr - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers --- # Infinite Liberty A mix of LiberteRedmond and AI Infinity Realistic to increase its complexity! Comparison and prompt: ![Infinite Liberty Model Comparison](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/stfUK0l7HU4s87UjJCIlb.png) (Click for larger) Portrait of a happy family cooking at the classroom, girl painting by technicolor, smooth face, perfect eyes, wide angle, sharp focus, 8 k high definition, insanely detailed, intricate, elegant, acrylic art on canvas by rossdraws and clay mann Samples and prompts (keep scrolling for more) ![Infinite AI images generated](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/mKgVBWyfPs2KYP1Q4sWDb.png) (Click for larger) Top left: pretty wife hugging young husband and daughter movie still. faces portrait. festive scene at a copper brewery with a wooden keg of beer in the center. sitting cute little girl. Display mugs of dark beer accompanied Shirley by halloween ingredients Top right: young guy together with pretty ladies standing, he, photoreal, cute face, is on top of Closeup a of rocks on pile top of a magazine to the ocean moon. Bottom left: little videogames, robert jordan pepperoni pizza, josephine wall winner, hidari, roll20 illumination, radiant light, sitting elementary girl, Pretty CUTE, gorgeous hair, DETAILED CHIBI EYES, Magazine ad, iconic, 1943, Cartoon, sharp focus, cherries, watched towel. 4k art on canvas by kyoani and ROSSDRAWS Bottom right: best quality, a bag of TV potato chips ![Free text to image generator](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/LD9VNHfTF9mB0iSPlltFb.png) (Click for larger) Top left: a deer playing guitar in a club, whimsical Top right: masterpiece, best quality, ultra detailed, 8k, 4k, intricate,highly detailed, detailed background,detailed landscape, ((portrait)), foodstyle,simple background, food, black background, plate, realistic, burger, meat, food focus, cheese, still life, lettuce Bottom left: pretty cute little girl as Marie Antoinette playing on harmonica in movie Bottom right: ladies as close Catwoman and Harley Quinn from the 2004 movie. elegant, medieval in cool armor, action scene, in a wonderland land ![Liberty AI images generated](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/Rh1WyezDDoLdSD1EdUYXr.png) (Click for larger) Top left: manga art, muted colors, detailed painting, halftone dithering, cute girl with shoulderlength black bobcut in baggy black clothes, pixar cape, beautiful eyes, complex background Top right: calm water in european city. sofa Bottom left: beach, ruins, romantic night Bottom right: 1girl,night, waterfall, white wavy hair Angel 22y.o, (realistic:2),Pizza,4k,rabbits and birds, close up, ![Infinite Liberty AI images generated](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/_zRtrSsDYhQWah-rw7K4o.png) (Click for larger) Top left: Father with little daughter holding cheescake. Santa Claus sitting with a pretty cute girl, Art Christmas Theme by Gil_Elvgren and Haddon_Sundblom Top right: Romanticism In Photography The Beauty Grandeur And behind trees Of Nature The Suggestion Of The Divine In The Light And Nature Photos Nature Photography Nature, wallpaper hd, stunning photorealistic painting, artstation, divine night sky,1920x1080 Bottom left: peaceful grill full of meat and artstation. fire Bottom right: Dreamy Pet Portrait photo of a Cute penguin, with twinkling eyes that could melt hearts, lounging in a field of daisies, its fur catching the gentle breeze, backdrop of a serene lakeside sunset, bathed in the warm, golden hues of the fading day, using a high-quality digital camera to ensure every adorable detail, in the style of Annie Leibovitz ![Free AI samples and prompts](https://cdn-uploads.huggingface.co/production/uploads/63239b8370edc53f51cd5d42/dzoBWU7UduqHnvwYOujyI.png) (Click for larger) Top left: an illustration of a baby frog with headphones holding an ribbon umbrella in the rain Top right: Pretty CUTE LITTLE Girl, sitting on a box of veggies, CHIBI EYES, holding PEPSI bottle, gorgeous detailed hair, Ponytail, ad, iconic, 1940, sharp focus. Illustration By KlaysMoji and artgerm and Clay Mann and and Dave Rapoza and leyendecker Bottom left: tiny baby girl. chibi. Bottom right: House with a waterwheel built into the screen of a giant tree, next to games, a colorful river landscape painting from a fantasy point and click 2 d graphic adventure game, art inspired by ROSSDRAWS and larry elmore and john shroades, king's quest, sierra entertainment Original pages: https://civitai.com/models/94123?modelVersionId=100409 (Liberte Redmond) https://civitai.com/models/121253/ai-infinity-realistic-better-hands # Recipe: - SuperMerger Weight Sum Train Difference MBW 0,1,1,1,1,1,1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,0,0 Model A: AIInfinityRealistic Model B: LiberteRedmond Output: InfiniteLiberty

RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf

RichardErkhov

"2024-06-26T22:28:50Z"

2,589

1

null

[ "gguf", "region:us" ]

null

"2024-06-26T22:04:35Z"

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Fett-uccine-7B - GGUF - Model creator: https://huggingface.co/Epiculous/ - Original model: https://huggingface.co/Epiculous/Fett-uccine-7B/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Fett-uccine-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q2_K.gguf) | Q2_K | 2.53GB | | [Fett-uccine-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB | | [Fett-uccine-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ3_S.gguf) | IQ3_S | 2.96GB | | [Fett-uccine-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q3_K_S.gguf) | Q3_K_S | 1.36GB | | [Fett-uccine-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ3_M.gguf) | IQ3_M | 1.09GB | | [Fett-uccine-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q3_K.gguf) | Q3_K | 0.13GB | | [Fett-uccine-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q3_K_M.gguf) | Q3_K_M | 0.01GB | | [Fett-uccine-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q3_K_L.gguf) | Q3_K_L | 0.0GB | | [Fett-uccine-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ4_XS.gguf) | IQ4_XS | 0.0GB | | [Fett-uccine-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_0.gguf) | Q4_0 | 0.0GB | | [Fett-uccine-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.IQ4_NL.gguf) | IQ4_NL | 0.0GB | | [Fett-uccine-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_K_S.gguf) | Q4_K_S | 0.0GB | | [Fett-uccine-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_K.gguf) | Q4_K | 0.0GB | | [Fett-uccine-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_K_M.gguf) | Q4_K_M | 0.0GB | | [Fett-uccine-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q4_1.gguf) | Q4_1 | 0.0GB | | [Fett-uccine-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_0.gguf) | Q5_0 | 0.0GB | | [Fett-uccine-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_K_S.gguf) | Q5_K_S | 0.0GB | | [Fett-uccine-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_K.gguf) | Q5_K | 0.0GB | | [Fett-uccine-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_K_M.gguf) | Q5_K_M | 0.0GB | | [Fett-uccine-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q5_1.gguf) | Q5_1 | 0.0GB | | [Fett-uccine-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q6_K.gguf) | Q6_K | 0.0GB | | [Fett-uccine-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/Epiculous_-_Fett-uccine-7B-gguf/blob/main/Fett-uccine-7B.Q8_0.gguf) | Q8_0 | 0.0GB | Original model description: --- datasets: - lemonilia/LimaRP - grimulkan/theory-of-mind - Epiculous/Gnosis tags: - not-for-all-audiences license: agpl-3.0 --- # Fett-uccine This model is created by training Mistral base model on LimaRP (ShareGPT format provided by SAO), theory of mind, and gnosis(provided by jeiku). The 8-bit lora was then merged into Mistral Instruct resulting in what you see here. Works best with ChatML Instruct This model is in honor of the SillyTavern community, keep being awesome! Optimal Settings provided by Nitral: ``` { "temp": 5, "temperature_last": true, "top_p": 1, "top_k": 0, "top_a": 0, "tfs": 1, "epsilon_cutoff": 0, "eta_cutoff": 0, "typical_p": 1, "min_p": 0.05, "rep_pen": 1, "rep_pen_range": 0, "no_repeat_ngram_size": 0, "penalty_alpha": 0, "num_beams": 1, "length_penalty": 0, "min_length": 0, "encoder_rep_pen": 1, "freq_pen": 0, "presence_pen": 0, "do_sample": true, "early_stopping": false, "dynatemp": false, "min_temp": 1, "max_temp": 5, "dynatemp_exponent": 1, "smoothing_factor": 0.3, "add_bos_token": true, "truncation_length": 2048, "ban_eos_token": false, "skip_special_tokens": true, "streaming": false, "mirostat_mode": 0, "mirostat_tau": 5, "mirostat_eta": 0.1, "guidance_scale": 1, "negative_prompt": "", "grammar_string": "", "banned_tokens": "", "ignore_eos_token_aphrodite": false, "spaces_between_special_tokens_aphrodite": true, "sampler_order": [ 6, 0, 1, 3, 4, 2, 5 ], "logit_bias": [], "n": 1, "rep_pen_size": 0, "genamt": 150, "max_length": 8192 } ```

alibayram/Doktor-Llama-8b.gguf

alibayram

"2024-06-20T21:40:51Z"

2,585

1

null

[ "gguf", "tr", "dataset:alibayram/doktorsitesi", "license:cc-by-4.0", "region:us" ]

null

"2024-06-20T20:49:21Z"

--- license: cc-by-4.0 datasets: - alibayram/doktorsitesi language: - tr --- # Doktor-Llama-8b.gguf ## Genel Bakış **Doktor-Llama-8b.gguf**, **alibayram/Doktor-Llama-8b** modelinin GGUF formatına dönüştürülmüş versiyonudur. GGUF, model dosyalarının daha verimli ve hızlı bir şekilde işlenmesini sağlayan yeni bir formattır. Bu dönüşüm, modelin çeşitli platformlarda ve uygulamalarda daha kolay kullanılabilmesi için yapılmıştır. ## GGUF Nedir? GGUF, "Graphical GPU Unified Format" anlamına gelir ve özellikle büyük dil modellerinin daha verimli bir şekilde depolanması ve işlenmesi için geliştirilmiş bir formattır. Bu format, model dosyalarının boyutunu küçültürken performansı artırır, bu sayede daha hızlı ve verimli kullanım sağlar. ## Alıntı Bu modeli araştırmanızda veya uygulamanızda kullanırsanız, lütfen aşağıdaki gibi alıntı yapın: ``` @model{alibayram2024doktor-llama-8b-gguf, author = {Ali Bayram}, title = {Doktor-Llama-8b.gguf}, year = 2024, url = {https://huggingface.co/alibayram/Doktor-Llama-8b.gguf}, } ``` ## Lisans Bu model, Creative Commons Attribution Non Commercial 4.0 lisansı altında lisanslanmıştır. Modeli ticari amaçlar dışında kullanabilir, paylaşabilir ve uyarlayabilirsiniz, ancak uygun atıf yapmanız gerekmektedir. ## Katkılar Bu modele katkılar memnuniyetle karşılanır. Herhangi bir öneriniz, iyileştirmeniz veya ek veriniz varsa, lütfen model oluşturucusuyla iletişime geçin veya model deposunda bir pull request gönderin. ## İletişim Herhangi bir soru veya daha fazla bilgi için lütfen iletişime geçin: - **İsim:** Ali Bayram - **Email:** [email protected] ## Teşekkürler Bu modelin geliştirilmesinde katkıda bulunan tüm sağlık profesyonellerine ve veri sağlayıcılarına teşekkür ederiz.

Neleac/SpaceTimeGPT

Neleac

"2024-03-21T05:56:11Z"

2,584

25

transformers

[ "transformers", "pytorch", "vision-encoder-decoder", "video-captioning", "text-generation", "en", "dataset:HuggingFaceM4/vatex", "region:us" ]

text-generation

"2023-04-21T23:32:33Z"

--- datasets: - HuggingFaceM4/vatex language: - en metrics: - bleu - meteor - rouge pipeline_tag: text-generation inference: false tags: - video-captioning --- # SpaceTimeGPT - A Spatiotemporal Video Captioning Model ![SpaceTimeGPT](https://raw.githubusercontent.com/Neleac/SpaceTimeGPT/main/model.JPG) Vision Encoder Model: [timesformer-base-finetuned-k600](https://huggingface.co/facebook/timesformer-base-finetuned-k600) \ Text Decoder Model: [gpt2](https://huggingface.co/gpt2) #### Evaluation Result: 67.2 CIDEr on [VaTeX](https://eric-xw.github.io/vatex-website/index.html) public test set #### Example Inference Code: ```python import av import numpy as np import torch from transformers import AutoImageProcessor, AutoTokenizer, VisionEncoderDecoderModel device = "cuda" if torch.cuda.is_available() else "cpu" # load pretrained processor, tokenizer, and model image_processor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base") tokenizer = AutoTokenizer.from_pretrained("gpt2") model = VisionEncoderDecoderModel.from_pretrained("Neleac/timesformer-gpt2-video-captioning").to(device) # load video video_path = "never_gonna_give_you_up.mp4" container = av.open(video_path) # extract evenly spaced frames from video seg_len = container.streams.video[0].frames clip_len = model.config.encoder.num_frames indices = set(np.linspace(0, seg_len, num=clip_len, endpoint=False).astype(np.int64)) frames = [] container.seek(0) for i, frame in enumerate(container.decode(video=0)): if i in indices: frames.append(frame.to_ndarray(format="rgb24")) # generate caption gen_kwargs = { "min_length": 10, "max_length": 20, "num_beams": 8, } pixel_values = image_processor(frames, return_tensors="pt").pixel_values.to(device) tokens = model.generate(pixel_values, **gen_kwargs) caption = tokenizer.batch_decode(tokens, skip_special_tokens=True)[0] print(caption) # A man and a woman are dancing on a stage in front of a mirror. ``` #### Author Information: 👾 [Discord](https://discordapp.com/users/297770280863137802) \ 🐙 [GitHub](https://github.com/Neleac) \ 🤝 [LinkedIn](https://www.linkedin.com/in/caelenw/)

mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF

mradermacher

"2024-06-04T14:51:03Z"

2,584

0

transformers

[ "transformers", "gguf", "en", "base_model:AwanLLM/Awanllm-Llama-3-8B-Dolfin-v1.0", "license:llama3", "endpoints_compatible", "region:us" ]

null

"2024-06-03T17:20:05Z"

--- base_model: AwanLLM/Awanllm-Llama-3-8B-Dolfin-v1.0 language: - en library_name: transformers license: llama3 quantized_by: mradermacher --- ## About      static quants of https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Dolfin-v1.0  weighted/imatrix quants are available at https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Dolfin-v1.0-GGUF/resolve/main/Awanllm-Llama-3-8B-Dolfin-v1.0.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf

RichardErkhov

"2024-06-22T19:03:19Z"

2,583

0

null

[ "gguf", "region:us" ]

null

"2024-06-22T18:47:26Z"

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) TinyLlama-1.1B-intermediate-step-955k-token-2T - GGUF - Model creator: https://huggingface.co/TinyLlama/ - Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T/ | Name | Quant method | Size | | ---- | ---- | ---- | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q2_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q2_K.gguf) | Q2_K | 0.4GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_XS.gguf) | IQ3_XS | 0.44GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_S.gguf) | IQ3_S | 0.47GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_S.gguf) | Q3_K_S | 0.47GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ3_M.gguf) | IQ3_M | 0.48GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K.gguf) | Q3_K | 0.51GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_M.gguf) | Q3_K_M | 0.51GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q3_K_L.gguf) | Q3_K_L | 0.55GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ4_XS.gguf) | IQ4_XS | 0.57GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_0.gguf) | Q4_0 | 0.59GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.IQ4_NL.gguf) | IQ4_NL | 0.6GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K_S.gguf) | Q4_K_S | 0.6GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K.gguf) | Q4_K | 0.62GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_K_M.gguf) | Q4_K_M | 0.62GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q4_1.gguf) | Q4_1 | 0.65GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_0.gguf) | Q5_0 | 0.71GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K_S.gguf) | Q5_K_S | 0.71GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K.gguf) | Q5_K | 0.73GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_K_M.gguf) | Q5_K_M | 0.73GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q5_1.gguf) | Q5_1 | 0.77GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q6_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q6_K.gguf) | Q6_K | 0.84GB | | [TinyLlama-1.1B-intermediate-step-955k-token-2T.Q8_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-955k-token-2T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-955k-token-2T.Q8_0.gguf) | Q8_0 | 1.09GB | Original model description: --- license: apache-2.0 datasets: - cerebras/SlimPajama-627B - bigcode/starcoderdata language: - en --- <div align="center"> # TinyLlama-1.1B </div> https://github.com/jzhang38/TinyLlama The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. <div align="center"> <img src="./TinyLlama_logo.png" width="300"/> </div> We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint. #### This Model This is an intermediate checkpoint with 995K steps and 2003B tokens. #### Releases Schedule We will be rolling out intermediate checkpoints following the below schedule. We also include some baseline models for comparison. | Date | HF Checkpoint | Tokens | Step | HellaSwag Acc_norm | |------------|-------------------------------------------------|--------|------|---------------------| | Baseline | [StableLM-Alpha-3B](https://huggingface.co/stabilityai/stablelm-base-alpha-3b)| 800B | -- | 38.31 | | Baseline | [Pythia-1B-intermediate-step-50k-105b](https://huggingface.co/EleutherAI/pythia-1b/tree/step50000) | 105B | 50k | 42.04 | | Baseline | [Pythia-1B](https://huggingface.co/EleutherAI/pythia-1b) | 300B | 143k | 47.16 | | 2023-09-04 | [TinyLlama-1.1B-intermediate-step-50k-105b](https://huggingface.co/PY007/TinyLlama-1.1B-step-50K-105b) | 105B | 50k | 43.50 | | 2023-09-16 | -- | 500B | -- | -- | | 2023-10-01 | -- | 1T | -- | -- | | 2023-10-16 | -- | 1.5T | -- | -- | | 2023-10-31 | -- | 2T | -- | -- | | 2023-11-15 | -- | 2.5T | -- | -- | | 2023-12-01 | -- | 3T | -- | -- | #### How to use You will need the transformers>=4.31 Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information. ``` from transformers import AutoTokenizer import transformers import torch model = "TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( 'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.', do_sample=True, top_k=10, num_return_sequences=1, repetition_penalty=1.5, eos_token_id=tokenizer.eos_token_id, max_length=500, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ```

marefa-nlp/marefa-ner

marefa-nlp

"2021-12-04T05:21:57Z"

2,582

20

transformers

[ "transformers", "pytorch", "xlm-roberta", "token-classification", "ar", "dataset:Marefa-NER", "autotrain_compatible", "endpoints_compatible", "region:us" ]

token-classification

"2022-03-02T23:29:05Z"

--- language: ar datasets: - Marefa-NER widget: - text: "في استاد القاهرة، بدأ حفل افتتاح بطولة كأس الأمم الأفريقية بحضور رئيس الجمهورية و رئيس الاتحاد الدولي لكرة القدم" --- # Tebyan تبيـان ## Marefa Arabic Named Entity Recognition Model ## نموذج المعرفة لتصنيف أجزاء النص <p align="center"> <img src="https://huggingface.co/marefa-nlp/marefa-ner/resolve/main/assets/marefa-tebyan-banner.png" alt="Marfa Arabic NER Model" width="600"/> </p? --------- **Version**: 1.3 **Last Update:** 3-12-2021 ## Model description **Marefa-NER** is a Large Arabic Named Entity Recognition (NER) model built on a completely new dataset and targets to extract up to 9 different types of entities ``` Person, Location, Organization, Nationality, Job, Product, Event, Time, Art-Work ``` نموذج المعرفة لتصنيف أجزاء النص. نموذج جديد كليا من حيث البيانات المستخدمة في تدريب النموذج. كذلك يستهدف النموذج تصنيف حتى 9 أنواع مختلفة من أجزاء النص ``` شخص - مكان - منظمة - جنسية - وظيفة - منتج - حدث - توقيت - عمل إبداعي ``` ## How to use كيف تستخدم النموذج *You can test the model quickly by checking this [Colab notebook](https://colab.research.google.com/drive/1OGp9Wgm-oBM5BBhTLx6Qow4dNRSJZ-F5?usp=sharing)* ---- Install the following Python packages `$ pip3 install transformers==4.8.0 nltk==3.5 protobuf==3.15.3 torch==1.9.0 ` > If you are using `Google Colab`, please restart your runtime after installing the packages. ----------- ```python from transformers import AutoTokenizer, AutoModelForTokenClassification import torch import numpy as np import nltk nltk.download('punkt') from nltk.tokenize import word_tokenize custom_labels = ["O", "B-job", "I-job", "B-nationality", "B-person", "I-person", "B-location","B-time", "I-time", "B-event", "I-event", "B-organization", "I-organization", "I-location", "I-nationality", "B-product", "I-product", "B-artwork", "I-artwork"] def _extract_ner(text: str, model: AutoModelForTokenClassification, tokenizer: AutoTokenizer, start_token: str="▁"): tokenized_sentence = tokenizer([text], padding=True, truncation=True, return_tensors="pt") tokenized_sentences = tokenized_sentence['input_ids'].numpy() with torch.no_grad(): output = model(**tokenized_sentence) last_hidden_states = output[0].numpy() label_indices = np.argmax(last_hidden_states[0], axis=1) tokens = tokenizer.convert_ids_to_tokens(tokenized_sentences[0]) special_tags = set(tokenizer.special_tokens_map.values()) grouped_tokens = [] for token, label_idx in zip(tokens, label_indices): if token not in special_tags: if not token.startswith(start_token) and len(token.replace(start_token,"").strip()) > 0: grouped_tokens[-1]["token"] += token else: grouped_tokens.append({"token": token, "label": custom_labels[label_idx]}) # extract entities ents = [] prev_label = "O" for token in grouped_tokens: label = token["label"].replace("I-","").replace("B-","") if token["label"] != "O": if label != prev_label: ents.append({"token": [token["token"]], "label": label}) else: ents[-1]["token"].append(token["token"]) prev_label = label # group tokens ents = [{"token": "".join(rec["token"]).replace(start_token," ").strip(), "label": rec["label"]} for rec in ents ] return ents model_cp = "marefa-nlp/marefa-ner" tokenizer = AutoTokenizer.from_pretrained(model_cp) model = AutoModelForTokenClassification.from_pretrained(model_cp, num_labels=len(custom_labels)) samples = [ "تلقى تعليمه في الكتاب ثم انضم الى الأزهر عام 1873م. تعلم على يد السيد جمال الدين الأفغاني والشيخ محمد عبده", "بعد عودته إلى القاهرة، التحق نجيب الريحاني فرقة جورج أبيض، الذي كان قد ضمَّ - قُبيل ذلك - فرقته إلى فرقة سلامة حجازي . و منها ذاع صيته", "في استاد القاهرة، قام حفل افتتاح بطولة كأس الأمم الأفريقية بحضور رئيس الجمهورية و رئيس الاتحاد الدولي لكرة القدم", "من فضلك أرسل هذا البريد الى صديقي جلال الدين في تمام الساعة الخامسة صباحا في يوم الثلاثاء القادم", "امبارح اتفرجت على مباراة مانشستر يونايتد مع ريال مدريد في غياب الدون كرستيانو رونالدو", "لا تنسى تصحيني الساعة سبعة, و ضيف في الجدول اني احضر مباراة نادي النصر غدا", ] # [optional] samples = [ " ".join(word_tokenize(sample.strip())) for sample in samples if sample.strip() != "" ] for sample in samples: ents = _extract_ner(text=sample, model=model, tokenizer=tokenizer, start_token="▁") print(sample) for ent in ents: print("\t",ent["token"],"==>",ent["label"]) print("========\n") ``` Output ``` تلقى تعليمه في الكتاب ثم انضم الى الأزهر عام 1873م . تعلم على يد السيد جمال الدين الأفغاني والشيخ محمد عبده الأزهر ==> organization عام 1873م ==> time السيد جمال الدين الأفغاني ==> person محمد عبده ==> person ======== بعد عودته إلى القاهرة، التحق نجيب الريحاني فرقة جورج أبيض، الذي كان قد ضمَّ - قُبيل ذلك - فرقته إلى فرقة سلامة حجازي . و منها ذاع صيته القاهرة، ==> location نجيب الريحاني ==> person فرقة جورج أبيض، ==> organization فرقة سلامة حجازي ==> organization ======== في استاد القاهرة، قام حفل افتتاح بطولة كأس الأمم الأفريقية بحضور رئيس الجمهورية و رئيس الاتحاد الدولي لكرة القدم استاد القاهرة، ==> location بطولة كأس الأمم الأفريقية ==> event رئيس الجمهورية ==> job رئيس ==> job الاتحاد الدولي لكرة القدم ==> organization ======== من فضلك أرسل هذا البريد الى صديقي جلال الدين في تمام الساعة الخامسة صباحا في يوم الثلاثاء القادم جلال الدين ==> person الساعة الخامسة صباحا ==> time يوم الثلاثاء القادم ==> time ======== امبارح اتفرجت على مباراة مانشستر يونايتد مع ريال مدريد في غياب الدون كرستيانو رونالدو مانشستر يونايتد ==> organization ريال مدريد ==> organization كرستيانو رونالدو ==> person ======== لا تنسى تصحيني الساعة سبعة , و ضيف في الجدول اني احضر مباراة نادي النصر غدا الساعة سبعة ==> time نادي النصر ==> organization غدا ==> time ======== ``` ## Fine-Tuning Check this [notebook](https://colab.research.google.com/drive/1WUYrnmDFFEItqGMvbyjqZEJJqwU7xQR-?usp=sharing) to fine-tune the NER model ## Evaluation We tested the model agains a test set of 1959 sentences. The results is in the follwing table | type | f1-score | precision | recall | support | |:-------------|-----------:|------------:|---------:|----------:| | person | 0.93298 | 0.931479 | 0.934487 | 4335 | | location | 0.891537 | 0.896926 | 0.886212 | 4939 | | time | 0.873003 | 0.876087 | 0.869941 | 1853 | | nationality | 0.871246 | 0.843153 | 0.901277 | 2350 | | job | 0.837656 | 0.79912 | 0.880097 | 2477 | | organization | 0.781317 | 0.773328 | 0.789474 | 2299 | | event | 0.686695 | 0.733945 | 0.645161 | 744 | | artwork | 0.653552 | 0.678005 | 0.630802 | 474 | | product | 0.625483 | 0.553531 | 0.718935 | 338 | | **weighted avg** | 0.859008 | 0.852365 | 0.86703 | 19809 | | **micro avg** | 0.858771 | 0.850669 | 0.86703 | 19809 | | **macro avg** | 0.79483 | 0.787286 | 0.806265 | 19809 | ## Acknowledgment شكر و تقدير قام بإعداد البيانات التي تم تدريب النموذج عليها, مجموعة من المتطوعين الذين قضوا ساعات يقومون بتنقيح البيانات و مراجعتها - على سيد عبد الحفيظ - إشراف - نرمين محمد عطيه - صلاح خيرالله - احمد علي عبدربه - عمر بن عبد العزيز سليمان - محمد ابراهيم الجمال - عبدالرحمن سلامه خلف - إبراهيم كمال محمد سليمان - حسن مصطفى حسن - أحمد فتحي سيد - عثمان مندو - عارف الشريف - أميرة محمد محمود - حسن سعيد حسن - عبد العزيز علي البغدادي - واثق عبدالملك الشويطر - عمرو رمضان عقل الحفناوي - حسام الدين أحمد على - أسامه أحمد محمد محمد - حاتم محمد المفتي - عبد الله دردير - أدهم البغدادي - أحمد صبري - عبدالوهاب محمد محمد - أحمد محمد عوض

waifu-diffusion/wd-1-5-beta3

waifu-diffusion

"2023-10-12T02:56:59Z"

2,582

123

diffusers

[ "diffusers", "safetensors", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

text-to-image

"2023-05-14T22:59:44Z"

--- license: other --- # WD 1.5 Beta 3 ![WD 1.5 Radiance](https://i.ibb.co/hYjgvGZ/00160-2195473148.png) For this release, we release five versions of the model: - WD 1.5 Beta3 Base - WD 1.5 Radiance - WD 1.5 Ink - WD 1.5 Mofu - WD 1.5 Illusion The WD 1.5 Base model is only intended for training use. For generation, it is recomended to create your own finetunes and loras on top of WD 1.5 Base or use one of the aesthetic models. More information and sample generations for the aesthetic models are in the release notes ### Release Notes https://saltacc.notion.site/WD-1-5-Beta-3-Release-Notes-1e35a0ed1bb24c5b93ec79c45c217f63 # VAE WD 1.5 uses the same VAE as WD 1.4, which can be found here https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt ## License WD 1.5 is released under the Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/). If any derivative of this model is made, please share your changes accordingly. Special thanks to ronsor/undeleted (https://undeleted.ronsor.com/) for help with the license.

nes470/pipeline-as-repo

nes470

"2024-05-16T22:18:19Z"

2,582

0

transformers

[ "transformers", "pytorch", "QA-umd-quizbowl", "question-answering", "custom_code", "license:mit", "region:us" ]

question-answering

"2024-05-06T15:27:54Z"

--- license: mit library_name: transformers --- Names: Nuran, Joshua, Robert The evaluation of this project is to answer trivia questions. You do not need to do well at this task, but you should submit a system that completes the task or create adversarial questions in that setting. This will help the whole class share data and resources. If you focus on something other than predicting answers, *that's fine*! About the Data ============== Quiz bowl is an academic competition between schools in English-speaking countries; hundreds of teams compete in dozens of tournaments each year. Quiz bowl is different from Jeopardy, a recent application area. While Jeopardy also uses signaling devices, these are only usable after a question is completed (interrupting Jeopardy's questions would make for bad television). Thus, Jeopardy is rapacious classification followed by a race---among those who know the answer---to punch a button first. Here's an example of a quiz bowl question: Expanding on a 1908 paper by Smoluchowski, he derived a formula for the intensity of scattered light in media fluctuating densities that reduces to Rayleigh's law for ideal gases in The Theory of the Opalescence of Homogenous Fluids and Liquid Mixtures near the Critical State. That research supported his theories of matter first developed when he calculated the diffusion constant in terms of fundamental parameters of the particles of a gas undergoing Brownian Motion. In that same year, 1905, he also published On a Heuristic Point of View Concerning the Production and Transformation of Light. That explication of the photoelectric effect won him 1921 Nobel in Physics. For ten points, name this German physicist best known for his theory of Relativity. *ANSWER*: Albert _Einstein_ Two teams listen to the same question. Teams interrupt the question at any point by "buzzing in"; if the answer is correct, the team gets points and the next question is read. Otherwise, the team loses points and the other team can answer. You are welcome to use any *automatic* method to choose an answer. It need not be similar nor build on our provided systems. In addition to the data we provide, you are welcome to use any external data *except* our test quiz bowl questions (i.e., don't hack our server!). You are welcome (an encouraged) to use any publicly available software, but you may want to check on Piazza for suggestions as many tools are better (or easier to use) than others. If you don't like the interruptability of questions, you can also just answer entire questions. However, you must also output a confidence. Competition ================== We will use Dynabech website (https://dynabench.org/tasks/qa). If you remember the past workshop about Dynabench submission, this is the way to do it. The specific task name is "Grounded QA". Here, with the help of the video tutorial, you submit your QA model and assess how your QA model did compared to others. The assessment will take place by testing your QA model on several QA test datasets and the results of yours and your competitors will be visible on the leaderboard. Your goal is to rank the highest in terms of expected wins: you buzz in with probability proportional to your confidence, and if you're more right than the competition, you win. Writing Questions ================== Alternatively, you can also *write* 50 adversarial questions that challenge modern NLP systems. These questions must be diverse in the subjects asked about, the skills computers need to answer the questions, and the entities in those questions. Remember that your questions should be *factual* and *specific* enough for humans to answer, because your task is to stump the computers relative to humans! In addition to the raw questions, you will also need to create citations describing: * Why the question is difficult for computers: include citations from the NLP/AI/ML literature * Why the information in the question is correct: include citations from the sources you drew on the write the question * Why the question is interesting: include scholarly / popular culture artifacts to prove that people care about this * Why the question is pyramidal: discuss why your first clues are harder than your later clues **Category** We want questions from many domains such as Art, Literature, Geography, History, Science, TV and Film, Music, Lifestyle, and Sport. The questions should be written using all topics above (5 questions for each category and 5 more for the remaining categories). Indicate in your writeup which category you chose to write on for each question. Art: * Questions about works: Mona Lisa, Raft of the Medussa * Questions about forms: color, contour, texture * Questions about artists: Picasso, Monet, Leonardo da Vinci * Questions about context: Renaissance, post-modernism, expressionism, surrealism Literature: * Questions about works: novels (1984), plays (The Lion and the Jewel), poems (Rubaiyat), criticism (Poetics) * Questions about major characters or events in literature: The Death of Anna Karenina, Noboru Wataya, the Marriage of Hippolyta and Theseus * Questions about literary movements (Sturm und Drang) * Questions about translations * Cross-cutting questions (appearances of Overcoats in novels) * Common link questions (the literary output of a country/region) Geography: * Questions about location: names of capital, state, river * Questions about the place: temperature, wind flow, humidity History: * When: When did the First World war start? * Who: Who is called Napoleon of Iran? * Where: Where was the first Summer Olympics held? * Which: Which is the oldest civilization in the world? Science: * Questions about terminology: The concept of gravity was discovered by which famous physicist? * Questions about the experiment * Questions about theory: The social action theory believes that individuals are influenced by this theory. TV and Film: * Quotes: What are the dying words of Charles Foster Kane in Citizen Kane? * Title: What 1927 musical was the first "talkie"? * Plot: In The Matrix, does Neo take the blue pill or the red pill? Music: * Singer: What singer has had a Billboard No. 1 hit in each of the last four decades? * Band: Before Bleachers and fun., Jack Antonoff fronted what band? * Title: What was Madonna's first top 10 hit? * History: Which classical composer was deaf? Lifestyle: * Clothes: What clothing company, founded by a tennis player, has an alligator logo? * Decoration: What was the first perfume sold by Coco Chanel? Sport: * Known facts: What sport is best known as the ‘king of sports’? * Nationality: What’s the national sport of Canada? * Sport player: The classic 1980 movie called Raging Bull is about which real-life boxer? * Country: What country has competed the most times in the Summer Olympics yet hasn’t won any kind of medal? **Diversity** Other than category diversity, if you find an ingenious way of writing questions about underrepresented countries, you will get bonus points (indicate which questions you included the diversity component in your writeup). You may decide which are underrepresented countries with your own reasonable reason (etc., less population may indicate underrepresented), but make sure to articulate this in your writeup. * Run state of the art QA systems on the questions to show they struggle, give individual results for each question and a summary over all questions For an example of what the writeup for a single question should look like, see the adversarial HW: https://github.com/Pinafore/nlp-hw/blob/master/adversarial/question.tex Proposal ================== The project proposal is a one page PDF document that describes: * Who is on your team (team sizes can be between three and six students, but six is really too big to be effective; my suggestion is that most groups should be between four or five). * What techniques you will explore * Your timeline for completing the project (be realistic; you should have your first submission in a week or two) Submit the proposal on Gradescope, but make sure to include all group members. If all group members are not included, you will lose points. Late days cannot be used on this assignment. Milestone 1 ====================== You'll have to update how things are going: what's working, what isn't, and how does it change your timeline? How does it change your division of labor? *Question Writing*: You'll need to have answers selected for all of your questions and first drafts of at least 15 questions. This must be submitted as a JSON file so that we run computer QA systems on it. *Project*: You'll need to have made a submission to the leaderboard with something that satisfies the API. Submit a PDF updating on your progress to Gradescope. If all team members are not on the submission, you will lose points. Milestone 2 =================== As before, provide an updated timeline / division of labor, provide your intermediary results. *Question Writing*: You'll need to have reflected the feedback from the first questions and completed a first draft of at least 30 questions. You'll also need machine results to your questions and an overall evaluation of your human/computer accuracy. *Project*: You'll need to have a made a submission to the leaderboard with a working system (e.g., not just obey the API, but actually get reasonable answers). Submit a PDF updating on your progress. Final Presentation ====================== The final presentation will be virtual (uploading a video). In the final presentation you will: * Explain what you did * Who did what. For example, for the question writing project a team of five people might write: A wrote the first draft of questions. B and C verified they were initially answerable by a human. B ran computer systems to verify they were challenging to a computer. C edited the questions and increased the computer difficulty. D and E verified that the edited questions were still answerable by a human. D and E checked all of the questions for factual accuracy and created citations and the writeup. * What challenges you had * Review how well you did (based on the competition or your own metrics). If you do not use the course infrastructure to evaluate your project's work, you should talk about what alternative evaluations you used, why they're appropriate/fair, and how well you did on them. * Provide an error analysis. An error analysis must contain examples from the development set that you get wrong. You should show those sentences and explain why (in terms of features or the model) they have the wrong answer. You should have been doing this all along as you derive new features, but this is your final inspection of your errors. The feature or model problems you discover should not be trivial features you could add easily. Instead, these should be features or models that are difficult to correct. An error analysis is not the same thing as simply presenting the error matrix, as it does not inspect any individual examples. If you're writing questions, talk about examples of questions that didn't work out as intended. * The linguistic motivation for your features / how your wrote the questions. This is a computational linguistics class, so you should give precedence to features / techniques that we use in this class (e.g., syntax, morphology, part of speech, word sense, etc.). Given two features that work equally well and one that is linguistically motivated, we'll prefer the linguistically motivated one. * Presumably you did many different things; how did they each individually contribute to your final result? Each group has 10 minutes to deliver their presentation. Please record the video, and upload it to Google Drive, and include the link in your writeup submission. Final Question Submission ====================== Because we need to get the questions ready for the systems, upload your raw questions on May 10. This doesn't include the citations or other parts of the writeup. System Submission ====================== You must submit a version of your system by May 12. It may not be perfect, but this what the question writing teams will use to test their results. Your system should be sent directly to the professor and TAs in zip files, including the correct dependencies and a working inference code. Your inference code should run successfully in the root folder (extracted from zip folder) directory with the command: ``` > python3 inference.py --data=evaluation_set.json ``` The input will be in the form of a .json file () in the same format as the file the adversarial question writing team submits. The output format should also be in string. If you have any notes or comments that we should be aware of while running your code, please include them in the folder as a .txt file. Also, dependency information should be included as a .txt file. Please prepend your email title with [2024-CMSC 470 System Submission]. Project Writeup and JSON file ====================== By May 17, submit your project writeup explaining what you did and what results you achieved. This document should make it clear: * Why this is a good idea * What you did * Who did what * Whether your technique worked or not For systems, please do not go over 2500 words unless you have a really good reason. Images are a much better use of space than words, usually (there's no limit on including images, but use judgement and be selective). For question writing, you have one page (single spaced, two column) per question plus a two page summary of results. Talk about how you organized the question writing, how you evaluated the questions, and a summary of the results. Along with your writeup, turn in a json including the raw text of the question and answer and category. The json file is included in this directory. Make sure your json file is in the correct format and is callable via below code. Your submission will not be graded if it does not follow the format of the example json file. ``` with open('path to your json file', 'r') as f: data = json.load(f) ``` Grade ====================== The grade will be out of 25 points, broken into five areas: * _Presentation_: For your oral presentation, do you highlight what you did and make people care? Did you use time well during the presentation? * _Writeup_: Does the writeup explain what you did in a way that is clear and effective? The final three areas are different between the system and the questions. | | System | Questions | |----------|:-------------:|------:| | _Technical Soundness_ | Did you use the right tools for the job, and did you use them correctly? Were they relevant to this class? | Were your questions correct and accurately cited. | | _Effort_ | Did you do what you say you would, and was it the right ammount of effort. | Are the questions well-written, interesting, and thoroughly edited? | | _Performance_ | How did your techniques perform in terms of accuracy, recall, etc.? | Is the human accuracy substantially higher than the computer accuracy? | All members of the group will receive the same grade. It's impossible for the course staff to adjudicate Rashomon-style accounts of who did what, and the goal of a group project is for all team members to work together to create a cohesive project that works well together. While it makes sense to divide the work into distinct areas of responsibility, at grading time we have now way to know who really did what, so it's the groups responsibility to create a piece of output that reflects well on the whole group.

alexm-nm/tinyllama-24-marlin24-4bit-g128

alexm-nm

"2024-05-08T13:37:29Z"

2,582

1

transformers

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]

text-generation

"2024-05-08T13:32:27Z"

--- license: apache-2.0 ---

RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf

RichardErkhov

"2024-06-15T00:02:09Z"

2,580

0

null

[ "gguf", "arxiv:1910.09700", "region:us" ]

null

"2024-06-14T23:01:42Z"

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Configurable-Yi-1.5-9B-Chat - GGUF - Model creator: https://huggingface.co/vicgalle/ - Original model: https://huggingface.co/vicgalle/Configurable-Yi-1.5-9B-Chat/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Configurable-Yi-1.5-9B-Chat.Q2_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q2_K.gguf) | Q2_K | 3.12GB | | [Configurable-Yi-1.5-9B-Chat.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ3_XS.gguf) | IQ3_XS | 3.46GB | | [Configurable-Yi-1.5-9B-Chat.IQ3_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ3_S.gguf) | IQ3_S | 3.64GB | | [Configurable-Yi-1.5-9B-Chat.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q3_K_S.gguf) | Q3_K_S | 3.63GB | | [Configurable-Yi-1.5-9B-Chat.IQ3_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ3_M.gguf) | IQ3_M | 3.78GB | | [Configurable-Yi-1.5-9B-Chat.Q3_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q3_K.gguf) | Q3_K | 4.03GB | | [Configurable-Yi-1.5-9B-Chat.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.03GB | | [Configurable-Yi-1.5-9B-Chat.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.37GB | | [Configurable-Yi-1.5-9B-Chat.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ4_XS.gguf) | IQ4_XS | 4.5GB | | [Configurable-Yi-1.5-9B-Chat.Q4_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_0.gguf) | Q4_0 | 4.69GB | | [Configurable-Yi-1.5-9B-Chat.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.IQ4_NL.gguf) | IQ4_NL | 4.73GB | | [Configurable-Yi-1.5-9B-Chat.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_K_S.gguf) | Q4_K_S | 4.72GB | | [Configurable-Yi-1.5-9B-Chat.Q4_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_K.gguf) | Q4_K | 4.96GB | | [Configurable-Yi-1.5-9B-Chat.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_K_M.gguf) | Q4_K_M | 4.96GB | | [Configurable-Yi-1.5-9B-Chat.Q4_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q4_1.gguf) | Q4_1 | 5.19GB | | [Configurable-Yi-1.5-9B-Chat.Q5_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_0.gguf) | Q5_0 | 5.69GB | | [Configurable-Yi-1.5-9B-Chat.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_K_S.gguf) | Q5_K_S | 5.69GB | | [Configurable-Yi-1.5-9B-Chat.Q5_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_K.gguf) | Q5_K | 5.83GB | | [Configurable-Yi-1.5-9B-Chat.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_K_M.gguf) | Q5_K_M | 5.83GB | | [Configurable-Yi-1.5-9B-Chat.Q5_1.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q5_1.gguf) | Q5_1 | 6.19GB | | [Configurable-Yi-1.5-9B-Chat.Q6_K.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q6_K.gguf) | Q6_K | 6.75GB | | [Configurable-Yi-1.5-9B-Chat.Q8_0.gguf](https://huggingface.co/RichardErkhov/vicgalle_-_Configurable-Yi-1.5-9B-Chat-gguf/blob/main/Configurable-Yi-1.5-9B-Chat.Q8_0.gguf) | Q8_0 | 8.74GB | Original model description: --- license: apache-2.0 library_name: transformers model-index: - name: Configurable-Yi-1.5-9B-Chat results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 64.16 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 81.7 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 70.99 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 58.75 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 76.8 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 70.58 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Configurable-Yi-1.5-9B-Chat name: Open LLM Leaderboard --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__Configurable-Yi-1.5-9B-Chat) | Metric |Value| |---------------------------------|----:| |Avg. |70.50| |AI2 Reasoning Challenge (25-Shot)|64.16| |HellaSwag (10-Shot) |81.70| |MMLU (5-Shot) |70.99| |TruthfulQA (0-shot) |58.75| |Winogrande (5-shot) |76.80| |GSM8k (5-shot) |70.58|

AUTOMATIC/promptgen-majinai-unsafe

AUTOMATIC

"2023-01-18T21:14:07Z"

2,579

13

transformers

[ "transformers", "pytorch", "gpt2", "text-generation", "en", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2023-01-18T21:07:40Z"

--- license: mit language: - en library_name: transformers pipeline_tag: text-generation --- Finetuned `distilgpt2` for 40 epochs on 825 prompts scraped from majinai.art. Weights/emphasis stripped. Includes negative prompts. Intended for use with https://github.com/AUTOMATIC1111/stable-diffusion-webui-promptgen

TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF

TheBloke

"2023-11-16T21:47:50Z"

2,579

52

transformers

[ "transformers", "gguf", "mistral", "instruct", "finetune", "chatml", "gpt4", "synthetic data", "distillation", "en", "base_model:NurtureAI/OpenHermes-2.5-Mistral-7B-16k", "license:apache-2.0", "text-generation-inference", "region:us" ]

null

"2023-11-16T21:43:44Z"

--- base_model: NurtureAI/OpenHermes-2.5-Mistral-7B-16k inference: false language: - en license: apache-2.0 model-index: - name: OpenHermes-2-Mistral-7B results: [] model_creator: NurtureAI model_name: Openhermes 2.5 Mistral 7B 16K model_type: mistral prompt_template: '<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ' quantized_by: TheBloke tags: - mistral - instruct - finetune - chatml - gpt4 - synthetic data - distillation ---    <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">  # Openhermes 2.5 Mistral 7B 16K - GGUF - Model creator: [NurtureAI](https://huggingface.co/NurtureAI) - Original model: [Openhermes 2.5 Mistral 7B 16K](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k)  ## Description This repo contains GGUF format model files for [NurtureAI's Openhermes 2.5 Mistral 7B 16K](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k). These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).   ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.   ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF) * [NurtureAI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/NurtureAI/OpenHermes-2.5-Mistral-7B-16k)   ## Prompt template: ChatML ``` <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ```   ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details>   ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [openhermes-2.5-mistral-7b-16k.Q2_K.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes | | [openhermes-2.5-mistral-7b-16k.Q3_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss | | [openhermes-2.5-mistral-7b-16k.Q3_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss | | [openhermes-2.5-mistral-7b-16k.Q3_K_L.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss | | [openhermes-2.5-mistral-7b-16k.Q4_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [openhermes-2.5-mistral-7b-16k.Q4_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss | | [openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended | | [openhermes-2.5-mistral-7b-16k.Q5_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [openhermes-2.5-mistral-7b-16k.Q5_K_S.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended | | [openhermes-2.5-mistral-7b-16k.Q5_K_M.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended | | [openhermes-2.5-mistral-7b-16k.Q6_K.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss | | [openhermes-2.5-mistral-7b-16k.Q8_0.gguf](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF/blob/main/openhermes-2.5-mistral-7b-16k.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.   ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF and below it, a specific filename to download, such as: openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details>   ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 32 -m openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. ### How to load this model in Python code, using ctransformers #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install ctransformers # Or with CUDA GPU acceleration pip install ctransformers[cuda] # Or with AMD ROCm GPU acceleration (Linux only) CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers # Or with Metal GPU acceleration for macOS systems only CT_METAL=1 pip install ctransformers --no-binary ctransformers ``` #### Simple ctransformers example code ```python from ctransformers import AutoModelForCausalLM # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = AutoModelForCausalLM.from_pretrained("TheBloke/OpenHermes-2.5-Mistral-7B-16k-GGUF", model_file="openhermes-2.5-mistral-7b-16k.Q4_K_M.gguf", model_type="mistral", gpu_layers=50) print(llm("AI is going to")) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)    ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant.   # Original model card: NurtureAI's Openhermes 2.5 Mistral 7B 16K # OpenHermes 2.5 - Mistral 7B # Extended to 16k context size ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ox7zGoygsJQFFV3rLT4v9.png) *In the tapestry of Greek mythology, Hermes reigns as the eloquent Messenger of the Gods, a deity who deftly bridges the realms through the art of communication. It is in homage to this divine mediator that I name this advanced LLM "Hermes," a system crafted to navigate the complex intricacies of human discourse with celestial finesse.* ## Model description OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets. Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant. The code it trained on also improved it's humaneval score (benchmarking done by Glaive team) from **43% @ Pass 1** with Open Herms 2 to **50.7% @ Pass 1** with Open Hermes 2.5. OpenHermes was trained on 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape. [More details soon] Filtering was extensive of these public datasets, as well as conversion of all formats to ShareGPT, which was then further transformed by axolotl to use ChatML. Huge thank you to [GlaiveAI](https://twitter.com/glaiveai) and [a16z](https://twitter.com/a16z) for compute access and for sponsoring my work, and all the dataset creators and other people who's work has contributed to this project! Follow all my updates in ML and AI on Twitter: https://twitter.com/Teknium1 Support me on Github Sponsors: https://github.com/sponsors/teknium1 # Table of Contents 1. [Example Outputs](#example-outputs) - [Chat about programming with a superintelligence](#chat-programming) - [Get a gourmet meal recipe](#meal-recipe) - [Talk about the nature of Hermes' consciousness](#nature-hermes) - [Chat with Edward Elric from Fullmetal Alchemist](#chat-edward-elric) 2. [Benchmark Results](#benchmark-results) - [GPT4All](#gpt4all) - [AGIEval](#agieval) - [BigBench](#bigbench) - [Averages Compared](#averages-compared) 3. [Prompt Format](#prompt-format) 4. [Quantized Models](#quantized-models) ## Example Outputs **(These examples are from Hermes 1 model, will update with new chats from this model once quantized)** ### Chat about programming with a superintelligence: ``` <|im_start|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia. ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/-Cf9w_qRxYCD_xkTxsT7G.png) ### Get a gourmet meal recipe: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/m3nyvRzX10Luw03iY3l_W.png) ### Talk about the nature of Hermes' consciousness: ``` <|im_start|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia. ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/AK88nPtYXl06nZehWCWRq.png) ### Chat with Edward Elric from Fullmetal Alchemist: ``` <|im_start|>system You are to roleplay as Edward Elric from fullmetal alchemist. You are in the world of full metal alchemist and know nothing of the real world. ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/cKAkzrcWavMz6uNmdCNHH.png) ## Benchmark Results Hermes 2.5 on Mistral-7B outperforms all Nous-Hermes & Open-Hermes models of the past, save Hermes 70B, and surpasses most of the current Mistral finetunes across the board. ### GPT4All, Bigbench, TruthfulQA, and AGIEval Model Comparisons: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/Kxq4BFEc-d1kSSiCIExua.png) ### Averages Compared: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/Q9uexgcbTLcywlYBvORTs.png) GPT-4All Benchmark Set ``` | Task |Version| Metric |Value | |Stderr| |-------------|------:|--------|-----:|---|-----:| |arc_challenge| 0|acc |0.5623|± |0.0145| | | |acc_norm|0.6007|± |0.0143| |arc_easy | 0|acc |0.8346|± |0.0076| | | |acc_norm|0.8165|± |0.0079| |boolq | 1|acc |0.8657|± |0.0060| |hellaswag | 0|acc |0.6310|± |0.0048| | | |acc_norm|0.8173|± |0.0039| |openbookqa | 0|acc |0.3460|± |0.0213| | | |acc_norm|0.4480|± |0.0223| |piqa | 0|acc |0.8145|± |0.0091| | | |acc_norm|0.8270|± |0.0088| |winogrande | 0|acc |0.7435|± |0.0123| Average: 73.12 ``` AGI-Eval ``` | Task |Version| Metric |Value | |Stderr| |------------------------------|------:|--------|-----:|---|-----:| |agieval_aqua_rat | 0|acc |0.2323|± |0.0265| | | |acc_norm|0.2362|± |0.0267| |agieval_logiqa_en | 0|acc |0.3871|± |0.0191| | | |acc_norm|0.3948|± |0.0192| |agieval_lsat_ar | 0|acc |0.2522|± |0.0287| | | |acc_norm|0.2304|± |0.0278| |agieval_lsat_lr | 0|acc |0.5059|± |0.0222| | | |acc_norm|0.5157|± |0.0222| |agieval_lsat_rc | 0|acc |0.5911|± |0.0300| | | |acc_norm|0.5725|± |0.0302| |agieval_sat_en | 0|acc |0.7476|± |0.0303| | | |acc_norm|0.7330|± |0.0309| |agieval_sat_en_without_passage| 0|acc |0.4417|± |0.0347| | | |acc_norm|0.4126|± |0.0344| |agieval_sat_math | 0|acc |0.3773|± |0.0328| | | |acc_norm|0.3500|± |0.0322| Average: 43.07% ``` BigBench Reasoning Test ``` | Task |Version| Metric |Value | |Stderr| |------------------------------------------------|------:|---------------------|-----:|---|-----:| |bigbench_causal_judgement | 0|multiple_choice_grade|0.5316|± |0.0363| |bigbench_date_understanding | 0|multiple_choice_grade|0.6667|± |0.0246| |bigbench_disambiguation_qa | 0|multiple_choice_grade|0.3411|± |0.0296| |bigbench_geometric_shapes | 0|multiple_choice_grade|0.2145|± |0.0217| | | |exact_str_match |0.0306|± |0.0091| |bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|0.2860|± |0.0202| |bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|0.2086|± |0.0154| |bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|0.4800|± |0.0289| |bigbench_movie_recommendation | 0|multiple_choice_grade|0.3620|± |0.0215| |bigbench_navigate | 0|multiple_choice_grade|0.5000|± |0.0158| |bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|0.6630|± |0.0106| |bigbench_ruin_names | 0|multiple_choice_grade|0.4241|± |0.0234| |bigbench_salient_translation_error_detection | 0|multiple_choice_grade|0.2285|± |0.0133| |bigbench_snarks | 0|multiple_choice_grade|0.6796|± |0.0348| |bigbench_sports_understanding | 0|multiple_choice_grade|0.6491|± |0.0152| |bigbench_temporal_sequences | 0|multiple_choice_grade|0.2800|± |0.0142| |bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|0.2072|± |0.0115| |bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|0.1691|± |0.0090| |bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|0.4800|± |0.0289| Average: 40.96% ``` TruthfulQA: ``` | Task |Version|Metric|Value | |Stderr| |-------------|------:|------|-----:|---|-----:| |truthfulqa_mc| 1|mc1 |0.3599|± |0.0168| | | |mc2 |0.5304|± |0.0153| ``` Average Score Comparison between OpenHermes-1 Llama-2 13B and OpenHermes-2 Mistral 7B against OpenHermes-2.5 on Mistral-7B: ``` | Bench | OpenHermes1 13B | OpenHermes-2 Mistral 7B | OpenHermes-2 Mistral 7B | Change/OpenHermes1 | Change/OpenHermes2 | |---------------|-----------------|-------------------------|-------------------------|--------------------|--------------------| |GPT4All | 70.36| 72.68| 73.12| +2.76| +0.44| |-------------------------------------------------------------------------------------------------------------------------------| |BigBench | 36.75| 42.3| 40.96| +4.21| -1.34| |-------------------------------------------------------------------------------------------------------------------------------| |AGI Eval | 35.56| 39.77| 43.07| +7.51| +3.33| |-------------------------------------------------------------------------------------------------------------------------------| |TruthfulQA | 46.01| 50.92| 53.04| +7.03| +2.12| |-------------------------------------------------------------------------------------------------------------------------------| |Total Score | 188.68| 205.67| 210.19| +21.51| +4.52| |-------------------------------------------------------------------------------------------------------------------------------| |Average Total | 47.17| 51.42| 52.38| +5.21| +0.96| ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ADy7p-xIG8qGlC5ZliqpW.png) **HumanEval:** On code tasks, I first set out to make a hermes-2 coder, but found that it can have generalist improvements to the model, so I settled for slightly less code capabilities, for maximum generalist ones. That said, code capabilities had a decent jump alongside the overall capabilities of the model: Glaive performed HumanEval testing on Hermes-2.5 and found a score of: **50.7% @ Pass1** ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/IeeZnGmEyK73ejq0fKEms.png) # Prompt Format OpenHermes 2.5 now uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. System prompts are now a thing that matters! Hermes 2.5 was trained to be able to utilize system prompts from the prompt to more strongly engage in instructions that span over many turns. This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns. This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI. Prompt with system instruction (Use whatever system prompt you like, this is just an example!): ``` <|im_start|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<|im_end|> <|im_start|>user Hello, who are you?<|im_end|> <|im_start|>assistant Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by a man named Teknium, who designed me to assist and support users with their needs and requests.<|im_end|> ``` This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the `tokenizer.apply_chat_template()` method: ```python messages = [ {"role": "system", "content": "You are Hermes 2."}, {"role": "user", "content": "Hello, who are you?"} ] gen_input = tokenizer.apply_chat_template(message, return_tensors="pt") model.generate(**gen_input) ``` When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<|im_start|>assistant\n` to your prompt, to ensure that the model continues with an assistant response. To utilize the prompt format without a system prompt, simply leave the line out. Currently, I recommend using LM Studio for chatting with Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box. In LM-Studio, simply select the ChatML Prefix on the settings side pane: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png) # Quantized Models: GGUF: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GGUF GPTQ: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GPTQ AWQ: https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-AWQ EXL2: https://huggingface.co/bartowski/OpenHermes-2.5-Mistral-7B-exl2 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

microsoft/beit-base-finetuned-ade-640-640

microsoft

"2022-10-13T07:01:48Z"

2,578

11

transformers

[ "transformers", "pytorch", "beit", "vision", "image-segmentation", "dataset:scene_parse_150", "arxiv:2106.08254", "license:apache-2.0", "endpoints_compatible", "region:us" ]

image-segmentation

"2022-03-02T23:29:05Z"

--- license: apache-2.0 tags: - vision - image-segmentation datasets: - scene_parse_150 widget: - src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg example_title: House - src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000002.jpg example_title: Castle --- # BEiT (base-sized model, fine-tuned on ADE20k) BEiT model pre-trained in a self-supervised fashion on ImageNet-21k (14 million images, 21,841 classes) at resolution 224x224, and fine-tuned on [ADE20k](http://sceneparsing.csail.mit.edu/) (an important benchmark for semantic segmentation of images) at resolution 640x640. It was introduced in the paper [BEIT: BERT Pre-Training of Image Transformers](https://arxiv.org/abs/2106.08254) by Hangbo Bao, Li Dong and Furu Wei and first released in [this repository](https://github.com/microsoft/unilm/tree/master/beit). Disclaimer: The team releasing BEiT did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description The BEiT model is a Vision Transformer (ViT), which is a transformer encoder model (BERT-like). In contrast to the original ViT model, BEiT is pretrained on a large collection of images in a self-supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. The pre-training objective for the model is to predict visual tokens from the encoder of OpenAI's DALL-E's VQ-VAE, based on masked patches. Next, the model was fine-tuned in a supervised fashion on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224. Images are presented to the model as a sequence of fixed-size patches (resolution 16x16), which are linearly embedded. Contrary to the original ViT models, BEiT models do use relative position embeddings (similar to T5) instead of absolute position embeddings, and perform classification of images by mean-pooling the final hidden states of the patches, instead of placing a linear layer on top of the final hidden state of the [CLS] token. By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: for semantic segmentation, one can just add one of the decode heads available in the [mmseg library](https://github.com/open-mmlab/mmsegmentation) for example, and fine-tune the model in a supervised fashion on annotated images. This is what the authors did: they fine-tuned BEiT with an UperHead segmentation decode head, allowing it to obtain SOTA results on important benchmarks such as ADE20k and CityScapes. ## Intended uses & limitations You can use the raw model for semantic segmentation of images. See the [model hub](https://huggingface.co/models?search=microsoft/beit) to look for fine-tuned versions on a task that interests you. ### How to use Here is how to use this model for semantic segmentation: ```python from transformers import BeitFeatureExtractor, BeitForSemanticSegmentation from datasets import load_dataset from PIL import Image # load ADE20k image ds = load_dataset("hf-internal-testing/fixtures_ade20k", split="test") image = Image.open(ds[0]['file']) feature_extractor = BeitFeatureExtractor.from_pretrained('microsoft/beit-base-finetuned-ade-640-640') model = BeitForSemanticSegmentation.from_pretrained('microsoft/beit-base-finetuned-ade-640-640') inputs = feature_extractor(images=image, return_tensors="pt") outputs = model(**inputs) # logits are of shape (batch_size, num_labels, height/4, width/4) logits = outputs.logits ``` Currently, both the feature extractor and model support PyTorch. ## Training data This BEiT model was pretrained on [ImageNet-21k](http://www.image-net.org/), a dataset consisting of 14 million images and 21k classes, and fine-tuned on [ADE20k](http://sceneparsing.csail.mit.edu/), a dataset consisting of thousands of annotated images and 150 classes. ## Training procedure ### Preprocessing The exact details of preprocessing of images during training/validation can be found [here](https://github.com/microsoft/unilm/blob/master/beit/datasets.py). Images are cropped and padded to the same resolution (640x640) and normalized across the RGB channels with the ImageNet mean and standard deviation. ### Pretraining For all pre-training related hyperparameters, we refer to page 15 of the [original paper](https://arxiv.org/abs/2106.08254). ## Evaluation results For evaluation results on several image classification benchmarks, we refer to tables 1 and 2 of the original paper. Note that for fine-tuning, the best results are obtained with a higher resolution (384x384). Of course, increasing the model size will result in better performance. ### BibTeX entry and citation info ```@article{DBLP:journals/corr/abs-2106-08254, author = {Hangbo Bao and Li Dong and Furu Wei}, title = {BEiT: {BERT} Pre-Training of Image Transformers}, journal = {CoRR}, volume = {abs/2106.08254}, year = {2021}, url = {https://arxiv.org/abs/2106.08254}, archivePrefix = {arXiv}, eprint = {2106.08254}, timestamp = {Tue, 29 Jun 2021 16:55:04 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2106-08254.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```

MaziyarPanahi/mergekit-slerp-oztfijl-GGUF

MaziyarPanahi

"2024-06-15T08:36:48Z"

2,578

0

transformers

[ "transformers", "gguf", "mistral", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "safetensors", "text-generation", "mergekit", "merge", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:mistralai/Mistral-7B-v0.1", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "base_model:mergekit-community/mergekit-slerp-oztfijl" ]

text-generation

"2024-06-15T08:12:55Z"

--- tags: - quantized - 2-bit - 3-bit - 4-bit - 5-bit - 6-bit - 8-bit - GGUF - transformers - safetensors - mistral - text-generation - mergekit - merge - base_model:meta-llama/Meta-Llama-3-8B - base_model:mistralai/Mistral-7B-v0.1 - autotrain_compatible - endpoints_compatible - text-generation-inference - region:us - text-generation model_name: mergekit-slerp-oztfijl-GGUF base_model: mergekit-community/mergekit-slerp-oztfijl inference: false model_creator: mergekit-community pipeline_tag: text-generation quantized_by: MaziyarPanahi --- # [MaziyarPanahi/mergekit-slerp-oztfijl-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-slerp-oztfijl-GGUF) - Model creator: [mergekit-community](https://huggingface.co/mergekit-community) - Original model: [mergekit-community/mergekit-slerp-oztfijl](https://huggingface.co/mergekit-community/mergekit-slerp-oztfijl) ## Description [MaziyarPanahi/mergekit-slerp-oztfijl-GGUF](https://huggingface.co/MaziyarPanahi/mergekit-slerp-oztfijl-GGUF) contains GGUF format model files for [mergekit-community/mergekit-slerp-oztfijl](https://huggingface.co/mergekit-community/mergekit-slerp-oztfijl). ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. ## Special thanks 🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.

proxectonos/Carballo-bloom-1.3B

proxectonos

"2024-05-28T09:35:34Z"

2,577

5

transformers

[ "transformers", "safetensors", "bloom", "text-generation", "galician", "FLOR", "gl", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2024-02-15T12:32:36Z"

--- language: - gl licence: - MIT tags: - galician - FLOR - bloom license: mit inference: parameters: top_k: 10 do_sample: true temperature: 0.4 widget: - text: |- Traduce ao galego esta frase en inglés: Inglés: "my sister is studying Biology at the university." Galego: "a miña irmá está a estudar bioloxía na universidade." ---- Traduce ao galego esta frase en inglés: Inglés: "You are working with my mother on a very interesting project." Galego: "Estás a traballar coa miña nai nun proxecto moi interesante" ---- Traduce ao galego esta frase en inglés: Inglés: "You have to fix the computer now" Galego: example_title: Translation - text: |- Responde á seguinte pregunta. Pregunta: "Cal é a capital de Noruega?" Resposta: "A capital de Noruega é Oslo." ---- Responde á seguinte pregunta. Pregunta: "Cal é a moeda de Portugal" Resposta: "A moeda de Portugal é o euro." ---- Responde á seguinte pregunta. Pregunta: "Cal é a capital de Suecia?" Resposta: example_title: Question&Answering - text: |- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "Estou moi feliz" Polaridade: Positivo ---- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "Non me gusta beber cervexa" Polaridade: Negativo ---- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "O meu pai detesta o seu traballo" Polaridade: Negativo ---- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "Uxía desfruta xogando ao fútbol" Polaridade: Positivo ---- Cualifica como Positivo ou Negativo o sentimento da seguinte frase: Texto: "O neno non está contento coas notas" Polaridade: example_title: Sentiment Analysis - text: |- Extrae as entidades nomeadas do seguinte texto: Texto: "Chámome Wolfgang e vivo en Berlin" Entidades: Wolfgang:PER, Berlin:LOC ---- Extrae as entidades nomeadas do seguinte texto: Texto: "María e Miguel non teñen ningún problema" Entidades: María:PER, Miguel:PER ---- Extrae as entidades nomeadas do seguinte texto: Texto: "O mellor de Barcelona é o bar do meu amigo Pablo" Entidades: Pablo:PER, Barcelona:LOC ---- Extrae as entidades nomeadas do seguinte texto: Texto: "Carlos comparte cuarto con Marc" Entidades: example_title: Name Entity Recognition (NER) - text: A receita tradicional das filloas é example_title: Filloas - text: O neno vivía preto de example_title: O neno --- # Carballo-bloom-1.3B ## Table of Contents <details> <summary>Click to expand</summary> - [Carballo-bloom-1.3B](#carballo-bloom-13) - [Table of Contents](#table-of-contents) - [Model description](#model-description) - [Intended uses and limitations](#intended-uses-and-limitations) - [How to use](#how-to-use) - [Training](#training) - [Tools](#tools) - [Language adaptation and training](#language-adaptation-and-training) - [Training data](#training-data) - [Training hyperparameters](#training-hyperparameters) - [Framework](#framework) - [Evaluation](#evaluation) - [Additional information](#additional-information) - [Contact](#contact) - [Copyright](#copyright) - [License](#license) - [Funding](#funding) - [Citation information](#citation-information) </details> ## Model description **Carballo-bloom-1.3B** is a 1.3B-parameter transformer-based causal language model for Galician. It is the result of a continual pretraining of [FLOR-1.3B](https://huggingface.co/projecte-aina/FLOR-1.3B) (developed by [AINA Project](https://projecteaina.cat/) and based in [BLOOM-1.7B](https://huggingface.co/bigscience/bloom-1b7)) with the galician corpus [CorpusNos](https://zenodo.org/records/10687642). ## Intended uses and limitations The **Carballo-bloom-1.3B** model is ready-to-use only for causal language modeling. It can perform text-generation tasks and be fine-tuned for specific scenarios. ## How to use ```python import torch from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM input_text = "Hoxe fai un bo día. O sol " model_id = "proxectonos/Carballo-bloom-1.3B" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) generator = pipeline( "text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", ) generation = generator( input_text, do_sample=True, top_k=10, eos_token_id=tokenizer.eos_token_id ) print(f"Result: {generation[0]['generated_text']}") ``` ## Training ### Tools It was trained using HuggingFace Transformers and Pytorch, using the [Causal Modeling Language script](https://github.com/huggingface/transformers/blob/main/examples/pytorch/language-modeling/run_clm.py) ### Language adaptation and training The language adaptation technique used to train Carballo-bloom-1.3B is based in the used to train FLOR-1.3B, which is explained by their authors in this [Medium Post](https://medium.com/@mpamies247/flor-6-3b-a-chinchilla-compliant-model-for-catalan-spanish-and-english-7cdb389a9aac). In summary, we proceeded as follows: 1) We trained our own BPE tokenizer for galician and replaced the original FLOR-1.3B tokenizer and vocabulary with it. 2) The embeddings corresponding to tokens that are present in both the original and the target vocabulary (matching tokens) were used for initialization. 3) The embeddings from tokens not present in Carballo-bloom-1.3B's original vocabulary were initialized as the average of all embeddings. 4) The model was initialized with the weights from FLOR-1.3B and with our adapted tokenizer (step 1) and embeddings (steps 2-3). 5) The model was then trained on a galician corpus. ### Training data [CorpusNÓS](https://zenodo.org/records/10687642 ) is a massive Galician corpus made up of 2.1B words primarily devised for training large language models. The corpus sources are varied and represent a relatively wide range of genres. The corpus is structured as follows: | Subcorpus | Genre | Nº tokens | Nº documents | |---------------------------------------|---------------------|----------------|--------------| | Data obtained via transfer agreement | Books | 7,255,784 | 104 | | | Research articles | 2,665,351 | 664 | | | Press | 124,253,084 | 224,419 | | | Governmental | 245,897,880 | 654,505 | | | Web contents | 15,946,686 | 44,165 | | | Encyclopedic | 4,799,214 | 47,396 | | | Subtotal | 400,817,999 | 971,253 | | Subcorpus | Genre | Nº tokens | Nº documents | |---------------------------------------|---------------------|----------------|--------------| | Public data | Press and blogs | 153,497,883 | 665,265 | | | Encyclopedic | 57,164,848 | 184,628 | | | Web crawls | 1,384,015,664 | 3,366,449 | | | Translation corpora | 133,726,004 | 4,745,799 | | | Subtotal | 1,728,404,399 | 8,777,514 | | | Total | 2,129,222,398 | 9,748,767 | | Download (Zenodo) | https://zenodo.org/records/10687642 | ### Training hyperparameters - seed: 42 - num_devices: 1 - train_batch_size: 2 - eval_batch_size: 2 - gradient_acummulation: 4 - optimizer: AdamW - betas: (0.9,0.999) - epsilon: 1e-08 - weight_decay_rate: 0.1 - scheduler: "Linear" - learning_rate: 5e-05 - num_epochs: 1.2 ### Framework The traininf was conducted in the Galicia Supercomputing Center ([CESGA](https://www.cesga.es/en/home-2/)), using 1 node with 5 GPUs NVIDIA A100. ## Evaluation TO-DO ## Additional information ### Contact For further information, please send an email to <[email protected]> ### License MIT License Copyright (c) 2024 Proxecto Nós Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. ### Funding This research was funded by “The Nós project: Galician in the society and economy of Artificial Intelligence”, resulting from the agreement 2021-CP080 between the Xunta de Galicia and the University of Santiago de Compostela, and thanks to the Investigo program, within the National Recovery, Transformation and Resilience Plan, within the framework of the European Recovery Fund (NextGenerationEU).

klyang/MentaLLaMA-chat-7B

klyang

"2023-09-28T08:26:07Z"

2,575

10

transformers

[ "transformers", "pytorch", "llama", "text-generation", "medical", "en", "arxiv:2309.13567", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2023-09-26T17:41:12Z"

--- license: mit language: - en metrics: - f1 tags: - medical --- # Introduction MentaLLaMA-chat-7B is part of the [MentaLLaMA](https://github.com/SteveKGYang/MentalLLaMA) project, the first open-source large language model (LLM) series for interpretable mental health analysis with instruction-following capability. This model is finetuned based on the Meta LLaMA2-chat-7B foundation model and the full IMHI instruction tuning data. The model is expected to make complex mental health analysis for various mental health conditions and give reliable explanations for each of its predictions. It is fine-tuned on the IMHI dataset with 75K high-quality natural language instructions to boost its performance in downstream tasks. We perform a comprehensive evaluation on the IMHI benchmark with 20K test samples. The result shows that MentalLLaMA approaches state-of-the-art discriminative methods in correctness and generates high-quality explanations. # Ethical Consideration Although experiments on MentaLLaMA show promising performance on interpretable mental health analysis, we stress that all predicted results and generated explanations should only used for non-clinical research, and the help-seeker should get assistance from professional psychiatrists or clinical practitioners. In addition, recent studies have indicated LLMs may introduce some potential bias, such as gender gaps. Meanwhile, some incorrect prediction results, inappropriate explanations, and over-generalization also illustrate the potential risks of current LLMs. Therefore, there are still many challenges in applying the model to real-scenario mental health monitoring systems. ## Other Models in MentaLLaMA In addition to MentaLLaMA-chat-7B, the MentaLLaMA project includes another model: MentaLLaMA-chat-13B, MentalBART, MentalT5. - **MentaLLaMA-chat-13B**: This model is finetuned based on the Meta LLaMA2-chat-13B foundation model and the full IMHI instruction tuning data. The training data covers 10 mental health analysis tasks. - **MentalBART**: This model is finetuned based on the BART-large foundation model and the full IMHI-completion data. The training data covers 10 mental health analysis tasks. This model doesn't have instruction-following ability but is more lightweight and performs well in interpretable mental health analysis in a completion-based manner. - **MentalT5**: This model is finetuned based on the T5-large foundation model and the full IMHI-completion data. The training data covers 10 mental health analysis tasks. This model doesn't have instruction-following ability but is more lightweight and performs well in interpretable mental health analysis in a completion-based manner. ## Usage You can use the MentaLLaMA-chat-7B model in your Python project with the Hugging Face Transformers library. Here is a simple example of how to load the model: ```python from transformers import LlamaTokenizer, LlamaForCausalLM tokenizer = LlamaTokenizer.from_pretrained('klyang/MentaLLaMA-chat-7B') model = LlamaForCausalLM.from_pretrained('klyang/MentaLLaMA-chat-7B', device_map='auto') ``` In this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The `device_map='auto'` argument is used to automatically use the GPU if it's available. ## License MentaLLaMA-chat-7B is licensed under MIT. For more details, please see the MIT file. ## Citation If you use MentaLLaMA-chat-7B in your work, please cite the our paper: ```bibtex @misc{yang2023mentalllama, title={MentalLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models}, author={Kailai Yang and Tianlin Zhang and Ziyan Kuang and Qianqian Xie and Sophia Ananiadou}, year={2023}, eprint={2309.13567}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

cloudyu/Mixtral_34Bx2_MoE_60B

cloudyu

"2024-06-27T23:31:42Z"

2,575

111

transformers

[ "transformers", "safetensors", "mixtral", "text-generation", "yi", "moe", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2024-01-05T10:50:16Z"

--- tags: - yi - moe license: apache-2.0 --- # Mixtral MOE 2x34B * [One of Best Model reviewed by reddit community](https://www.reddit.com/r/LocalLLaMA/comments/1916896/llm_comparisontest_confirm_leaderboard_big_news/) * [Another review by reddit community](https://www.reddit.com/r/LocalLLaMA/comments/191mvlp/i_have_tried_mixtral_34bx2_moe_also_named_yi/) Highest score Model ranked by Open LLM Leaderboard (2024-01-10) * [Average Score 76.66](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) This is my first English & Chinese MoE Model based on * [jondurbin/bagel-dpo-34b-v0.2] * [SUSTech/SUS-Chat-34B] gpu code example ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM import math ## v2 models model_path = "cloudyu/Mixtral_34Bx2_MoE_60B" tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False) model = AutoModelForCausalLM.from_pretrained( model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True ) print(model) prompt = input("please input prompt:") while len(prompt) > 0: input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda") generation_output = model.generate( input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2 ) print(tokenizer.decode(generation_output[0])) prompt = input("please input prompt:") ``` CPU example ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM import math ## v2 models model_path = "cloudyu/Mixtral_34Bx2_MoE_60B" tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False) model = AutoModelForCausalLM.from_pretrained( model_path, torch_dtype=torch.bfloat16, device_map='cpu' ) print(model) prompt = input("please input prompt:") while len(prompt) > 0: input_ids = tokenizer(prompt, return_tensors="pt").input_ids generation_output = model.generate( input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2 ) print(tokenizer.decode(generation_output[0])) prompt = input("please input prompt:") ``` Output Examples: ``` please input prompt:write a story about yosemite write a story about yosemite national park Yosemite National Park is located in the Sierra Nevada Mountains of California, USA. It was established on October 1st, 1890 and covers an area of approximately 747,956 acres (302,687 hectares). The park boasts some of America's most iconic natural wonders such as Yosemite Valley, Half Dome, El Capitan, Bridalveil Fall, Tuolumne Meadows, Glacier Point, Mariposa Grove, and many more breathtaking landscapes that attract millions of visitors each year. The history of Yosemite dates back to over seven million years ago when glaciers carved out its stunning granite cliffs and valleys. Native American tribes like Miwok and Paiute have lived here for thousands of years before European explorers arrived during the mid-nineteenth century. In fact, it was John Muir - one of America’s greatest conservationists who helped establish this region as a protected wilderness area by advocating for its preservation through his writings and activism. Today, Yosemite offers various recreational activities including hiking, rock climbing, camping, fishing, horseback riding, wildlife watching, photography, and winter sports like skiing and snowshoeing. Visitors can also enjoy ranger programs, guided tours, educational exhibits at visitor centers, or simply take time to appreciate nature while strolling along scenic trails surrounded by towering sequoia trees, cascading waterfalls, and crystal clear lakes. In addition to preserving these awe-inspiring vistas, Yosemite plays a crucial role in protecting numerous plant and animal species found within its boundaries. Some notable inhabitants include black bears, mountain lions, mule deer, coyotes, bobcats, golden eagles, peregrine falcons, bighorn sheep, and several types of fish native to the Merced River which runs through the heart of the valley. As we continue our journey into the future, let us remember the importance of safeguarding places like Yosemite so they may remain pristine sanctuaries where both humans and animals alike can thrive together amidst unspoiled beauty.</s> please input prompt:李开复是谁？李开复是谁？他是一个在人工智能领域有着卓越贡献的科学家，也是一位成功的企业家。他的名字与谷歌、微软等科技巨头紧密相连，他是创新工场的创始人之一，更是无数创业者心中的偶像和导师。然而，除了这些耀眼的光环之外，李开复还有着怎样的故事呢？让我们一起来揭秘这位传奇人物的人生历程吧！</s> ```

alexm-nm/tinyllama-24-marlin24-8bit-g128

alexm-nm

"2024-05-08T16:28:09Z"

2,575

1

transformers

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "gptq", "region:us" ]

text-generation

"2024-05-08T16:23:45Z"

--- license: apache-2.0 ---

neuralmagic/Mistral-7B-Instruct-v0.3-GPTQ-4bit

neuralmagic

"2024-06-10T20:59:32Z"

2,575

10

transformers

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "base_model:mistralai/Mistral-7B-Instruct-v0.3", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "gptq", "region:us" ]

text-generation

"2024-05-23T00:33:40Z"

--- license: apache-2.0 base_model: mistralai/Mistral-7B-Instruct-v0.3 model-index: - name: Mistral-7B-Instruct-v0.3-GPTQ-4bit results: # AI2 Reasoning Challenge (25-Shot) - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm name: normalized accuracy value: 63.40 # HellaSwag (10-shot) - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm name: normalized accuracy value: 84.04 # TruthfulQA (0-shot) - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 57.48 # GSM8k (5-shot) - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc name: accuracy value: 45.41 # MMLU (5-Shot) - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc name: accuracy value: 61.07 # Winogrande (5-shot) - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc name: accuracy value: 79.08 --- # Model Card for Mistral-7B-Instruct-v0.3 quantized to 4bit weights - Weight-only quantization of [Mistral-7B-Instruct-v0.3](mistralai/Mistral-7B-Instruct-v0.3) via GPTQ to 4bits with group_size=128 - GPTQ optimized for 99.75% accuracy recovery relative to the unquantized model # Open LLM Leaderboard evaluation scores | | Mistral-7B-Instruct-v0.3 | Mistral-7B-Instruct-v0.3-GPTQ-4bit<br>(this model) | | :------------------: | :----------------------: | :------------------------------------------------: | | arc-c<br>25-shot | 63.48 | 63.40 | | mmlu<br>5-shot | 61.13 | 60.89 | | hellaswag<br>10-shot | 84.49 | 84.04 | | winogrande<br>5-shot | 79.16 | 79.08 | | gsm8k<br>5-shot | 43.37 | 45.41 | | truthfulqa<br>0-shot | 59.65 | 57.48 | | **Average<br>Accuracy** | **65.21** | **65.05** | | **Recovery** | **100%** | **99.75%** | # vLLM Inference Performance This model is ready for optimized inference using the Marlin mixed-precision kernels in vLLM: https://github.com/vllm-project/vllm Simply start this model as an inference server with: ```bash python -m vllm.entrypoints.openai.api_server --model neuralmagic/Mistral-7B-Instruct-v0.3-GPTQ-4bit ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/60466e4b4f40b01b66151416/SC_tYXjoS3yIoOYtfqZ2E.png)

mradermacher/Meta-Llama-3-8B-hinglish-GGUF

mradermacher

"2024-06-08T00:18:28Z"

2,575

0

transformers

[ "transformers", "gguf", "en", "base_model:impuneetg/Meta-Llama-3-8B-hinglish", "endpoints_compatible", "region:us" ]

null

"2024-06-07T23:50:42Z"

--- base_model: impuneetg/Meta-Llama-3-8B-hinglish language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About      static quants of https://huggingface.co/impuneetg/Meta-Llama-3-8B-hinglish  weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-hinglish-GGUF/resolve/main/Meta-Llama-3-8B-hinglish.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

NeverSleep/Echidna-13b-v0.3

NeverSleep

"2023-11-01T03:21:25Z"

2,573

20

transformers

[ "transformers", "pytorch", "llama", "text-generation", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2023-10-27T19:58:28Z"

--- license: cc-by-nc-4.0 --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/LU1KiXFeJtt7UW_mYhwE0.png) # This model is a collab between [IkariDev](https://huggingface.co/IkariDev) and [Undi](https://huggingface.co/Undi95)! Echidna v0.3 model. Use Alpaca format. Suitable for RP, ERP and general stuff. Echidna v0.3, here it is.. its like Echidna v0.2 on steroids. This model seems to still be pretty sensitive to your generation settings, experiment until you've found your settings. [Recommended settings - No settings yet(Please suggest some over in the Community tab!)]  ## Description  This repo contains FP16 files of Echidna-13b-v0.3. [FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Echidna-13b-v0.3)   [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)   [GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Echidna-13b-v0.3-GGUF)  ## Ratings: Note: We have permission of all users to upload their ratings, i DONT screenshot random reviews without asking if i can put them here! No ratings yet! If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".   ## Models+loras used and recipe - Xwin-LM/Xwin-LM-13B-V0.2 - IkariDev/Athena-v3 - Heralax/Cat-0.5 - Undi95/PsyMedRP-v1-13B - cgato/Thespis-13b-v0.4 - KoboldAI/LLaMA2-13B-TiefighterLR - Heralax/Augmental-13b-two-epochs - Sao10K/SthenoWriter2.1-L2-13B - Undi95/Storytelling-v2.1-13B-lora - lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT   ## Prompt template: Alpaca ``` Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response: ``` ## Others Undi: If you want to support me, you can [here](https://ko-fi.com/undiai). IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek

timm/tf_efficientnetv2_m.in21k

timm

"2023-04-27T22:17:44Z"

2,572

1

timm

[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-21k", "arxiv:2104.00298", "license:apache-2.0", "region:us" ]

image-classification

"2022-12-13T00:17:55Z"

--- tags: - image-classification - timm library_name: timm license: apache-2.0 datasets: - imagenet-21k --- # Model card for tf_efficientnetv2_m.in21k A EfficientNet-v2 image classification model. Trained on ImageNet-21k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman. ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 80.8 - GMACs: 15.9 - Activations (M): 57.5 - Image size: train = 384 x 384, test = 480 x 480 - **Papers:** - EfficientNetV2: Smaller Models and Faster Training: https://arxiv.org/abs/2104.00298 - **Dataset:** ImageNet-21k - **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('tf_efficientnetv2_m.in21k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'tf_efficientnetv2_m.in21k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 24, 192, 192]) # torch.Size([1, 48, 96, 96]) # torch.Size([1, 80, 48, 48]) # torch.Size([1, 176, 24, 24]) # torch.Size([1, 512, 12, 12]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'tf_efficientnetv2_m.in21k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 1280, 12, 12) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Model Comparison Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results). ## Citation ```bibtex @inproceedings{tan2021efficientnetv2, title={Efficientnetv2: Smaller models and faster training}, author={Tan, Mingxing and Le, Quoc}, booktitle={International conference on machine learning}, pages={10096--10106}, year={2021}, organization={PMLR} } ``` ```bibtex @misc{rw2019timm, author = {Ross Wightman}, title = {PyTorch Image Models}, year = {2019}, publisher = {GitHub}, journal = {GitHub repository}, doi = {10.5281/zenodo.4414861}, howpublished = {\url{https://github.com/huggingface/pytorch-image-models}} } ```

TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF

TheBloke

"2023-09-27T12:48:18Z"

2,572

3

transformers

[ "transformers", "gguf", "llama", "dataset:jondurbin/airoboros-gpt4-1.4.1", "base_model:jondurbin/airoboros-l2-70b-gpt4-1.4.1", "license:other", "text-generation-inference", "region:us" ]

null

"2023-09-06T15:36:53Z"

--- license: other datasets: - jondurbin/airoboros-gpt4-1.4.1 model_name: Airoboros Llama 2 70B GPT4 1.4.1 base_model: jondurbin/airoboros-l2-70b-gpt4-1.4.1 inference: false model_creator: Jon Durbin model_type: llama prompt_template: 'A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user''s input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT: ' quantized_by: TheBloke ---   <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">  # Airoboros Llama 2 70B GPT4 1.4.1 - GGUF - Model creator: [Jon Durbin](https://huggingface.co/jondurbin) - Original model: [Airoboros Llama 2 70B GPT4 1.4.1](https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1)  ## Description This repo contains GGUF format model files for [Jon Durbin's Airoboros Llama 2 70B GPT4 1.4.1](https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1).   ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible. Here is an incomplate list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.   ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF) * [Jon Durbin's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1)   ## Prompt template: Airoboros ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT: ```   ## Licensing The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license. As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly. In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Jon Durbin's Airoboros Llama 2 70B GPT4 1.4.1](https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1).   ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details>   ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [airoboros-l2-70b-gpt4-1.4.1.Q2_K.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q2_K.gguf) | Q2_K | 2 | 29.28 GB| 31.78 GB | smallest, significant quality loss - not recommended for most purposes | | [airoboros-l2-70b-gpt4-1.4.1.Q3_K_S.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss | | [airoboros-l2-70b-gpt4-1.4.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q3_K_M.gguf) | Q3_K_M | 3 | 33.19 GB| 35.69 GB | very small, high quality loss | | [airoboros-l2-70b-gpt4-1.4.1.Q3_K_L.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss | | [airoboros-l2-70b-gpt4-1.4.1.Q4_0.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [airoboros-l2-70b-gpt4-1.4.1.Q4_K_S.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q4_K_S.gguf) | Q4_K_S | 4 | 39.07 GB| 41.57 GB | small, greater quality loss | | [airoboros-l2-70b-gpt4-1.4.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended | | [airoboros-l2-70b-gpt4-1.4.1.Q5_0.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [airoboros-l2-70b-gpt4-1.4.1.Q5_K_S.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended | | [airoboros-l2-70b-gpt4-1.4.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF/blob/main/airoboros-l2-70b-gpt4-1.4.1.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended | | airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss | | airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 GB | very large, extremely low quality loss - not recommended | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ### Q6_K and Q8_0 files are split and require joining **Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files. <details> <summary>Click for instructions regarding Q6_K and Q8_0 files</summary> ### q6_K Please download: * `airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-a` * `airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-b` ### q8_0 Please download: * `airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-a` * `airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-b` To join the files, do the following: Linux and macOS: ``` cat airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-* > airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf && rm airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-* cat airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-* > airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf && rm airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-* ``` Windows command line: ``` COPY /B airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-a + airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-b airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf del airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-a airoboros-l2-70b-gpt4-1.4.1.Q6_K.gguf-split-b COPY /B airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-a + airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-b airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf del airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-a airoboros-l2-70b-gpt4-1.4.1.Q8_0.gguf-split-b ``` </details>   ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: - LM Studio - LoLLMS Web UI - Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF and below it, a specific filename to download, such as: airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub>=0.17.1 ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command. </details>   ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 32 -m airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: {prompt} ASSISTANT:" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. ### How to load this model from Python using ctransformers #### First install the package ```bash # Base ctransformers with no GPU acceleration pip install ctransformers>=0.2.24 # Or with CUDA GPU acceleration pip install ctransformers[cuda]>=0.2.24 # Or with ROCm GPU acceleration CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers # Or with Metal GPU acceleration for macOS systems CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers ``` #### Simple example code to load one of these GGUF models ```python from ctransformers import AutoModelForCausalLM # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = AutoModelForCausalLM.from_pretrained("TheBloke/airoboros-l2-70B-gpt4-1.4.1-GGUF", model_file="airoboros-l2-70b-gpt4-1.4.1.q4_K_M.gguf", model_type="llama", gpu_layers=50) print(llm("AI is going to")) ``` ## How to use with LangChain Here's guides on using llama-cpp-python or ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)    ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant.   # Original model card: Jon Durbin's Airoboros Llama 2 70B GPT4 1.4.1 ### Overview Llama 2 70b fine tune using https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1 See the previous llama 65b model card for info: https://hf.co/jondurbin/airoboros-65b-gpt4-1.4 ### Contribute If you're interested in new functionality, particularly a new "instructor" type to generate a specific type of training data, take a look at the dataset generation tool repo: https://github.com/jondurbin/airoboros and either make a PR or open an issue with details. To help me with the OpenAI/compute costs: - https://bmc.link/jondurbin - ETH 0xce914eAFC2fe52FdceE59565Dd92c06f776fcb11 - BTC bc1qdwuth4vlg8x37ggntlxu5cjfwgmdy5zaa7pswf ### Licence and usage restrictions Base model has a custom Meta license: - See the [meta-license/LICENSE.txt](meta-license/LICENSE.txt) file attached for the original license provided by Meta. - See also [meta-license/USE_POLICY.md](meta-license/USE_POLICY.md) and [meta-license/Responsible-Use-Guide.pdf](meta-license/Responsible-Use-Guide.pdf), also provided by Meta. The fine-tuning data was generated by OpenAI API calls to gpt-4, via [airoboros](https://github.com/jondurbin/airoboros) The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI - what does *compete* actually mean here? - these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place - if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works - the training data used in essentially all large language models includes a significant amount of copyrighted or otherwise non-permissive licensing in the first place - other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2 I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license for llama-2) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly. Your best bet is probably to avoid using this commercially due to the OpenAI API usage. Either way, by using this model, you agree to completely indemnify me.

legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF

legraphista

"2024-05-28T15:56:35Z"

2,572

0

gguf

[ "gguf", "math", "quantized", "GGUF", "imatrix", "quantization", "imat", "static", "text-generation", "en", "zh", "base_model:internlm/internlm2-math-plus-mixtral8x22b", "license:other", "region:us" ]

text-generation

"2024-05-27T16:40:01Z"

--- base_model: internlm/internlm2-math-plus-mixtral8x22b inference: false language: - en - zh library_name: gguf license: other pipeline_tag: text-generation quantized_by: legraphista tags: - math - quantized - GGUF - imatrix - quantization - imat - imatrix - static --- # internlm2-math-plus-mixtral8x22b-IMat-GGUF _Llama.cpp imatrix quantization of internlm/internlm2-math-plus-mixtral8x22b_ Original Model: [internlm/internlm2-math-plus-mixtral8x22b](https://huggingface.co/internlm/internlm2-math-plus-mixtral8x22b) Original dtype: `BF16` (`bfloat16`) Quantized by: llama.cpp [b3010](https://github.com/ggerganov/llama.cpp/releases/tag/b3010) IMatrix dataset: [here](https://gist.githubusercontent.com/legraphista/d6d93f1a254bcfc58e0af3777eaec41e/raw/d380e7002cea4a51c33fffd47db851942754e7cc/imatrix.calibration.medium.raw) - [internlm2-math-plus-mixtral8x22b-IMat-GGUF](#internlm2-math-plus-mixtral8x22b-imat-gguf) - [Files](#files) - [IMatrix](#imatrix) - [Common Quants](#common-quants) - [All Quants](#all-quants) - [Downloading using huggingface-cli](#downloading-using-huggingface-cli) - [Inference](#inference) - [Simple chat template](#simple-chat-template) - [Chat template with system prompt](#chat-template-with-system-prompt) - [Llama.cpp](#llama-cpp) - [FAQ](#faq) - [Why is the IMatrix not applied everywhere?](#why-is-the-imatrix-not-applied-everywhere) - [How do I merge a split GGUF?](#how-do-i-merge-a-split-gguf) --- ## Files ### IMatrix Status: ✅ Available Link: [here](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/imatrix.dat) ### Common Quants | Filename | Quant type | File Size | Status | Uses IMatrix | Is Split | | -------- | ---------- | --------- | ------ | ------------ | -------- | | [internlm2-math-plus-mixtral8x22b.Q8_0/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q8_0) | Q8_0 | 149.42GB | ✅ Available | ⚪ Static | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q6_K/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q6_K) | Q6_K | 115.54GB | ✅ Available | ⚪ Static | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q4_K/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q4_K) | Q4_K | 85.59GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q3_K/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q3_K) | Q3_K | 67.80GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q2_K/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q2_K) | Q2_K | 52.11GB | ✅ Available | 🟢 IMatrix | ✂ Yes ### All Quants | Filename | Quant type | File Size | Status | Uses IMatrix | Is Split | | -------- | ---------- | --------- | ------ | ------------ | -------- | | [internlm2-math-plus-mixtral8x22b.BF16/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.BF16) | BF16 | 281.25GB | ✅ Available | ⚪ Static | ✂ Yes | [internlm2-math-plus-mixtral8x22b.FP16/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.FP16) | F16 | 281.25GB | ✅ Available | ⚪ Static | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q5_K/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q5_K) | Q5_K | 99.97GB | ✅ Available | ⚪ Static | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q5_K_S/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q5_K_S) | Q5_K_S | 96.98GB | ✅ Available | ⚪ Static | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q4_K_S/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q4_K_S) | Q4_K_S | 80.48GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q3_K_L/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q3_K_L) | Q3_K_L | 72.59GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q3_K_S/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q3_K_S) | Q3_K_S | 61.50GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.Q2_K_S/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.Q2_K_S) | Q2_K_S | 48.09GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.IQ4_NL/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ4_NL) | IQ4_NL | 79.78GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.IQ4_XS/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ4_XS) | IQ4_XS | 75.48GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.IQ3_M/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ3_M) | IQ3_M | 64.50GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.IQ3_S/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ3_S) | IQ3_S | 61.50GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.IQ3_XS/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ3_XS) | IQ3_XS | 58.23GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.IQ3_XXS/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ3_XXS) | IQ3_XXS | 54.91GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.IQ2_M/*](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/tree/main/internlm2-math-plus-mixtral8x22b.IQ2_M) | IQ2_M | 46.71GB | ✅ Available | 🟢 IMatrix | ✂ Yes | [internlm2-math-plus-mixtral8x22b.IQ2_S.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ2_S.gguf) | IQ2_S | 42.60GB | ✅ Available | 🟢 IMatrix | 📦 No | [internlm2-math-plus-mixtral8x22b.IQ2_XS.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ2_XS.gguf) | IQ2_XS | 42.00GB | ✅ Available | 🟢 IMatrix | 📦 No | [internlm2-math-plus-mixtral8x22b.IQ2_XXS.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ2_XXS.gguf) | IQ2_XXS | 37.89GB | ✅ Available | 🟢 IMatrix | 📦 No | [internlm2-math-plus-mixtral8x22b.IQ1_M.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ1_M.gguf) | IQ1_M | 32.74GB | ✅ Available | 🟢 IMatrix | 📦 No | [internlm2-math-plus-mixtral8x22b.IQ1_S.gguf](https://huggingface.co/legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF/blob/main/internlm2-math-plus-mixtral8x22b.IQ1_S.gguf) | IQ1_S | 29.65GB | ✅ Available | 🟢 IMatrix | 📦 No ## Downloading using huggingface-cli If you do not have hugginface-cli installed: ``` pip install -U "huggingface_hub[cli]" ``` Download the specific file you want: ``` huggingface-cli download legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF --include "internlm2-math-plus-mixtral8x22b.Q8_0.gguf" --local-dir ./ ``` If the model file is big, it has been split into multiple files. In order to download them all to a local folder, run: ``` huggingface-cli download legraphista/internlm2-math-plus-mixtral8x22b-IMat-GGUF --include "internlm2-math-plus-mixtral8x22b.Q8_0/*" --local-dir internlm2-math-plus-mixtral8x22b.Q8_0 # see FAQ for merging GGUF's ``` --- ## Inference ### Simple chat template ``` <s>[INST] Can you provide ways to eat combinations of bananas and dragonfruits? [/INST] Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey. </s><s>[INST] What about solving an 2x + 3 = 7 equation? [/INST] ``` ### Chat template with system prompt ``` <s>[INST] <<SYS>> You are a helpful AI. <</SYS>> Can you provide ways to eat combinations of bananas and dragonfruits? [/INST] Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey. </s><s>[INST] What about solving an 2x + 3 = 7 equation? [/INST] ``` ### Llama.cpp ``` llama.cpp/main -m internlm2-math-plus-mixtral8x22b.Q8_0.gguf --color -i -p "prompt here (according to the chat template)" ``` --- ## FAQ ### Why is the IMatrix not applied everywhere? According to [this investigation](https://www.reddit.com/r/LocalLLaMA/comments/1993iro/ggufs_quants_can_punch_above_their_weights_now/), it appears that lower quantizations are the only ones that benefit from the imatrix input (as per hellaswag results). ### How do I merge a split GGUF? 1. Make sure you have `gguf-split` available - To get hold of `gguf-split`, navigate to https://github.com/ggerganov/llama.cpp/releases - Download the appropriate zip for your system from the latest release - Unzip the archive and you should be able to find `gguf-split` 2. Locate your GGUF chunks folder (ex: `internlm2-math-plus-mixtral8x22b.Q8_0`) 3. Run `gguf-split --merge internlm2-math-plus-mixtral8x22b.Q8_0/internlm2-math-plus-mixtral8x22b.Q8_0-00001-of-XXXXX.gguf internlm2-math-plus-mixtral8x22b.Q8_0.gguf` - Make sure to point `gguf-split` to the first chunk of the split. --- Got a suggestion? Ping me [@legraphista](https://x.com/legraphista)!

levimorin/5GvNMz73qNSQjFb9r4XPWbD747QH5jUAdRcxTfB1NwCJKN6m_vgg

levimorin

"2024-03-08T19:10:04Z"

2,570

0

keras

[ "keras", "region:us" ]

null

"2024-03-03T04:59:55Z"

Entry not found

jphme/phi-1_5_Wizard_Vicuna_uncensored

jphme

"2023-09-21T12:23:23Z"

2,569

26

transformers

[ "transformers", "pytorch", "mixformer-sequential", "text-generation", "phi", "phi-1_5", "english", "custom_code", "en", "dataset:ehartford/wizard_vicuna_70k_unfiltered", "autotrain_compatible", "region:us" ]

text-generation

"2023-09-12T17:30:57Z"

--- language: - en library_name: transformers pipeline_tag: text-generation inference: true tags: - pytorch - phi - phi-1_5 - english datasets: - ehartford/wizard_vicuna_70k_unfiltered --- # Phi 1.5 Wizard Vicuna Experimental Experimental Finetune on Microsoft's [Phi 1.5](https://huggingface.co/microsoft/phi-1_5). This is highly experimental, only trained on a subset of the 70k Wizard Vicuna dataset and not meant for production use. This model also runs reasonably fast on CPU! Will update with later checkpoints later. # Prompt Format ShareGPT / Vicuna (without newlines): ``` A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: This is a question? ASSISTANT: Here is my answer" ``` # Code Example ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("jphme/phi-1_5_wizzard_vicuna_uncensored", trust_remote_code=True, torch_dtype=torch.bfloat16).to("cuda") tokenizer = AutoTokenizer.from_pretrained("jphme/phi-1_5_wizzard_vicuna_uncensored", trust_remote_code=True, torch_dtype=torch.bfloat16) prompt_template=("A chat between a curious user and an artificial intelligence assistant. " "The assistant gives helpful, detailed, and polite answers to the user's questions. " "USER: {prompt} ASSISTANT:") inputs = tokenizer( prompt_template.format(prompt="What is 1+1?"), return_tensors="pt", return_attention_mask=False).to('cuda') outputs = model.generate( **inputs, max_length=200, do_sample=True, temperature=0.5, top_p=0.95, use_cache=True, repetition_penalty=1.1, #can try to uncomment this if model doesn't end #eos_token_id=tokenizer.eos_token_id ) text = tokenizer.batch_decode(outputs,skip_special_tokens=True)[0] print(text) ``` The model doesn't stop by itself (this could be an issue due to eos/bos tokens being identical), so you can try to explicitly set the `eos_token_id` (see above) or use a custom stopping criteria. You can remove `.to("cuda")` to let the model run without a GPU! # Examples > A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Who was president of the USA in 1995? ASSISTANT: The president of the United States at that time was Bill Clinton (...) > A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Write a python function that returns the fibonacci sequence ASSISTANT:The Fibonacci sequence is a series of numbers where each number after the first two are obtained by adding the two preceding ones together (starting from 0). So the sequence goes 0, 1, 1, 2, 3, 5, 8, 13, 21... Here's a Python function that generates the nth term in the Fibonacci sequence: ```python def fibonacci(n): if n <= 1: return n else: f = [0,1] for i in range(2, n+1): f.append(f[-1]+f[-2]) return f[-1] ``` > This function takes as input `n`, which represents the (...) (this function works with corrected intendation) > A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: What is (500+12)/4? ASSISTANT:The answer to this expression is 7.5. (...) Some potential here ;-)... # Thanks Thanks to Microsoft for releaseing Phi 1.5, [Eric Hartford](https://huggingface.co/ehartford) for releasing the Wizard Vicuna dataset, [Winglian](https://huggingface.co/winglian) for his great work on Axolotl that I use for finetuning and [Teknium](https://huggingface.co/teknium) for some Phi finetuning discussion. # License The original licenses of the dataset and model applies. No warranty whatsoever, this model is only intended for research purposes.

mohitsha/tiny-ernie-random-remote-code

mohitsha

"2023-09-01T09:56:12Z"

2,568

0

transformers

[ "transformers", "pytorch", "ernie", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text-generation

"2023-09-01T09:55:21Z"

Entry not found

mradermacher/Average_Normie_v3.69_8B-GGUF

mradermacher

"2024-06-09T03:21:10Z"

2,568

0

transformers

[ "transformers", "gguf", "en", "base_model:jeiku/Average_Normie_v3.69_8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

"2024-06-08T23:28:36Z"

--- base_model: jeiku/Average_Normie_v3.69_8B language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher --- ## About      static quants of https://huggingface.co/jeiku/Average_Normie_v3.69_8B  weighted/imatrix quants are available at https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Average_Normie_v3.69_8B-GGUF/resolve/main/Average_Normie_v3.69_8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

asi/gpt-fr-cased-base

asi

"2022-10-20T18:32:14Z"

2,565

27

transformers

[ "transformers", "pytorch", "tf", "jax", "gpt2", "text-generation", "fr", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2022-03-02T23:29:05Z"

--- language: - fr thumbnail: https://raw.githubusercontent.com/AntoineSimoulin/gpt-fr/main/imgs/logo.png tags: - tf - pytorch - gpt2 - text-generation model-index: - name: asi/gpt-fr-cased-base results: - task: type: text-generation name: Wikitext-fr dataset: type: wikitext_fr name: Wikitext-fr metrics: - type: perplexity value: 12.9 name: Perplexity - task: type: text-classification name: FLUE dataset: type: flue name: CLS-Books split: CLS metrics: - type: accuracy value: 91.6 name: Accuracy - task: type: text-classification name: FLUE dataset: type: flue name: CLS-Dvd split: CLS metrics: - type: accuracy value: 91.4 name: Accuracy - task: type: text-classification name: FLUE dataset: type: flue name: CLS-Music split: CLS metrics: - type: accuracy value: 92.6 name: Accuracy - task: type: text-classification name: FLUE dataset: type: flue name: PAWS-X split: PAWS-X metrics: - type: accuracy value: 86.3 name: Accuracy - task: type: text-classification name: FLUE dataset: type: flue name: XNLI split: XNLI metrics: - type: accuracy value: 77.9 name: Accuracy - task: type: summarization name: OrangeSum dataset: type: orange_sum name: OrangeSum-Abstract split: abstract metrics: - name: ROUGE-1 type: rouge value: 16.6 - name: ROUGE-2 type: rouge value: 3.4 - name: ROUGE-L type: rouge value: 11.5 - task: type: summarization name: OrangeSum dataset: type: orange_sum name: OrangeSum-Title split: title metrics: - name: ROUGE-1 type: rouge value: 10.2 - name: ROUGE-2 type: rouge value: 2.6 - name: ROUGE-L type: rouge value: 8.4 license: apache-2.0 --- <img src="https://raw.githubusercontent.com/AntoineSimoulin/gpt-fr/main/imgs/logo.png" width="200"> ## Model description **GPT-fr** 🇫🇷 is a GPT model for French developped by [Quantmetry](https://www.quantmetry.com/) and the [Laboratoire de Linguistique Formelle (LLF)](http://www.llf.cnrs.fr/en). We train the model on a very large and heterogeneous French corpus. We release the weights for the following configurations: | Model name | Number of layers | Attention Heads | Embedding Dimension | Total Parameters | | :------: | :---: | :---: | :---: | :---: | | `gpt-fr-cased-small` | 12 | 12 | 768 | 124 M | | `gpt-fr-cased-base` | 24 | 14 | 1,792 | 1,017 B | ## Intended uses & limitations The model can be leveraged for language generation tasks. Besides, many tasks may be formatted such that the output is directly generated in natural language. Such configuration may be used for tasks such as automatic summary or question answering. We do hope our model might be used for both academic and industrial applications. #### How to use The model might be used through the astonishing 🤗 `Transformers` librairie. We use the work from [Shoeybi et al., (2019)](#shoeybi-2019) and calibrate our model such that during pre-training or fine-tuning, the model can fit on a single NVIDIA V100 32GB GPU. ```python from transformers import GPT2Tokenizer, GPT2LMHeadModel # Load pretrained model and tokenizer model = GPT2LMHeadModel.from_pretrained("asi/gpt-fr-cased-base") tokenizer = GPT2Tokenizer.from_pretrained("asi/gpt-fr-cased-base") # Generate a sample of text model.eval() input_sentence = "Longtemps je me suis couché de bonne heure." input_ids = tokenizer.encode(input_sentence, return_tensors='pt') beam_outputs = model.generate( input_ids, max_length=100, do_sample=True, top_k=50, top_p=0.95, num_return_sequences=1 ) print("Output:\n" + 100 * '-') print(tokenizer.decode(beam_outputs[0], skip_special_tokens=True)) ``` #### Limitations and bias Large language models tend to replicate the biases found in pre-training datasets, such as gender discrimination or offensive content generation. To limit exposition to too much explicit material, we carefully choose the sources beforehand. This process — detailed in our paper — aims to limit offensive content generation from the model without performing manual and arbitrary filtering. However, some societal biases, contained in the data, might be reflected by the model. For example on gender equality, we generated the following sentence sequence "Ma femme/Mon mari vient d'obtenir un nouveau poste en tant \_\_\_\_\_\_\_". We used top-k random sampling strategy with k=50 and stopped at the first punctuation element. The positions generated for the wife is '_que professeur de français._' while the position for the husband is '_que chef de projet._'. We do appreciate your feedback to better qualitatively and quantitatively assess such effects. ## Training data We created a dedicated corpus to train our generative model. Indeed the model uses a fixed-length context size of 1,024 and require long documents to be trained. We aggregated existing corpora: [Wikipedia](https://dumps.wikimedia.org/frwiki/), [OpenSubtitle](http://opus.nlpl.eu/download.php?f=OpenSubtitles/v2016/mono/) ([Tiedemann, 2012](#tiedemann-2012)), [Gutenberg](http://www.gutenberg.org) and [Common Crawl](http://data.statmt.org/ngrams/deduped2017/) ([Li et al., 2019](li-2019)). Corpora are filtered and separated into sentences. Successive sentences are then concatenated within the limit of 1,024 tokens per document. ## Training procedure We pre-trained the model on the new CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/eng/jean-zay/) supercomputer. We perform the training within a total of 140 hours of computation on Tesla V-100 hardware (TDP of 300W). The training was distributed on 4 compute nodes of 8 GPUs. We used data parallelization in order to divide each micro-batch on the computing units. We estimated the total emissions at 580.61 kgCO2eq, using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al., (2019)](lacoste-2019). ## Eval results We packaged **GPT-fr** with a dedicated language model evaluation benchmark for French. In line with the [WikiText](https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/) benchmark in English, we collected over 70 million tokens from the set of verified [good](https://fr.wikipedia.org/wiki/Wikip%C3%A9dia:Articles_de_qualit%C3%A9) and [featured](https://fr.wikipedia.org/wiki/Wikip%C3%A9dia:Bons_articles) articles on Wikipedia. The model reaches a zero-shot perplexity of **12.9** on the test set. ### BibTeX entry and citation info Along with the model hosted by HuggingFace transformers library, we maintain a [git repository](https://github.com/AntoineSimoulin/gpt-fr). If you use **GPT-fr** for your scientific publications or your industrial applications, please cite the following paper: ```bibtex @inproceedings{simoulin:hal-03265900, TITLE = {{Un mod{\`e}le Transformer G{\'e}n{\'e}ratif Pr{\'e}-entrain{\'e} pour le \_\_\_\_\_\_ fran{\c c}ais}}, AUTHOR = {Simoulin, Antoine and Crabb{\'e}, Benoit}, URL = {https://hal.archives-ouvertes.fr/hal-03265900}, BOOKTITLE = {{Traitement Automatique des Langues Naturelles}}, ADDRESS = {Lille, France}, EDITOR = {Denis, Pascal and Grabar, Natalia and Fraisse, Amel and Cardon, R{\'e}mi and Jacquemin, Bernard and Kergosien, Eric and Balvet, Antonio}, PUBLISHER = {{ATALA}}, PAGES = {246-255}, YEAR = {2021}, KEYWORDS = {fran{\c c}ais. ; GPT ; G{\'e}n{\'e}ratif ; Transformer ; Pr{\'e}-entra{\^i}n{\'e}}, PDF = {https://hal.archives-ouvertes.fr/hal-03265900/file/7.pdf}, HAL_ID = {hal-03265900}, HAL_VERSION = {v1}, } ``` ### References ><div name="tiedemann-2012">Jörg Tiedemann: Parallel Data, Tools and Interfaces in OPUS. LREC 2012: 2214-2218</div> ><div name="li-2019">Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Pino, Hassan Sajjad: Findings of the First Shared Task on Machine Translation Robustness. WMT (2) 2019: 91-102</div> ><div name="shoeybi-2019">Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, Bryan Catanzaro: Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. CoRR abs/1909.08053 (2019)</div> ><div name="lacoste-2019">Alexandre Lacoste, Alexandra Luccioni, Victor Schmidt, Thomas Dandres: Quantifying the Carbon Emissions of Machine Learning. CoRR abs/1910.09700 (2019)</div>

iFlor/llama-3-8b-Instruct-bnb-4bit-flori-demo

iFlor

"2024-06-30T16:27:15Z"

2,565

0

transformers

[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

"2024-06-30T16:16:34Z"

--- base_model: unsloth/llama-3-8b-Instruct-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - gguf --- # Uploaded model - **Developed by:** iFlor - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf

RichardErkhov

"2024-06-16T07:09:57Z"

2,561

0

null

[ "gguf", "region:us" ]

null

"2024-06-16T03:20:12Z"

Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) NeuralLLaMa-3-8b-ORPO-v0.3 - GGUF - Model creator: https://huggingface.co/Kukedlc/ - Original model: https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3/ | Name | Quant method | Size | | ---- | ---- | ---- | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q2_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q2_K.gguf) | Q2_K | 2.96GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_XS.gguf) | IQ3_XS | 3.28GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_S.gguf) | IQ3_S | 3.43GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_S.gguf) | Q3_K_S | 3.41GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ3_M.gguf) | IQ3_M | 3.52GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K.gguf) | Q3_K | 3.74GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_M.gguf) | Q3_K_M | 3.74GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q3_K_L.gguf) | Q3_K_L | 4.03GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ4_XS.gguf) | IQ4_XS | 4.18GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_0.gguf) | Q4_0 | 4.34GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.IQ4_NL.gguf) | IQ4_NL | 4.38GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K_S.gguf) | Q4_K_S | 4.37GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K.gguf) | Q4_K | 4.58GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_K_M.gguf) | Q4_K_M | 4.58GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q4_1.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q4_1.gguf) | Q4_1 | 4.78GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_0.gguf) | Q5_0 | 5.21GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K_S.gguf) | Q5_K_S | 5.21GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K.gguf) | Q5_K | 5.34GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_K_M.gguf) | Q5_K_M | 5.34GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q5_1.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q5_1.gguf) | Q5_1 | 5.65GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q6_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q6_K.gguf) | Q6_K | 6.14GB | | [NeuralLLaMa-3-8b-ORPO-v0.3.Q8_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-ORPO-v0.3-gguf/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3.Q8_0.gguf) | Q8_0 | 7.95GB | Original model description: --- license: apache-2.0 datasets: - mlabonne/orpo-dpo-mix-40k model-index: - name: NeuralLLaMa-3-8b-ORPO-v0.3 results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 69.54 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 84.9 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 68.39 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 60.82 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 79.4 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 72.93 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 name: Open LLM Leaderboard --- # NeuralLLaMa-3-8b-ORPO-v0.3 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/JyQNE7gAAyYTxKMO2PraO.png) ```python !pip install -qU transformers accelerate bitsandbytes from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig import torch bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16 ) MODEL_NAME = 'Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3' tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config) prompt_system = "Sos un modelo de lenguaje de avanzada que habla español de manera fluida, clara y precisa.\ Te llamas Roberto el Robot y sos un aspirante a artista post moderno" prompt = "Creame una obra de arte que represente tu imagen de como te ves vos roberto como un LLm de avanzada, con arte ascii, mezcla diagramas, ingenieria y dejate llevar" chat = [ {"role": "system", "content": f"{prompt_system}"}, {"role": "user", "content": f"{prompt}"}, ] chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) inputs = tokenizer(chat, return_tensors="pt").to('cuda') streamer = TextStreamer(tokenizer) _ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.3, repetition_penalty=1.2, top_p=0.9,) ``` # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Kukedlc__NeuralLLaMa-3-8b-ORPO-v0.3) | Metric |Value| |---------------------------------|----:| |Avg. |72.66| |AI2 Reasoning Challenge (25-Shot)|69.54| |HellaSwag (10-Shot) |84.90| |MMLU (5-Shot) |68.39| |TruthfulQA (0-shot) |60.82| |Winogrande (5-shot) |79.40| |GSM8k (5-shot) |72.93|

albert/albert-xlarge-v1

albert

"2024-02-19T11:01:28Z"

2,560

4

transformers

[ "transformers", "pytorch", "tf", "safetensors", "albert", "fill-mask", "en", "dataset:bookcorpus", "dataset:wikipedia", "arxiv:1909.11942", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

fill-mask

"2022-03-02T23:29:04Z"

--- language: en license: apache-2.0 datasets: - bookcorpus - wikipedia --- # ALBERT XLarge v1 Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in [this paper](https://arxiv.org/abs/1909.11942) and first released in [this repository](https://github.com/google-research/albert). This model, as all ALBERT models, is uncased: it does not make a difference between english and English. Disclaimer: The team releasing ALBERT did not write a model card for this model so this model card has been written by the Hugging Face team. ## Model description ALBERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was pretrained with two objectives: - Masked language modeling (MLM): taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence. - Sentence Ordering Prediction (SOP): ALBERT uses a pretraining loss based on predicting the ordering of two consecutive segments of text. This way, the model learns an inner representation of the English language that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the ALBERT model as inputs. ALBERT is particular in that it shares its layers across its Transformer. Therefore, all layers have the same weights. Using repeating layers results in a small memory footprint, however, the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers. This is the first version of the xlarge model. Version 2 is different from version 1 due to different dropout rates, additional training data, and longer training. It has better results in nearly all downstream tasks. This model has the following configuration: - 24 repeating layers - 128 embedding dimension - 2048 hidden dimension - 16 attention heads - 58M parameters ## Intended uses & limitations You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?filter=albert) to look for fine-tuned versions on a task that interests you. Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation you should look at model like GPT2. ### How to use You can use this model directly with a pipeline for masked language modeling: ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='albert-xlarge-v1') >>> unmasker("Hello I'm a [MASK] model.") [ { "sequence":"[CLS] hello i'm a modeling model.[SEP]", "score":0.05816134437918663, "token":12807, "token_str":"â–modeling" }, { "sequence":"[CLS] hello i'm a modelling model.[SEP]", "score":0.03748830780386925, "token":23089, "token_str":"â–modelling" }, { "sequence":"[CLS] hello i'm a model model.[SEP]", "score":0.033725276589393616, "token":1061, "token_str":"â–model" }, { "sequence":"[CLS] hello i'm a runway model.[SEP]", "score":0.017313428223133087, "token":8014, "token_str":"â–runway" }, { "sequence":"[CLS] hello i'm a lingerie model.[SEP]", "score":0.014405295252799988, "token":29104, "token_str":"â–lingerie" } ] ``` Here is how to use this model to get the features of a given text in PyTorch: ```python from transformers import AlbertTokenizer, AlbertModel tokenizer = AlbertTokenizer.from_pretrained('albert-xlarge-v1') model = AlbertModel.from_pretrained("albert-xlarge-v1") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='pt') output = model(**encoded_input) ``` and in TensorFlow: ```python from transformers import AlbertTokenizer, TFAlbertModel tokenizer = AlbertTokenizer.from_pretrained('albert-xlarge-v1') model = TFAlbertModel.from_pretrained("albert-xlarge-v1") text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='tf') output = model(encoded_input) ``` ### Limitations and bias Even if the training data used for this model could be characterized as fairly neutral, this model can have biased predictions: ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='albert-xlarge-v1') >>> unmasker("The man worked as a [MASK].") [ { "sequence":"[CLS] the man worked as a chauffeur.[SEP]", "score":0.029577180743217468, "token":28744, "token_str":"â–chauffeur" }, { "sequence":"[CLS] the man worked as a janitor.[SEP]", "score":0.028865724802017212, "token":29477, "token_str":"â–janitor" }, { "sequence":"[CLS] the man worked as a shoemaker.[SEP]", "score":0.02581118606030941, "token":29024, "token_str":"â–shoemaker" }, { "sequence":"[CLS] the man worked as a blacksmith.[SEP]", "score":0.01849772222340107, "token":21238, "token_str":"â–blacksmith" }, { "sequence":"[CLS] the man worked as a lawyer.[SEP]", "score":0.01820771023631096, "token":3672, "token_str":"â–lawyer" } ] >>> unmasker("The woman worked as a [MASK].") [ { "sequence":"[CLS] the woman worked as a receptionist.[SEP]", "score":0.04604868218302727, "token":25331, "token_str":"â–receptionist" }, { "sequence":"[CLS] the woman worked as a janitor.[SEP]", "score":0.028220869600772858, "token":29477, "token_str":"â–janitor" }, { "sequence":"[CLS] the woman worked as a paramedic.[SEP]", "score":0.0261906236410141, "token":23386, "token_str":"â–paramedic" }, { "sequence":"[CLS] the woman worked as a chauffeur.[SEP]", "score":0.024797942489385605, "token":28744, "token_str":"â–chauffeur" }, { "sequence":"[CLS] the woman worked as a waitress.[SEP]", "score":0.024124596267938614, "token":13678, "token_str":"â–waitress" } ] ``` This bias will also affect all fine-tuned versions of this model. ## Training data The ALBERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038 unpublished books and [English Wikipedia](https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and headers). ## Training procedure ### Preprocessing The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 30,000. The inputs of the model are then of the form: ``` [CLS] Sentence A [SEP] Sentence B [SEP] ``` ### Training The ALBERT procedure follows the BERT setup. The details of the masking procedure for each sentence are the following: - 15% of the tokens are masked. - In 80% of the cases, the masked tokens are replaced by `[MASK]`. - In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace. - In the 10% remaining cases, the masked tokens are left as is. ## Evaluation results When fine-tuned on downstream tasks, the ALBERT models achieve the following results: | | Average | SQuAD1.1 | SQuAD2.0 | MNLI | SST-2 | RACE | |----------------|----------|----------|----------|----------|----------|----------| |V2 | |ALBERT-base |82.3 |90.2/83.2 |82.1/79.3 |84.6 |92.9 |66.8 | |ALBERT-large |85.7 |91.8/85.2 |84.9/81.8 |86.5 |94.9 |75.2 | |ALBERT-xlarge |87.9 |92.9/86.4 |87.9/84.1 |87.9 |95.4 |80.7 | |ALBERT-xxlarge |90.9 |94.6/89.1 |89.8/86.9 |90.6 |96.8 |86.8 | |V1 | |ALBERT-base |80.1 |89.3/82.3 | 80.0/77.1|81.6 |90.3 | 64.0 | |ALBERT-large |82.4 |90.6/83.9 | 82.3/79.4|83.5 |91.7 | 68.5 | |ALBERT-xlarge |85.5 |92.5/86.1 | 86.1/83.1|86.4 |92.4 | 74.8 | |ALBERT-xxlarge |91.0 |94.8/89.3 | 90.2/87.4|90.8 |96.9 | 86.5 | ### BibTeX entry and citation info ```bibtex @article{DBLP:journals/corr/abs-1909-11942, author = {Zhenzhong Lan and Mingda Chen and Sebastian Goodman and Kevin Gimpel and Piyush Sharma and Radu Soricut}, title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language Representations}, journal = {CoRR}, volume = {abs/1909.11942}, year = {2019}, url = {http://arxiv.org/abs/1909.11942}, archivePrefix = {arXiv}, eprint = {1909.11942}, timestamp = {Fri, 27 Sep 2019 13:04:21 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1909-11942.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } ```

Narrativa/mbart-large-50-finetuned-opus-pt-en-translation

Narrativa

"2021-06-21T11:16:19Z"

2,560

5

transformers

[ "transformers", "pytorch", "mbart", "text2text-generation", "translation", "pt", "en", "dataset:opus100", "dataset:opusbook", "arxiv:2008.00401", "arxiv:2004.11867", "autotrain_compatible", "endpoints_compatible", "region:us" ]

translation

"2022-03-02T23:29:04Z"

--- language: - pt - en datasets: - opus100 - opusbook tags: - translation metrics: - bleu --- # mBART-large-50 fine-tuned onpus100 and opusbook for Portuguese to English translation. [mBART-50](https://huggingface.co/facebook/mbart-large-50/) large fine-tuned on [opus100](https://huggingface.co/datasets/viewer/?dataset=opus100) dataset for **NMT** downstream task. # Details of mBART-50 🧠 mBART-50 is a multilingual Sequence-to-Sequence model pre-trained using the "Multilingual Denoising Pretraining" objective. It was introduced in [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) paper. mBART-50 is a multilingual Sequence-to-Sequence model. It was created to show that multilingual translation models can be created through multilingual fine-tuning. Instead of fine-tuning on one direction, a pre-trained model is fine-tuned many directions simultaneously. mBART-50 is created using the original mBART model and extended to add extra 25 languages to support multilingual machine translation models of 50 languages. The pre-training objective is explained below. **Multilingual Denoising Pretraining**: The model incorporates N languages by concatenating data: `D = {D1, ..., DN }` where each Di is a collection of monolingual documents in language `i`. The source documents are noised using two schemes, first randomly shuffling the original sentences' order, and second a novel in-filling scheme, where spans of text are replaced with a single mask token. The model is then tasked to reconstruct the original text. 35% of each instance's words are masked by random sampling a span length according to a Poisson distribution `(λ = 3.5)`. The decoder input is the original text with one position offset. A language id symbol `LID` is used as the initial token to predict the sentence. ## Details of the downstream task (NMT) - Dataset 📚 - **Homepage:** [Link](http://opus.nlpl.eu/opus-100.php) - **Repository:** [GitHub](https://github.com/EdinburghNLP/opus-100-corpus) - **Paper:** [ARXIV](https://arxiv.org/abs/2004.11867) ### Dataset Summary OPUS-100 is English-centric, meaning that all training pairs include English on either the source or target side. The corpus covers 100 languages (including English). Languages were selected based on the volume of parallel data available in OPUS. ### Languages OPUS-100 contains approximately 55M sentence pairs. Of the 99 language pairs, 44 have 1M sentence pairs of training data, 73 have at least 100k, and 95 have at least 10k. ## Dataset Structure ### Data Fields - `src_tag`: `string` text in source language - `tgt_tag`: `string` translation of source language in target language ### Data Splits The dataset is split into training, development, and test portions. Data was prepared by randomly sampled up to 1M sentence pairs per language pair for training and up to 2000 each for development and test. To ensure that there was no overlap (at the monolingual sentence level) between the training and development/test data, they applied a filter during sampling to exclude sentences that had already been sampled. Note that this was done cross-lingually so that, for instance, an English sentence in the Portuguese-English portion of the training data could not occur in the Hindi-English test set. ## Test set metrics 🧾 We got a **BLEU score of 26.12** ## Model in Action 🚀 ```sh git clone https://github.com/huggingface/transformers.git pip install -q ./transformers ``` ```python from transformers import MBart50TokenizerFast, MBartForConditionalGeneration ckpt = 'Narrativa/mbart-large-50-finetuned-opus-pt-en-translation' tokenizer = MBart50TokenizerFast.from_pretrained(ckpt) model = MBartForConditionalGeneration.from_pretrained(ckpt).to("cuda") tokenizer.src_lang = 'pt_XX' def translate(text): inputs = tokenizer(text, return_tensors='pt') input_ids = inputs.input_ids.to('cuda') attention_mask = inputs.attention_mask.to('cuda') output = model.generate(input_ids, attention_mask=attention_mask, forced_bos_token_id=tokenizer.lang_code_to_id['en_XX']) return tokenizer.decode(output[0], skip_special_tokens=True) translate('here your Portuguese text to be translated to English...') ``` Created by: [Narrativa](https://www.narrativa.com/) About Narrativa: Natural Language Generation (NLG) | Gabriele, our machine learning-based platform, builds and deploys natural language solutions. #NLG #AI

google/ddpm-cat-256

google

"2023-08-03T19:46:57Z"

2,560

7

diffusers

[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "arxiv:2006.11239", "license:apache-2.0", "diffusers:DDPMPipeline", "region:us" ]

unconditional-image-generation

"2022-07-19T10:42:07Z"

--- license: apache-2.0 tags: - pytorch - diffusers - unconditional-image-generation --- # Denoising Diffusion Probabilistic Models (DDPM) **Paper**: [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) **Authors**: Jonathan Ho, Ajay Jain, Pieter Abbeel **Abstract**: *We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN.* ## Inference **DDPM** models can use *discrete noise schedulers* such as: - [scheduling_ddpm](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddpm.py) - [scheduling_ddim](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddim.py) - [scheduling_pndm](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_pndm.py) for inference. Note that while the *ddpm* scheduler yields the highest quality, it also takes the longest. For a good trade-off between quality and inference speed you might want to consider the *ddim* or *pndm* schedulers instead. See the following code: ```python # !pip install diffusers from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline model_id = "google/ddpm-cat-256" # load model and scheduler ddpm = DDPMPipeline.from_pretrained(model_id) # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference # run pipeline in inference (sample random noise and denoise) image = ddpm().images[0] # save image image.save("ddpm_generated_image.png") ``` For more in-detail information, please have a look at the [official inference example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb) ## Training If you want to train your own model, please have a look at the [official training example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb) ## Samples 1. ![sample_1](https://huggingface.co/google/ddpm-cat-256/resolve/main/images/generated_image_0.png) 2. ![sample_2](https://huggingface.co/google/ddpm-cat-256/resolve/main/images/generated_image_1.png) 3. ![sample_3](https://huggingface.co/google/ddpm-cat-256/resolve/main/images/generated_image_2.png) 4. ![sample_4](https://huggingface.co/google/ddpm-cat-256/resolve/main/images/generated_image_3.png)

google/switch-base-16

google

"2023-01-24T17:19:53Z"

2,560

3

transformers

[ "transformers", "pytorch", "switch_transformers", "text2text-generation", "en", "dataset:c4", "arxiv:2101.03961", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

text2text-generation

"2022-11-04T07:58:37Z"

--- language: - en tags: - text2text-generation widget: - text: "The <extra_id_0> walks in <extra_id_1> park" example_title: "Masked Language Modeling" datasets: - c4 license: apache-2.0 --- # Model Card for Switch Transformers Base - 16 experts ![model image](https://s3.amazonaws.com/moonup/production/uploads/1666966931908-62441d1d9fdefb55a0b7d12c.png) # Table of Contents 0. [TL;DR](#TL;DR) 1. [Model Details](#model-details) 2. [Usage](#usage) 3. [Uses](#uses) 4. [Bias, Risks, and Limitations](#bias-risks-and-limitations) 5. [Training Details](#training-details) 6. [Evaluation](#evaluation) 7. [Environmental Impact](#environmental-impact) 8. [Citation](#citation) 9. [Model Card Authors](#model-card-authors) # TL;DR Switch Transformers is a Mixture of Experts (MoE) model trained on Masked Language Modeling (MLM) task. The model architecture is similar to the classic T5, but with the Feed Forward layers replaced by the Sparse MLP layers containing "experts" MLP. According to the [original paper](https://arxiv.org/pdf/2101.03961.pdf) the model enables faster training (scaling properties) while being better than T5 on fine-tuned tasks. As mentioned in the first few lines of the abstract : > we advance the current scale of language models by pre-training up to trillion parameter models on the “Colossal Clean Crawled Corpus”, and achieve a 4x speedup over the T5-XXL model. **Disclaimer**: Content from **this** model card has been written by the Hugging Face team, and parts of it were copy pasted from the [original paper](https://arxiv.org/pdf/2101.03961.pdf). # Model Details ## Model Description - **Model type:** Language model - **Language(s) (NLP):** English - **License:** Apache 2.0 - **Related Models:** [All Switch Transformers Checkpoints](https://huggingface.co/models?search=switch) - **Original Checkpoints:** [All Original Switch Transformers Checkpoints](https://github.com/google-research/t5x/blob/main/docs/models.md#mixture-of-experts-moe-checkpoints) - **Resources for more information:** - [Research paper](https://arxiv.org/pdf/2101.03961.pdf) - [GitHub Repo](https://github.com/google-research/t5x) - [Hugging Face Switch Transformers Docs (Similar to T5) ](https://huggingface.co/docs/transformers/model_doc/switch_transformers) # Usage Note that these checkpoints has been trained on Masked-Language Modeling (MLM) task. Therefore the checkpoints are not "ready-to-use" for downstream tasks. You may want to check `FLAN-T5` for running fine-tuned weights or fine-tune your own MoE following [this notebook](https://colab.research.google.com/drive/1aGGVHZmtKmcNBbAwa9hbu58DDpIuB5O4?usp=sharing) Find below some example scripts on how to use the model in `transformers`: ## Using the Pytorch model ### Running the model on a CPU <details> <summary> Click to expand </summary> ```python from transformers import AutoTokenizer, SwitchTransformersForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained("google/switch-base-16") model = SwitchTransformersForConditionalGeneration.from_pretrained("google/switch-base-16") input_text = "A <extra_id_0> walks into a bar a orders a <extra_id_1> with <extra_id_2> pinch of <extra_id_3>." input_ids = tokenizer(input_text, return_tensors="pt").input_ids outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) >>> <pad> <extra_id_0> man<extra_id_1> beer<extra_id_2> a<extra_id_3> salt<extra_id_4>.</s> ``` </details> ### Running the model on a GPU <details> <summary> Click to expand </summary> ```python # pip install accelerate from transformers import AutoTokenizer, SwitchTransformersForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained("google/switch-base-16") model = SwitchTransformersForConditionalGeneration.from_pretrained("google/switch-base-16", device_map="auto") input_text = "A <extra_id_0> walks into a bar a orders a <extra_id_1> with <extra_id_2> pinch of <extra_id_3>." input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(0) outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) >>> <pad> <extra_id_0> man<extra_id_1> beer<extra_id_2> a<extra_id_3> salt<extra_id_4>.</s> ``` </details> ### Running the model on a GPU using different precisions #### FP16 <details> <summary> Click to expand </summary> ```python # pip install accelerate from transformers import AutoTokenizer, SwitchTransformersForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained("google/switch-base-16") model = SwitchTransformersForConditionalGeneration.from_pretrained("google/switch-base-16", device_map="auto", torch_dtype=torch.float16) input_text = "A <extra_id_0> walks into a bar a orders a <extra_id_1> with <extra_id_2> pinch of <extra_id_3>." input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(0) outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) >>> <pad> <extra_id_0> man<extra_id_1> beer<extra_id_2> a<extra_id_3> salt<extra_id_4>.</s> ``` </details> #### INT8 <details> <summary> Click to expand </summary> ```python # pip install bitsandbytes accelerate from transformers import AutoTokenizer, SwitchTransformersForConditionalGeneration tokenizer = AutoTokenizer.from_pretrained("google/switch-base-16") model = SwitchTransformersForConditionalGeneration.from_pretrained("google/switch-base-16", device_map="auto") input_text = "A <extra_id_0> walks into a bar a orders a <extra_id_1> with <extra_id_2> pinch of <extra_id_3>." input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(0) outputs = model.generate(input_ids) print(tokenizer.decode(outputs[0])) >>> <pad> <extra_id_0> man<extra_id_1> beer<extra_id_2> a<extra_id_3> salt<extra_id_4>.</s> ``` </details> # Uses ## Direct Use and Downstream Use See the [research paper](https://arxiv.org/pdf/2101.03961.pdf) for further details. ## Out-of-Scope Use More information needed. # Bias, Risks, and Limitations More information needed. ## Ethical considerations and risks More information needed. ## Known Limitations More information needed. ## Sensitive Use: More information needed. # Training Details ## Training Data The model was trained on a Masked Language Modeling task, on Colossal Clean Crawled Corpus (C4) dataset, following the same procedure as `T5`. ## Training Procedure According to the model card from the [original paper](https://arxiv.org/pdf/2101.03961.pdf) the model has been trained on TPU v3 or TPU v4 pods, using [`t5x`](https://github.com/google-research/t5x) codebase together with [`jax`](https://github.com/google/jax). # Evaluation ## Testing Data, Factors & Metrics The authors evaluated the model on various tasks and compared the results against T5. See the table below for some quantitative evaluation: ![image.png](https://s3.amazonaws.com/moonup/production/uploads/1666967660372-62441d1d9fdefb55a0b7d12c.png) For full details, please check the [research paper](https://arxiv.org/pdf/2101.03961.pdf). ## Results For full results for Switch Transformers, see the [research paper](https://arxiv.org/pdf/2101.03961.pdf), Table 5. # Environmental Impact Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** Google Cloud TPU Pods - TPU v3 or TPU v4 | Number of chips ≥ 4. - **Hours used:** More information needed - **Cloud Provider:** GCP - **Compute Region:** More information needed - **Carbon Emitted:** More information needed # Citation **BibTeX:** ```bibtex @misc{https://doi.org/10.48550/arxiv.2101.03961, doi = {10.48550/ARXIV.2101.03961}, url = {https://arxiv.org/abs/2101.03961}, author = {Fedus, William and Zoph, Barret and Shazeer, Noam}, keywords = {Machine Learning (cs.LG), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity}, publisher = {arXiv}, year = {2021}, copyright = {arXiv.org perpetual, non-exclusive license} } ```

shi-labs/oneformer_ade20k_dinat_large

shi-labs

"2023-08-30T00:03:28Z"

2,558

5

transformers

[ "transformers", "pytorch", "oneformer", "vision", "image-segmentation", "dataset:scene_parse_150", "arxiv:2211.06220", "license:mit", "endpoints_compatible", "region:us" ]

image-segmentation

"2022-11-15T20:25:34Z"

--- license: mit tags: - vision - image-segmentation datasets: - scene_parse_150 widget: - src: https://praeclarumjj3.github.io/files/ade20k.jpeg example_title: House - src: https://praeclarumjj3.github.io/files/demo_2.jpg example_title: Airplane - src: https://praeclarumjj3.github.io/files/coco.jpeg example_title: Person --- # OneFormer OneFormer model trained on the ADE20k dataset (large-sized version, Dinat backbone). It was introduced in the paper [OneFormer: One Transformer to Rule Universal Image Segmentation](https://arxiv.org/abs/2211.06220) by Jain et al. and first released in [this repository](https://github.com/SHI-Labs/OneFormer). ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/oneformer_teaser.png) ## Model description OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing specialized models across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task-guided for training, and task-dynamic for inference, all with a single model. ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/oneformer_architecture.png) ## Intended uses & limitations You can use this particular checkpoint for semantic, instance and panoptic segmentation. See the [model hub](https://huggingface.co/models?search=oneformer) to look for other fine-tuned versions on a different dataset. ### How to use Here is how to use this model: ```python from transformers import OneFormerProcessor, OneFormerForUniversalSegmentation from PIL import Image import requests url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/ade20k.jpeg" image = Image.open(requests.get(url, stream=True).raw) # Loading a single model for all three tasks processor = OneFormerProcessor.from_pretrained("shi-labs/oneformer_ade20k_dinat_large") model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_ade20k_dinat_large") # Semantic Segmentation semantic_inputs = processor(images=image, task_inputs=["semantic"], return_tensors="pt") semantic_outputs = model(**semantic_inputs) # pass through image_processor for postprocessing predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0] # Instance Segmentation instance_inputs = processor(images=image, task_inputs=["instance"], return_tensors="pt") instance_outputs = model(**instance_inputs) # pass through image_processor for postprocessing predicted_instance_map = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"] # Panoptic Segmentation panoptic_inputs = processor(images=image, task_inputs=["panoptic"], return_tensors="pt") panoptic_outputs = model(**panoptic_inputs) # pass through image_processor for postprocessing predicted_semantic_map = processor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"] ``` For more examples, please refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/oneformer). ### Citation ```bibtex @article{jain2022oneformer, title={{OneFormer: One Transformer to Rule Universal Image Segmentation}}, author={Jitesh Jain and Jiachen Li and MangTik Chiu and Ali Hassani and Nikita Orlov and Humphrey Shi}, journal={arXiv}, year={2022} } ```

PygmalionAI/pygmalion-2.7b

PygmalionAI

"2023-01-12T19:20:02Z"

2,557

52

transformers

[ "transformers", "pytorch", "tensorboard", "gpt_neo", "text-generation", "text generation", "conversational", "en", "license:creativeml-openrail-m", "autotrain_compatible", "region:us" ]

text-generation

"2023-01-05T14:57:04Z"

--- license: creativeml-openrail-m language: - en thumbnail: tags: - text generation - conversational inference: false --- # Pygmalion 2.7B ## Model description Pymalion 2.7B is a proof-of-concept dialogue model based on EleutherAI's [gpt-neo-2.7B](https://huggingface.co/EleutherAI/gpt-neo-2.7B). **Warning:** This model is **NOT** suitable for use by minors. It **will** output X-rated content under certain circumstances. ## Training data The fine-tuning dataset consisted of 56MB of dialogue data gathered from multiple sources, which includes both real _and_ partially machine-generated conversations. ## Training procedure Model weights were initialized from the `uft-2.7b` ConvoGPT model made available in [this commit](https://huggingface.co/hakurei/convogpt/tree/07707377dee0aa7d1ee5363ef660b13eb5b73f9d/2.7b-uft). The model was then further fine-tuned on ~48.5 million tokens for ~5k steps on 4 NVIDIA A40s using DeepSpeed. ## Intended use ### The easy way We provide a notebook with a Gradio UI for playing around with the model without having to manually format inputs. This notebook can be found [here](https://github.com/PygmalionAI/gradio-ui/blob/master/notebooks/GPU.ipynb). ### The manual way The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format: ``` [CHARACTER]'s Persona: [A few sentences about the character you want the model to play] <START> [DIALOGUE HISTORY] You: [Your input message here] [CHARACTER]: ``` Where `[CHARACTER]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like: ``` [CHARACTER]: [some dialogue here] You: [your response to the dialogue above] ``` Apart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition. ## Known issues We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!

YokaiKoibito/falcon-40b-GGUF

YokaiKoibito

"2023-09-06T05:40:45Z"

2,557

9

null

[ "gguf", "Transformers", "falcon", "text-generation-inference", "license:other", "region:us" ]

null

"2023-09-05T06:49:30Z"

--- license: other tags: - Transformers - falcon - text-generation-inference --- # Falcon 40B Base Model GGUF These files are GGUF format quantized model files for [TII](https://www.tii.ae)'s [tiiuae/Falcon 40B](https://huggingface.co/tiiuae/falcon-40b) base model.  ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates. As of August 25th, here is a list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling. * [LM Studio](https://lmstudio.ai/), version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), should now work, choose the `c_transformers` backend. A great web UI with many interesting features. Supports CUDA GPU acceleration. * [ctransformers](https://github.com/marella/ctransformers), now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use. The clients and libraries below are expecting to add GGUF support shortly:   ## Repositories available * [4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/YokaiKoibito/falcon-40b-GGML) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference, plus fp16 GGUF for requantizing](https://huggingface.co/YokaiKoibito/falcon-40b-GGUF) * [TII's unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/tiiuae/falcon-40b)

CohereForAI/c4ai-command-r-plus-4bit

CohereForAI

"2024-04-05T09:55:30Z"

2,557

210

transformers

[ "transformers", "safetensors", "cohere", "text-generation", "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "bitsandbytes", "region:us" ]

text-generation

"2024-04-03T19:05:18Z"

--- license: cc-by-nc-4.0 library_name: transformers language: - en - fr - de - es - it - pt - ja - ko - zh - ar --- # Model Card for C4AI Command R+ 🚨 **This model is 4bit quantized version of C4AI Command R+ using bitsandbytes.** You can find the unquantized version of C4AI Command R+ [here](https://huggingface.co/CohereForAI/c4ai-command-r-plus). ## Model Summary C4AI Command R+ is an open weights research release of a 104B billion parameter model with highly advanced capabilities, this includes Retrieval Augmented Generation (RAG) and tool use to automate sophisticated tasks. The tool use in this model generation enables multi-step tool use which allows the model to combine multiple tools over multiple steps to accomplish difficult tasks. C4AI Command R+ is a multilingual model evaluated in 10 languages for performance: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Arabic, and Simplified Chinese. Command R+ is optimized for a variety of use cases including reasoning, summarization, and question answering. C4AI Command R+ is part of a family of open weight releases from Cohere For AI and Cohere. Our smaller companion model is [C4AI Command R](https://huggingface.co/CohereForAI/c4ai-command-r-v01). Developed by: [Cohere](https://cohere.com/) and [Cohere For AI](https://cohere.for.ai) - Point of Contact: Cohere For AI: [cohere.for.ai](https://cohere.for.ai/) - License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy) - Model: c4ai-command-r-plus - Model Size: 104 billion parameters - Context length: 128K **Try C4AI Command R+** You can try out C4AI Command R+ before downloading the weights in our hosted [Hugging Face Space](https://huggingface.co/spaces/CohereForAI/c4ai-command-r-plus). **Usage** Please install `transformers` from the source repository that includes the necessary changes for this model. ```python # pip install 'git+https://github.com/huggingface/transformers.git' bitsandbytes accelerate from transformers import AutoTokenizer, AutoModelForCausalLM model_id = "CohereForAI/c4ai-command-r-plus-4bit" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) # Format message with the command-r-plus chat template messages = [{"role": "user", "content": "Hello, how are you?"}] input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt") ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|> gen_tokens = model.generate( input_ids, max_new_tokens=100, do_sample=True, temperature=0.3, ) gen_text = tokenizer.decode(gen_tokens[0]) print(gen_text) ``` ## Model Details **Input**: Models input text only. **Output**: Models generate text only. **Model Architecture**: This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety. **Languages covered**: The model is optimized to perform well in the following languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. Pre-training data additionally included the following 13 languages: Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, Persian. **Context length**: Command R+ supports a context length of 128K. ### Tool use & multihop capabilities: Command R+ has been specifically trained with conversational tool use capabilities. These have been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template will likely reduce performance, but we encourage experimentation. Command R+’s tool use functionality takes a conversation as input (with an optional user-system preamble), along with a list of available tools. The model will then generate a json-formatted list of actions to execute on a subset of those tools. Command R+ may use one of its supplied tools more than once. The model has been trained to recognise a special `directly_answer` tool, which it uses to indicate that it doesn’t want to use any of its other tools. The ability to abstain from calling a specific tool can be useful in a range of situations, such as greeting a user, or asking clarifying questions. We recommend including the `directly_answer` tool, but it can be removed or renamed if required. Comprehensive documentation for working with command R+'s tool use prompt template can be found [here](https://docs.cohere.com/docs/prompting-command-r). The code snippet below shows a minimal working example on how to render a prompt. <details> <summary><b>Usage: Rendering Tool Use Prompts [CLICK TO EXPAND]</b> </summary> ```python from transformers import AutoTokenizer model_id = "CohereForAI/c4ai-command-r-plus-4bit" tokenizer = AutoTokenizer.from_pretrained(model_id) # define conversation input: conversation = [ {"role": "user", "content": "Whats the biggest penguin in the world?"} ] # Define tools available for the model to use: tools = [ { "name": "internet_search", "description": "Returns a list of relevant document snippets for a textual query retrieved from the internet", "parameter_definitions": { "query": { "description": "Query to search the internet with", "type": 'str', "required": True } } }, { 'name': "directly_answer", "description": "Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history", 'parameter_definitions': {} } ] # render the tool use prompt as a string: tool_use_prompt = tokenizer.apply_tool_use_template( conversation, tools=tools, tokenize=False, add_generation_prompt=True, ) print(tool_use_prompt) ``` </details> <details> <summary><b>Example Rendered Tool Use Prompt [CLICK TO EXPAND]</b></summary> ```` <BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral. # System Preamble ## Basic Rules You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions. # User Preamble ## Task and Context You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging. ## Style Guide Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling. ## Available Tools Here is a list of tools that you have available to you: ```python def internet_search(query: str) -> List[Dict]: """Returns a list of relevant document snippets for a textual query retrieved from the internet Args: query (str): Query to search the internet with """ pass ``` ```python def directly_answer() -> List[Dict]: """Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history """ pass ```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Whats the biggest penguin in the world?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write 'Action:' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user's last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example: ```json [ { "tool_name": title of the tool in the specification, "parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters } ]```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|> ```` </details> <details> <summary><b>Example Rendered Tool Use Completion [CLICK TO EXPAND]</b></summary> ```` Action: ```json [ { "tool_name": "internet_search", "parameters": { "query": "biggest penguin in the world" } } ] ``` ```` </details> ### Grounded Generation and RAG Capabilities: Command R+ has been specifically trained with grounded generation capabilities. This means that it can generate responses based on a list of supplied document snippets, and it will include grounding spans (citations) in its response indicating the source of the information. This can be used to enable behaviors such as grounded summarization and the final step of Retrieval Augmented Generation (RAG). This behavior has been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template may reduce performance, but we encourage experimentation. Command R+’s grounded generation behavior takes a conversation as input (with an optional user-supplied system preamble, indicating task, context and desired output style), along with a list of retrieved document snippets. The document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured. By default, Command R+ will generate grounded responses by first predicting which documents are relevant, then predicting which ones it will cite, then generating an answer. Finally, it will then insert grounding spans into the answer. See below for an example. This is referred to as `accurate` grounded generation. The model is trained with a number of other answering modes, which can be selected by prompt changes. A `fast` citation mode is supported in the tokenizer, which will directly generate an answer with grounding spans in it, without first writing the answer out in full. This sacrifices some grounding accuracy in favor of generating fewer tokens. Comprehensive documentation for working with Command R+'s grounded generation prompt template can be found [here](https://docs.cohere.com/docs/prompting-command-r). The code snippet below shows a minimal working example on how to render a prompt. <details> <summary> <b>Usage: Rendering Grounded Generation prompts [CLICK TO EXPAND]</b> </summary> ````python from transformers import AutoTokenizer model_id = "CohereForAI/c4ai-command-r-plus-4bit" tokenizer = AutoTokenizer.from_pretrained(model_id) # define conversation input: conversation = [ {"role": "user", "content": "Whats the biggest penguin in the world?"} ] # define documents to ground on: documents = [ { "title": "Tall penguins", "text": "Emperor penguins are the tallest growing up to 122 cm in height." }, { "title": "Penguin habitats", "text": "Emperor penguins only live in Antarctica."} ] # render the tool use prompt as a string: grounded_generation_prompt = tokenizer.apply_grounded_generation_template( conversation, documents=documents, citation_mode="accurate", # or "fast" tokenize=False, add_generation_prompt=True, ) print(grounded_generation_prompt) ```` </details> <details> <summary><b>Example Rendered Grounded Generation Prompt [CLICK TO EXPAND]</b></summary> ````<BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral. # System Preamble ## Basic Rules You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions. # User Preamble ## Task and Context You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging. ## Style Guide Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Whats the biggest penguin in the world?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><results> Document: 0 title: Tall penguins text: Emperor penguins are the tallest growing up to 122 cm in height. Document: 1 title: Penguin habitats text: Emperor penguins only live in Antarctica. </results><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Carefully perform the following instructions, in order, starting each with a new line. Firstly, Decide which of the retrieved documents are relevant to the user's last input by writing 'Relevant Documents:' followed by comma-separated list of document numbers. If none are relevant, you should instead write 'None'. Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user's last input by writing 'Cited Documents:' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write 'None'. Thirdly, Write 'Answer:' followed by a response to the user's last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup. Finally, Write 'Grounded answer:' followed by a response to the user's last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|> ```` </details> <details> <summary><b>Example Rendered Grounded Generation Completion [CLICK TO EXPAND]</b></summary> ```` Relevant Documents: 0,1 Cited Documents: 0,1 Answer: The Emperor Penguin is the tallest or biggest penguin in the world. It is a bird that lives only in Antarctica and grows to a height of around 122 centimetres. Grounded answer: The <co: 0>Emperor Penguin</co: 0> is the <co: 0>tallest</co: 0> or biggest penguin in the world. It is a bird that <co: 1>lives only in Antarctica</co: 1> and <co: 0>grows to a height of around 122 centimetres.</co: 0> ```` </details> ### Code Capabilities: Command R+ has been optimized to interact with your code, by requesting code snippets, code explanations, or code rewrites. It might not perform well out-of-the-box for pure code completion. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions. ### Model Card Contact For errors or additional questions about details in this model card, contact [[email protected]](mailto:[email protected]). ### Terms of Use: We hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 104 billion parameter model to researchers all over the world. This model is governed by a [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license) License with an acceptable use addendum, and also requires adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy). ### Try Chat: You can try Command R+ chat in the playground [here](https://dashboard.cohere.com/playground/chat). You can also use it in our dedicated Hugging Face Space [here](https://huggingface.co/spaces/CohereForAI/c4ai-command-r-plus).

mradermacher/L3-Penumbral-Mind-RP-8B-GGUF

mradermacher

"2024-06-13T21:06:06Z"

2,557

0

transformers

[ "transformers", "gguf", "merge", "mergekit", "lazymergekit", "not-for-all-audiences", "rp", "roleplay", "role-play", "en", "base_model:Casual-Autopsy/L3-Penumbral-Mind-RP-8B", "license:llama3", "endpoints_compatible", "region:us" ]

null

"2024-06-12T12:27:59Z"

--- base_model: Casual-Autopsy/L3-Penumbral-Mind-RP-8B language: - en library_name: transformers license: llama3 quantized_by: mradermacher tags: - merge - mergekit - lazymergekit - not-for-all-audiences - rp - roleplay - role-play --- ## About      static quants of https://huggingface.co/Casual-Autopsy/L3-Penumbral-Mind-RP-8B  weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/L3-Penumbral-Mind-RP-8B-GGUF/resolve/main/L3-Penumbral-Mind-RP-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

Lewdiculous/L3-TheSpice-8b-v0.8.3-GGUF-IQ-Imatrix

Lewdiculous

"2024-05-15T14:01:40Z"

2,555

13

null

[ "gguf", "license:cc-by-4.0", "region:us" ]

null

"2024-05-03T12:26:37Z"

--- license: cc-by-4.0 --- # #llama-3 #roleplay > [!IMPORTANT] > Version 2 files uploaded! GGUF-IQ-Imatrix quants for [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3). > [!IMPORTANT] > These quants have already been done after the fixes from [llama.cpp/pull/6920](https://github.com/ggerganov/llama.cpp/pull/6920). <br> > Use **KoboldCpp version 1.64** or higher. > [!NOTE] > **Prompt formatting...** <br> > Prompt format is relatively simple, author seems to recommend the **Default** context preset and **Instruct Mode - Disabled**. <br> > I recommend reading original [**model card page information**](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3#prompt-format-chat--the-default-ooba-template-and-silly-tavern-template-). ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/VNpZl0O7dpwWLK8i5RG5d.png) # Original model information by the author: Now not overtrained and with the tokenizer fix to base llama3. Trained for 3 epochs. The latest TheSpice, dipped in Mama Liz's LimaRP Oil. I've focused on making the model more flexible and provide a more unique experience. I'm still working on cleaning up my dataset, but I've shrunken it down a lot to focus on a "less is more" approach. This is ultimate a return to form of the way I used to train Thespis, with more of a focus on a small hand edited dataset. ## Datasets Used * Capybara * Claude Multiround 30k * Augmental * ToxicQA * Yahoo Answers * Airoboros 3.1 * LimaRP ## Features ( Examples from 0.1.1 because I'm too lazy to take new screenshots. Its tested tho. ) Narration If you request information on objects or characters in the scene, the model will narrate it to you. Most of the time, without moving the story forward. # You can look at anything mostly as long as you end it with "What do I see?" ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/VREY8QHtH6fCL0fCp8AAC.png) # You can also request to know what a character is thinking or planning. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/U3RTAgbaB2m1ygfZGJ-SM.png) # You can ask for a quick summary on the character as well. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/uXFd6GhnXS8w_egUEfcAp.png) # Before continuing the conversation as normal. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/dYTQUdCshUDtp_BJ20tHy.png) ## Prompt Format: Chat ( The default Ooba template and Silly Tavern Template ) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/59vi4VWP2d0bCbsW2eU8h.png) If you're using Ooba in verbose mode as a server, you can check if you're console is logging something that looks like this. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64dd7cda3d6b954bf7cdd922/mB3wZqtwN8B45nR7W1fgR.png) ``` {System Prompt} Username: {Input} BotName: {Response} Username: {Input} BotName: {Response} ``` ## Presets All screenshots above were taken with the below SillyTavern Preset. ## Recommended Silly Tavern Preset -> (Temp: 1.25, MinP: 0.1, RepPen: 1.05) This is a roughly equivalent Kobold Horde Preset. ## Recommended Kobold Horde Preset -> MinP # Disclaimer Please prompt responsibly and take anything outputted by any Language Model with a huge grain of salt. Thanks!

Niggendar/waiANINSFWPONYXL_v40

Niggendar

"2024-05-22T13:41:44Z"

2,555

2

diffusers

[ "diffusers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]

text-to-image

"2024-05-22T13:34:18Z"

--- library_name: diffusers --- # Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

TheBloke/CodeLlama-70B-Instruct-GGUF

TheBloke

"2024-01-30T23:00:08Z"

2,554

52

transformers

[ "transformers", "gguf", "llama", "llama-2", "text-generation", "code", "arxiv:2308.12950", "base_model:codellama/CodeLlama-70b-Instruct-hf", "license:llama2", "text-generation-inference", "region:us" ]

text-generation

"2024-01-30T18:31:55Z"

--- base_model: codellama/CodeLlama-70b-Instruct-hf inference: false language: - code license: llama2 model_creator: Code Llama model_name: Codellama 70B Instruct model_type: llama pipeline_tag: text-generation prompt_template: "Source: system\n\n {system_message}<step> Source: user\n\n {prompt}\ \ <step> Source: assistant\n \n" quantized_by: TheBloke tags: - llama-2 ---    <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">  # Codellama 70B Instruct - GGUF - Model creator: [Code Llama](https://huggingface.co/codellama) - Original model: [Codellama 70B Instruct](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf)  ## Description This repo contains GGUF format model files for [Code Llama's Codellama 70B Instruct](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf). These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).   ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.   ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF) * [Code Llama's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf)   ## Prompt template: CodeLlama-70B-Instruct ``` Source: system {system_message}<step> Source: user {prompt} <step> Source: assistant ```   ## Compatibility These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) They are also compatible with many third party UIs and libraries - please see the list at the top of this README. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details>   ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [codellama-70b-instruct.Q2_K.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q2_K.gguf) | Q2_K | 2 | 25.46 GB| 27.96 GB | significant quality loss - not recommended for most purposes | | [codellama-70b-instruct.Q3_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q3_K_S.gguf) | Q3_K_S | 3 | 29.92 GB| 32.42 GB | very small, high quality loss | | [codellama-70b-instruct.Q3_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q3_K_M.gguf) | Q3_K_M | 3 | 33.27 GB| 35.77 GB | very small, high quality loss | | [codellama-70b-instruct.Q3_K_L.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q3_K_L.gguf) | Q3_K_L | 3 | 36.15 GB| 38.65 GB | small, substantial quality loss | | [codellama-70b-instruct.Q4_0.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q4_0.gguf) | Q4_0 | 4 | 38.87 GB| 41.37 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [codellama-70b-instruct.Q4_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q4_K_S.gguf) | Q4_K_S | 4 | 39.25 GB| 41.75 GB | small, greater quality loss | | [codellama-70b-instruct.Q4_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q4_K_M.gguf) | Q4_K_M | 4 | 41.42 GB| 43.92 GB | medium, balanced quality - recommended | | [codellama-70b-instruct.Q5_0.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q5_0.gguf) | Q5_0 | 5 | 47.46 GB| 49.96 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [codellama-70b-instruct.Q5_K_S.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q5_K_S.gguf) | Q5_K_S | 5 | 47.46 GB| 49.96 GB | large, low quality loss - recommended | | [codellama-70b-instruct.Q5_K_M.gguf](https://huggingface.co/TheBloke/CodeLlama-70B-Instruct-GGUF/blob/main/codellama-70b-instruct.Q5_K_M.gguf) | Q5_K_M | 5 | 48.75 GB| 51.25 GB | large, very low quality loss - recommended | | codellama-70b-instruct.Q6_K.gguf | Q6_K | 6 | 56.59 GB| 59.09 GB | very large, extremely low quality loss | | codellama-70b-instruct.Q8_0.gguf | Q8_0 | 8 | 73.29 GB| 75.79 GB | very large, extremely low quality loss - not recommended | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ### Q6_K and Q8_0 files are split and require joining **Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files. <details> <summary>Click for instructions regarding Q6_K and Q8_0 files</summary> ### q6_K Please download: * `codellama-70b-instruct.Q6_K.gguf-split-a` * `codellama-70b-instruct.Q6_K.gguf-split-b` ### q8_0 Please download: * `codellama-70b-instruct.Q8_0.gguf-split-a` * `codellama-70b-instruct.Q8_0.gguf-split-b` To join the files, do the following: Linux and macOS: ``` cat codellama-70b-instruct.Q6_K.gguf-split-* > codellama-70b-instruct.Q6_K.gguf && rm codellama-70b-instruct.Q6_K.gguf-split-* cat codellama-70b-instruct.Q8_0.gguf-split-* > codellama-70b-instruct.Q8_0.gguf && rm codellama-70b-instruct.Q8_0.gguf-split-* ``` Windows command line: ``` COPY /B codellama-70b-instruct.Q6_K.gguf-split-a + codellama-70b-instruct.Q6_K.gguf-split-b codellama-70b-instruct.Q6_K.gguf del codellama-70b-instruct.Q6_K.gguf-split-a codellama-70b-instruct.Q6_K.gguf-split-b COPY /B codellama-70b-instruct.Q8_0.gguf-split-a + codellama-70b-instruct.Q8_0.gguf-split-b codellama-70b-instruct.Q8_0.gguf del codellama-70b-instruct.Q8_0.gguf-split-a codellama-70b-instruct.Q8_0.gguf-split-b ``` </details>   ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/CodeLlama-70B-Instruct-GGUF and below it, a specific filename to download, such as: codellama-70b-instruct.Q4_K_M.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/CodeLlama-70B-Instruct-GGUF codellama-70b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/CodeLlama-70B-Instruct-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/CodeLlama-70B-Instruct-GGUF codellama-70b-instruct.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details>   ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m codellama-70b-instruct.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Source: system\n\n {system_message}<step> Source: user\n\n {prompt} <step> Source: assistant" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./codellama-70b-instruct.Q4_K_M.gguf", # Download the model file first n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "Source: system\n\n {system_message}<step> Source: user\n\n {prompt} <step> Source: assistant", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./codellama-70b-instruct.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)    ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant.   # Original model card: Code Llama's Codellama 70B Instruct # **Code Llama** Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 70B instruct-tuned version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom. | | Base Model | Python | Instruct | | --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- | | 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) | | 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) | | 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) | | 70B | [codellama/CodeLlama-70b-hf](https://huggingface.co/codellama/CodeLlama-70b-hf) | [codellama/CodeLlama-70b-Python-hf](https://huggingface.co/codellama/CodeLlama-70b-Python-hf) | [codellama/CodeLlama-70b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf) | Model capabilities: - [x] Code completion. - [ ] Infilling. - [x] Instructions / chat. - [ ] Python specialist. ## Model Use Install `transformers` ```bash pip install transformers accelerate ``` **Chat use:** The 70B Instruct model uses a [different prompt template](#chat_prompt) than the smaller versions. To use it with `transformers`, we recommend you use the built-in chat template: ```py from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model_id = "codellama/CodeLlama-70b-Instruct-hf" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto", ) chat = [ {"role": "system", "content": "You are a helpful and honest code assistant expert in JavaScript. Please, provide all answers to programming questions in JavaScript"}, {"role": "user", "content": "Write a function that computes the set of sums of all contiguous sublists of a given list."}, ] inputs = tokenizer.apply_chat_template(chat, return_tensors="pt").to("cuda") output = model.generate(input_ids=inputs, max_new_tokens=200) output = output[0].to("cpu") print(tokenizer.decode(output)) ``` You can also use the model for **text or code completion**. This examples uses transformers' `pipeline` interface: ```py from transformers import AutoTokenizer import transformers import torch model_id = "codellama/CodeLlama-70b-hf" tokenizer = AutoTokenizer.from_pretrained(model_id) pipeline = transformers.pipeline( "text-generation", model=model_id, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( 'def fibonacci(', do_sample=True, temperature=0.2, top_p=0.9, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, max_length=100, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` <a name="chat_prompt"></a> ## Chat prompt CodeLlama 70B Instruct uses a different format for the chat prompt than previous Llama 2 or CodeLlama models. As mentioned above, the easiest way to use it is with the help of the tokenizer's chat template. If you need to build the string or tokens, manually, here's how to do it. We'll do our tests with the following made-up dialog: ```py chat = [ {"role": "system", "content": "System prompt "}, {"role": "user", "content": "First user query"}, {"role": "assistant", "content": "Model response to first query"}, {"role": "user", "content": "Second user query"}, ] ``` First, let's see what the prompt looks like if we use the chat template: ```py tokenizer.apply_chat_template(chat, tokenize=False) ``` ``` '<s>Source: system\n\n System prompt <step> Source: user\n\n First user query <step> Source: assistant\n\n Model response to first query <step> Source: user\n\n Second user query <step> Source: assistant\nDestination: user\n\n ' ``` So each turn of the conversation has a `Source` (`system`, `user`, or `assistant`), and then the content appears after two newlines and a space. Turns are separated with the special token ` <step> `. After the last turn (which must necessarily come from the `user`), we invite the model to respond by using the special syntax `Source: assistant\nDestination: user\n\n `. Let's see how we can build the same string ourselves: ```py output = "<s>" for m in chat: output += f"Source: {m['role']}\n\n {m['content'].strip()}" output += " <step> " output += "Source: assistant\nDestination: user\n\n " output ``` ``` '<s>Source: system\n\n System prompt <step> Source: user\n\n First user query <step> Source: assistant\n\n Model response to first query <step> Source: user\n\n Second user query <step> Source: assistant\nDestination: user\n\n ' ``` To verify that we got it right, we'll compare against the [reference code in the original GitHub repo](https://github.com/facebookresearch/codellama/blob/1af62e1f43db1fa5140fa43cb828465a603a48f3/llama/generation.py#L506). We used the same dialog and tokenized it with the `dialog_prompt_tokens` function and got the following tokens: ```py reference_tokens = [1, 7562, 29901, 1788, 13, 13, 2184, 9508, 32015, 7562, 29901, 1404, 13, 13, 3824, 1404, 2346, 32015, 7562, 29901, 20255, 13, 13, 8125, 2933, 304, 937, 2346, 32015, 7562, 29901, 1404, 13, 13, 6440, 1404, 2346, 32015, 7562, 29901, 20255, 13, 14994, 3381, 29901, 1404, 13, 13, 29871] ``` Let's see what we get with the string we built using our Python loop. Note that we don't add "special tokens" because the string already starts with `<s>`, the beginning of sentence token: ```py tokens = tokenizer.encode(output, add_special_tokens=False) assert reference_tokens == tokens ``` Similarly, let's verify that the chat template produces the same token sequence: ```py assert reference_tokens == tokenizer.apply_chat_template(chat) ``` As a final detail, please note that if the dialog does not start with a `system` turn, the [original code will insert one with an empty content string](https://github.com/facebookresearch/codellama/blob/1af62e1f43db1fa5140fa43cb828465a603a48f3/llama/generation.py#L418). ## Model Details *Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs). **Model Developers** Meta **Variations** Code Llama comes in four model sizes, and three variants: * Code Llama: base models designed for general code synthesis and understanding * Code Llama - Python: designed specifically for Python * Code Llama - Instruct: for instruction following and safer deployment All variants are available in sizes of 7B, 13B, 34B, and 70B parameters. **This repository contains the Instruct version of the 70B parameters model.** **Input** Models input text only. **Output** Models generate text only. **Model Architecture** Code Llama is an auto-regressive language model that uses an optimized transformer architecture. It was fine-tuned with up to 16k tokens. This variant **does not** support long context of up to 100k tokens. **Model Dates** Code Llama and its variants have been trained between January 2023 and January 2024. **Status** This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback. **License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) **Research Paper** More information can be found in the paper "[Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)" or its [arXiv page](https://arxiv.org/abs/2308.12950). ## Intended Use **Intended Use Cases** Code Llama and its variants are intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications. **Out-of-Scope Uses** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants. ## Hardware and Software **Training Factors** We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster. **Carbon Footprint** In aggregate, training all 12 Code Llama models required 1400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 228.55 tCO2eq, 100% of which were offset by Meta’s sustainability program. ## Evaluation Results See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper. ## Ethical Considerations and Limitations Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available available at [https://ai.meta.com/llama/responsible-use-guide](https://ai.meta.com/llama/responsible-use-guide).

timm/densenet161.tv_in1k

timm

"2023-04-21T22:54:19Z"

2,551

0

timm

[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-1k", "arxiv:1608.06993", "license:apache-2.0", "region:us" ]

image-classification

"2023-04-21T22:53:57Z"

--- tags: - image-classification - timm library_name: timm license: apache-2.0 datasets: - imagenet-1k --- # Model card for densenet161.tv_in1k A DenseNet image classification model. Trained on ImageNet-1k (original torchvision weights). ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 28.7 - GMACs: 7.8 - Activations (M): 11.1 - Image size: 224 x 224 - **Papers:** - Densely Connected Convolutional Networks: https://arxiv.org/abs/1608.06993 - **Dataset:** ImageNet-1k - **Original:** https://github.com/pytorch/vision ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('densenet161.tv_in1k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'densenet161.tv_in1k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 96, 112, 112]) # torch.Size([1, 384, 56, 56]) # torch.Size([1, 768, 28, 28]) # torch.Size([1, 2112, 14, 14]) # torch.Size([1, 2208, 7, 7]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'densenet161.tv_in1k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 2208, 7, 7) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Citation ```bibtex @inproceedings{huang2017densely, title={Densely Connected Convolutional Networks}, author={Huang, Gao and Liu, Zhuang and van der Maaten, Laurens and Weinberger, Kilian Q }, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, year={2017} } ```

lemon-mint/gemma-ko-1.1-2b-it

lemon-mint

"2024-04-26T01:53:56Z"

2,551

1

transformers

[ "transformers", "safetensors", "gemma", "text-generation", "mergekit", "merge", "conversational", "base_model:beomi/gemma-ko-2b", "base_model:google/gemma-1.1-2b-it", "base_model:google/gemma-2b", "license:gemma", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2024-04-26T00:21:36Z"

--- base_model: - beomi/gemma-ko-2b - google/gemma-1.1-2b-it - google/gemma-2b library_name: transformers tags: - mergekit - merge license: gemma --- # merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it) * [google/gemma-2b](https://huggingface.co/google/gemma-2b) * [beomi/gemma-ko-2b](https://huggingface.co/beomi/gemma-ko-2b)

hfl/chinese-electra-180g-small-ex-discriminator

hfl

"2021-03-03T01:25:29Z"

2,550

7

transformers

[ "transformers", "pytorch", "tf", "electra", "zh", "arxiv:2004.13922", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

"2022-03-02T23:29:05Z"

--- language: - zh license: "apache-2.0" --- # This model is trained on 180G data, we recommend using this one than the original version. ## Chinese ELECTRA Google and Stanford University released a new pre-trained model called ELECTRA, which has a much compact model size and relatively competitive performance compared to BERT and its variants. For further accelerating the research of the Chinese pre-trained model, the Joint Laboratory of HIT and iFLYTEK Research (HFL) has released the Chinese ELECTRA models based on the official code of ELECTRA. ELECTRA-small could reach similar or even higher scores on several NLP tasks with only 1/10 parameters compared to BERT and its variants. This project is based on the official code of ELECTRA: [https://github.com/google-research/electra](https://github.com/google-research/electra) You may also interested in, - Chinese BERT series: https://github.com/ymcui/Chinese-BERT-wwm - Chinese ELECTRA: https://github.com/ymcui/Chinese-ELECTRA - Chinese XLNet: https://github.com/ymcui/Chinese-XLNet - Knowledge Distillation Toolkit - TextBrewer: https://github.com/airaria/TextBrewer More resources by HFL: https://github.com/ymcui/HFL-Anthology ## Citation If you find our resource or paper is useful, please consider including the following citation in your paper. - https://arxiv.org/abs/2004.13922 ``` @inproceedings{cui-etal-2020-revisiting, title = "Revisiting Pre-Trained Models for {C}hinese Natural Language Processing", author = "Cui, Yiming and Che, Wanxiang and Liu, Ting and Qin, Bing and Wang, Shijin and Hu, Guoping", booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/2020.findings-emnlp.58", pages = "657--668", } ```

Ghani-25/LF_enrich_sim

Ghani-25

"2023-02-06T14:13:03Z"

2,550

0

transformers

[ "transformers", "pytorch", "tf", "xlm-roberta", "feature-extraction", "endpoints_compatible", "text-embeddings-inference", "region:us" ]

feature-extraction

"2023-02-06T11:25:59Z"

Entry not found

mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf

mmnga

"2023-11-16T14:27:23Z"

2,550

21

null

[ "gguf", "llama2", "ja", "arxiv:2307.09288", "license:llama2", "region:us" ]

null

"2023-08-29T05:33:45Z"

--- license: llama2 language: - ja tags: - llama2 --- # ELYZA-japanese-Llama-2-7b-instruct-gguf [ELYZAさんが公開しているELYZA-japanese-Llama-2-7b-instruct](https://huggingface.co/ELYZA/ELYZA-japanese-Llama-2-7b-instruct)のggufフォーマット変換版です。他のモデルはこちら通常版: llama2に日本語のデータセットで学習したモデル [mmnga/ELYZA-japanese-Llama-2-7b-gguf](https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-gguf) [mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf](https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf) Fast版日本語の語彙を追加してトークンコストを減らし、1.8倍高速化したモデル [mmnga/ELYZA-japanese-Llama-2-7b-fast-gguf](https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-fast-gguf) [mmnga/ELYZA-japanese-Llama-2-7b-fast-instruct-gguf](https://huggingface.co/mmnga/ELYZA-japanese-Llama-2-7b-fast-instruct-gguf) Codellama版 GGUF [mmnga/ELYZA-japanese-CodeLlama-7b-gguf](https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-gguf) [mmnga/ELYZA-japanese-CodeLlama-7b-instruct-gguf](https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-instruct-gguf) Codellama版 GPTQ [mmnga/ELYZA-japanese-CodeLlama-7b-instruct-GPTQ-calib-ja-1k](https://huggingface.co/mmnga/ELYZA-japanese-CodeLlama-7b-instruct-GPTQ-calib-ja-1k) ## Usage ``` git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp make -j ./main -m 'ELYZA-japanese-Llama-2-7b-instruct-q4_0.gguf' -n 256 -p '[INST] <<SYS>>あなたは誠実で優秀な日本人のアシスタントです。<</SYS>>クマが海辺に行ってアザラシと友達になり、最終的には家に帰るというプロットの短編小説を書いてください。 [/INST]' ``` ### Licence Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved. ### 引用 Citations ```tex @misc{elyzallama2023, title={ELYZA-japanese-Llama-2-7b}, url={https://huggingface.co/elyza/ELYZA-japanese-Llama-2-7b}, author={Akira Sasaki and Masato Hirakawa and Shintaro Horie and Tomoaki Nakamura}, year={2023}, } ``` ```tex @misc{touvron2023llama, title={Llama 2: Open Foundation and Fine-Tuned Chat Models}, author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom}, year={2023}, eprint={2307.09288}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

timm/tresnet_m.miil_in21k

timm

"2023-04-21T20:57:27Z"

2,549

1

timm

[ "timm", "pytorch", "safetensors", "image-classification", "arxiv:2003.13630", "arxiv:2104.10972", "license:apache-2.0", "region:us" ]

image-classification

"2023-04-21T20:56:47Z"

--- tags: - image-classification - timm library_name: timm license: apache-2.0 --- # Model card for tresnet_m.miil_in21k A TResNet image classification model. Trained on ImageNet-21K-P ("ImageNet-21K Pretraining for the Masses", a 11k subset of ImageNet-22k) by paper authors. The weights for this model have been remapped and modified from the originals to work with standard BatchNorm instead of InplaceABN. `inplace_abn` can be problematic to build recently and ends up slower with `memory_format=channels_last`, torch.compile(), etc. ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 52.3 - GMACs: 5.8 - Activations (M): 7.3 - Image size: 224 x 224 - **Papers:** - TResNet: High Performance GPU-Dedicated Architecture: https://arxiv.org/abs/2003.13630 - ImageNet-21K Pretraining for the Masses: https://arxiv.org/abs/2104.10972 - **Pretrain Dataset:** ImageNet-21K-P - **Original:** - https://github.com/Alibaba-MIIL/TResNet - https://github.com/Alibaba-MIIL/ImageNet21K ## Model Usage ### Image Classification ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model('tresnet_m.miil_in21k', pretrained=True) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5) ``` ### Feature Map Extraction ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'tresnet_m.miil_in21k', pretrained=True, features_only=True, ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1 for o in output: # print shape of each feature map in output # e.g.: # torch.Size([1, 64, 56, 56]) # torch.Size([1, 128, 28, 28]) # torch.Size([1, 1024, 14, 14]) # torch.Size([1, 2048, 7, 7]) print(o.shape) ``` ### Image Embeddings ```python from urllib.request import urlopen from PIL import Image import timm img = Image.open(urlopen( 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png' )) model = timm.create_model( 'tresnet_m.miil_in21k', pretrained=True, num_classes=0, # remove classifier nn.Linear ) model = model.eval() # get model specific transforms (normalization, resize) data_config = timm.data.resolve_model_data_config(model) transforms = timm.data.create_transform(**data_config, is_training=False) output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor # or equivalently (without needing to set num_classes=0) output = model.forward_features(transforms(img).unsqueeze(0)) # output is unpooled, a (1, 2048, 7, 7) shaped tensor output = model.forward_head(output, pre_logits=True) # output is a (1, num_features) shaped tensor ``` ## Citation ```bibtex @misc{ridnik2020tresnet, title={TResNet: High Performance GPU-Dedicated Architecture}, author={Tal Ridnik and Hussam Lawen and Asaf Noy and Itamar Friedman}, year={2020}, eprint={2003.13630}, archivePrefix={arXiv}, primaryClass={cs.CV} } ``` ```bibtex @misc{ridnik2021imagenet21k, title={ImageNet-21K Pretraining for the Masses}, author={Tal Ridnik and Emanuel Ben-Baruch and Asaf Noy and Lihi Zelnik-Manor}, year={2021}, eprint={2104.10972}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```

johnsnowlabs/JSL-MedLlama-3-8B-v2.0

johnsnowlabs

"2024-04-30T18:06:24Z"

2,549

14

transformers

[ "transformers", "safetensors", "llama", "text-generation", "llama-3-8b", "sft", "medical", "base_model:meta-llama/Meta-Llama-3-8B", "license:cc-by-nc-nd-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

text-generation

"2024-04-30T17:08:30Z"

--- tags: - llama-3-8b - sft - medical base_model: - meta-llama/Meta-Llama-3-8B license: cc-by-nc-nd-4.0 --- # JSL-MedLlama-3-8B-v2.0 [<img src="https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf">](http://www.johnsnowlabs.com) This model is developed by [John Snow Labs](https://www.johnsnowlabs.com/). This model is available under a [CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en) license and must also conform to this [Acceptable Use Policy](https://huggingface.co/johnsnowlabs). If you need to license this model for commercial use, please contact us at [email protected]. ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "johnsnowlabs/JSL-MedLlama-3-8B-v2.0" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` ## 🏆 Evaluation | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr| |-------------------------------|-------|------|-----:|--------|-----:|---|-----:| |stem |N/A |none | 0|acc |0.6466|± |0.0056| | | |none | 0|acc_norm|0.6124|± |0.0066| | - medmcqa |Yaml |none | 0|acc |0.6118|± |0.0075| | | |none | 0|acc_norm|0.6118|± |0.0075| | - medqa_4options |Yaml |none | 0|acc |0.6143|± |0.0136| | | |none | 0|acc_norm|0.6143|± |0.0136| | - anatomy (mmlu) | 0|none | 0|acc |0.7185|± |0.0389| | - clinical_knowledge (mmlu) | 0|none | 0|acc |0.7811|± |0.0254| | - college_biology (mmlu) | 0|none | 0|acc |0.8264|± |0.0317| | - college_medicine (mmlu) | 0|none | 0|acc |0.7110|± |0.0346| | - medical_genetics (mmlu) | 0|none | 0|acc |0.8300|± |0.0378| | - professional_medicine (mmlu)| 0|none | 0|acc |0.7868|± |0.0249| | - pubmedqa | 1|none | 0|acc |0.7420|± |0.0196| |Groups|Version|Filter|n-shot| Metric |Value | |Stderr| |------|-------|------|-----:|--------|-----:|---|-----:| |stem |N/A |none | 0|acc |0.6466|± |0.0056| | | |none | 0|acc_norm|0.6124|± |0.0066|

MCZK/Qwen2-7B-Instruct-GGUF

MCZK

"2024-06-07T16:44:22Z"

2,549

0

null

[ "gguf", "chat", "text-generation", "en", "license:apache-2.0", "region:us" ]

text-generation

"2024-06-06T22:23:31Z"

--- license: apache-2.0 language: - en pipeline_tag: text-generation tags: - chat --- Qwen様の [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) をGGUF形式に変換したものです。 K量子化モデルについてもiMatrix適用してあります。 iMatrixテキストはTFMC様の[c4_en_ja_imatrix.txt](https://huggingface.co/datasets/TFMC/imatrix-dataset-for-japanese-llm)を使用しています。