Datasets:
librarian-bots
/
model_cards_with_metadata_test

Dataset card Data Studio Files
xet
Community
1
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
kyujinpy/PlatYi-34B-200k-Q-FastChat
kyujinpy
"2024-03-04T12:10:26Z"
1,361
3
transformers
[ "transformers", "pytorch", "llama", "text-generation", "en", "dataset:garage-bAInd/Open-Platypus", "license:cc-by-nc-sa-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-08T16:36:20Z"
--- language: - en license: cc-by-nc-sa-4.0 library_name: transformers datasets: - garage-bAInd/Open-Platypus pipeline_tag: text-generation model-index: - name: PlatYi-34B-200k-Q-FastChat 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: 64.93 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat 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: 84.46 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat 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: 77.13 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat 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: 48.38 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat 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: 80.74 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat 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: 51.48 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-200k-Q-FastChat name: Open LLM Leaderboard --- # **PlatYi-34B-200k-Q-FastChat** <img src='./PlatYi.png' width=256> ## Model Details **Model Developers** Kyujin Han (kyujinpy) **Input** Models input text only. **Output** Models generate text only. **Model Architecture** PlatYi-34B-200k-Q-FastChat is an auto-regressive language model based on the Yi-34B transformer architecture. **Blog Link** Blog: [Coming soon...] Github: [Coming soon...] **Base Model** [01-ai/Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K) **Training Dataset** [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). **Notice** While training, I used QLoRA. `lora_r` values is 64. **Apply prompting** References by [FastChat](https://github.com/lm-sys/FastChat/blob/daa2b9abe20597ebf34dc5df164d450456610c74/fastchat/conversation.py#L198-L229). # **Model Benchmark** ## Open leaderboard - Follow up as [link](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | | --- | --- | --- | --- | --- | --- | --- | --- | | **PlatYi-34B-200k-Q-FastChat** | 67.85 | 64.93 | 84.46 | 77.13 | 48.38 | 80.74 | 51.48 | | PlatYi-34B-Llama-Q-FastChat | 68.31 | 66.31 | 85.25 | 78.37 | 53.62 | 82.16 | 44.35 | | [Yi-34B](https://huggingface.co/01-ai/Yi-34B) | 69.42 | 64.59 | 85.69 | 76.35 | 56.23 | 83.03 | 50.64 | # Implementation Code ```python ### KO-Platypus from transformers import AutoModelForCausalLM, AutoTokenizer import torch repo = "kyujinpy/PlatYi-34B-200k-Q-FastChat" OpenOrca = AutoModelForCausalLM.from_pretrained( repo, return_dict=True, torch_dtype=torch.float16, device_map='auto' ) OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo) ``` --- # [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_kyujinpy__PlatYi-34B-200k-Q-FastChat) | Metric |Value| |---------------------------------|----:| |Avg. |67.85| |AI2 Reasoning Challenge (25-Shot)|64.93| |HellaSwag (10-Shot) |84.46| |MMLU (5-Shot) |77.13| |TruthfulQA (0-shot) |48.38| |Winogrande (5-shot) |80.74| |GSM8k (5-shot) |51.48|
abhishek/hepu-o4zf-ravz-7-0
abhishek
"2023-12-13T06:57:31Z"
1,361
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "autotrain", "conversational", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-13T06:45:25Z"
--- tags: - autotrain - text-generation widget: - text: "I love AutoTrain because " license: other --- # Model Trained Using AutoTrain This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain). # Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_path = "PATH_TO_THIS_REPO" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() # Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) # Model response: "Hello! How can I assist you today?" print(response) ```
aqweteddy/mistral_tv-neural-marconroni
aqweteddy
"2024-03-23T10:55:42Z"
1,361
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "en", "arxiv:2310.04799", "license:mit", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-29T16:12:24Z"
--- language: - en license: mit model-index: - name: mistral_tv-neural-marconroni 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: 69.2 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aqweteddy/mistral_tv-neural-marconroni 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: 86.26 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aqweteddy/mistral_tv-neural-marconroni 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: 65.07 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aqweteddy/mistral_tv-neural-marconroni 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: 60.03 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aqweteddy/mistral_tv-neural-marconroni 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: 80.9 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aqweteddy/mistral_tv-neural-marconroni 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: 66.19 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=aqweteddy/mistral_tv-neural-marconroni name: Open LLM Leaderboard --- ## Chat Vector CHAT VECTOR: A SIMPLE APPROACH TO EQUIP LLMS WITH NEW LANGUAGE CHAT CAPABILITIES https://arxiv.org/pdf/2310.04799.pdf With the advancements in conversational AI, such as ChatGPT, this paper focuses on exploring developing Large Language Models (LLMs) for non-English languages, especially emphasizing alignment with human preferences. We introduce a computationally efficient method, leveraging “chat vector,” to synergize pre-existing knowledge and behaviors in LLMs, restructuring the conventional training paradigm from continual pretrain SFT RLHF to continual pretrain + chat. Our empirical studies, primarily focused on Traditional Chinese, employ LLaMA2 as the base model and acquire the chat vector by subtracting the pre-trained weights, LLaMA2, from the weights of LLaMA2-chat. Evaluating from three distinct facets, which are toxicity, ability of instruction following and multi-turn dialogue demonstrates the chat vector's superior efficacy in “chatting”. To confirm the adaptability of our approach, we extend our experiments to include models pre-trained in both Korean and Simplified Chinese, illustrating the versatility of our methodology. Overall, we present a significant solution in aligning LLMs with human preferences efficiently across various languages, accomplished by the chat vector. ## Merged LM * mistral 7b * chat vector * neural-chat * marconroni # [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_aqweteddy__mistral_tv-neural-marconroni) | Metric |Value| |---------------------------------|----:| |Avg. |71.27| |AI2 Reasoning Challenge (25-Shot)|69.20| |HellaSwag (10-Shot) |86.26| |MMLU (5-Shot) |65.07| |TruthfulQA (0-shot) |60.03| |Winogrande (5-shot) |80.90| |GSM8k (5-shot) |66.19|
Yash21/Mistral-Quantum-dpo
Yash21
"2024-01-10T07:04:12Z"
1,361
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-09T06:51:16Z"
--- tags: - merge license: apache-2.0 --- # Mistral-Quantum-dpo Mistral-Quantum-dpo is a merge of the following models * [quantumaikr/quantum-dpo-v0.1](https://huggingface.co/quantumaikr/quantum-dpo-v0.1) * [mncai/mistral-7b-dpo-v6](https://huggingface.co/mncai/mistral-7b-dpo-v6) ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Yash21/Mistral-Quantum-dpo" 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"]) ```
OpenBuddy/openbuddy-deepseek-10b-v17.1-4k
OpenBuddy
"2024-01-22T13:48:41Z"
1,361
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "zh", "en", "fr", "de", "ja", "ko", "it", "ru", "fi", "license:other", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-11T15:53:06Z"
--- language: - zh - en - fr - de - ja - ko - it - ru - fi pipeline_tag: text-generation inference: false library_name: transformers license: other license_name: deepseek license_link: https://github.com/deepseek-ai/DeepSeek-LLM/blob/548a39bdd03986297ea4e233a8b7676edd6bec3e/LICENSE-MODEL --- # OpenBuddy - Open Multilingual Chatbot GitHub and Usage Guide: [https://github.com/OpenBuddy/OpenBuddy](https://github.com/OpenBuddy/OpenBuddy) Website and Demo: [https://openbuddy.ai](https://openbuddy.ai) Evaluation result of this model: [Evaluation.txt](Evaluation.txt) ![Demo](https://raw.githubusercontent.com/OpenBuddy/OpenBuddy/main/media/demo.png) # Copyright Notice Base model: https://huggingface.co/deepseek-ai/deepseek-llm-7b-base License: [deepseek](https://github.com/deepseek-ai/DeepSeek-LLM/blob/548a39bdd03986297ea4e233a8b7676edd6bec3e/LICENSE-MODEL) ## Disclaimer All OpenBuddy models have inherent limitations and may potentially produce outputs that are erroneous, harmful, offensive, or otherwise undesirable. Users should not use these models in critical or high-stakes situations that may lead to personal injury, property damage, or significant losses. Examples of such scenarios include, but are not limited to, the medical field, controlling software and hardware systems that may cause harm, and making important financial or legal decisions. OpenBuddy is provided "as-is" without any warranty of any kind, either express or implied, including, but not limited to, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement. In no event shall the authors, contributors, or copyright holders be liable for any claim, damages, or other liabilities, 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. By using OpenBuddy, you agree to these terms and conditions, and acknowledge that you understand the potential risks associated with its use. You also agree to indemnify and hold harmless the authors, contributors, and copyright holders from any claims, damages, or liabilities arising from your use of OpenBuddy. ## 免责声明 所有OpenBuddy模型均存在固有的局限性，可能产生错误的、有害的、冒犯性的或其他不良的输出。用户在关键或高风险场景中应谨慎行事，不要使用这些模型，以免导致人身伤害、财产损失或重大损失。此类场景的例子包括但不限于医疗领域、可能导致伤害的软硬件系统的控制以及进行重要的财务或法律决策。 OpenBuddy按“原样”提供，不附带任何种类的明示或暗示的保证，包括但不限于适销性、特定目的的适用性和非侵权的暗示保证。在任何情况下，作者、贡献者或版权所有者均不对因软件或使用或其他软件交易而产生的任何索赔、损害赔偿或其他责任（无论是合同、侵权还是其他原因）承担责任。 使用OpenBuddy即表示您同意这些条款和条件，并承认您了解其使用可能带来的潜在风险。您还同意赔偿并使作者、贡献者和版权所有者免受因您使用OpenBuddy而产生的任何索赔、损害赔偿或责任的影响。
AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T
AkiGogikar
"2024-03-05T08:08:30Z"
1,361
0
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "merge", "mergekit", "lazymergekit", "ahxt/LiteLlama-460M-1T", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-12T06:49:32Z"
--- license: apache-2.0 tags: - moe - merge - mergekit - lazymergekit - ahxt/LiteLlama-460M-1T - ahxt/LiteLlama-460M-1T - ahxt/LiteLlama-460M-1T - ahxt/LiteLlama-460M-1T - ahxt/LiteLlama-460M-1T - ahxt/LiteLlama-460M-1T model-index: - name: KnowledgeNinja-LiteLlama-460Mx6MoE-1T 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: 25.17 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T 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: 38.45 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T 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: 26.16 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T 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: 41.57 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T 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: 50.04 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T 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: 0.0 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T name: Open LLM Leaderboard --- # KnowledgeNinja-LiteLlama-460Mx6MoE-1T KnowledgeNinja-LiteLlama-460Mx6MoE-1T is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) * [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) * [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) * [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) * [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) * [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) ## 🧩 Configuration ```yaml base_model: ahxt/LiteLlama-460M-1T gate_mode: hidden dtype: bfloat16 experts: - source_model: ahxt/LiteLlama-460M-1T positive_prompts: ["Accounting"] - source_model: ahxt/LiteLlama-460M-1T positive_prompts: ["Finance"] - source_model: ahxt/LiteLlama-460M-1T positive_prompts: ["Strategy"] - source_model: ahxt/LiteLlama-460M-1T positive_prompts: ["Marketing"] - source_model: ahxt/LiteLlama-460M-1T positive_prompts: ["Organizational Behaviour"] - source_model: ahxt/LiteLlama-460M-1T positive_prompts: ["Economics"] ``` ## 💻 Usage ```python !pip install -qU transformers bitsandbytes accelerate from transformers import AutoTokenizer import transformers import torch model = "AkiGogikar/KnowledgeNinja-LiteLlama-460Mx6MoE-1T" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True}, ) messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}] prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) 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_AkiGogikar__KnowledgeNinja-LiteLlama-460Mx6MoE-1T) | Metric |Value| |---------------------------------|----:| |Avg. |30.23| |AI2 Reasoning Challenge (25-Shot)|25.17| |HellaSwag (10-Shot) |38.45| |MMLU (5-Shot) |26.16| |TruthfulQA (0-shot) |41.57| |Winogrande (5-shot) |50.04| |GSM8k (5-shot) | 0.00|
macadeliccc/SOLAR-math-2x10.7b
macadeliccc
"2024-03-04T19:25:08Z"
1,361
0
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "conversational", "en", "arxiv:2312.15166", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-13T18:14:27Z"
--- language: - en license: apache-2.0 library_name: transformers model-index: - name: SOLAR-math-2x10.7b 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: 68.43 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-math-2x10.7b 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: 86.31 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-math-2x10.7b 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: 66.9 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-math-2x10.7b 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: 64.21 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-math-2x10.7b 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: 83.35 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-math-2x10.7b 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: 71.04 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SOLAR-math-2x10.7b name: Open LLM Leaderboard --- # 🌞🚀 SOLAR-math-2x10.7_19B + This model is part of MoE experimentation. The other solar models in the collection are available [here](https://huggingface.co/collections/macadeliccc/solar-moe-65a2d28e3581a68c41381d5b) + If you like this model, version 2 is even better! It is competitve with GPT-3.5 Turbo and Gemini Pro. It exceeds the scores of Mixtral8x7b [macadeliccc/SOLAR-math-2x10.7b-v0.2](https://huggingface.co/macadeliccc/SOLAR-math-2x10.7b-v0.2) ![solar](solar-2.png) ## 🌅 Code Example Example also available in [colab](https://colab.research.google.com/drive/10FWCLODU_EFclVOFOlxNYMmSiLilGMBZ?usp=sharing) ```python from transformers import AutoModelForCausalLM, AutoTokenizer def generate_response(prompt): """ Generate a response from the model based on the input prompt. Args: prompt (str): Prompt for the model. Returns: str: The generated response from the model. """ # Tokenize the input prompt inputs = tokenizer(prompt, return_tensors="pt") # Generate output tokens outputs = model.generate(**inputs, max_new_tokens=512, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id) # Decode the generated tokens to a string response = tokenizer.decode(outputs[0], skip_special_tokens=True) return response # Load the model and tokenizer model_id = "macadeliccc/SOLAR-math-2x10.7b" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True) prompt = "Explain the proof of Fermat's Last Theorem and its implications in number theory." print("Response:") print(generate_response(prompt), "\n") ``` ## Evaluations | Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average| |---------------------------------------------------------------------------|------:|------:|---------:|-------:|------:| |[SOLAR-math-2x10.7b](https://huggingface.co/macadeliccc/SOLAR-math-2x10.7b)| 47.2| 75.18| 64.73| 45.15| 58.07| ### AGIEval | Task |Version| Metric |Value| |Stderr| |------------------------------|------:|--------|----:|---|-----:| |agieval_aqua_rat | 0|acc |30.31|± | 2.89| | | |acc_norm|30.31|± | 2.89| |agieval_logiqa_en | 0|acc |43.78|± | 1.95| | | |acc_norm|43.93|± | 1.95| |agieval_lsat_ar | 0|acc |21.74|± | 2.73| | | |acc_norm|19.13|± | 2.60| |agieval_lsat_lr | 0|acc |57.25|± | 2.19| | | |acc_norm|56.47|± | 2.20| |agieval_lsat_rc | 0|acc |68.77|± | 2.83| | | |acc_norm|68.03|± | 2.85| |agieval_sat_en | 0|acc |78.16|± | 2.89| | | |acc_norm|79.13|± | 2.84| |agieval_sat_en_without_passage| 0|acc |47.57|± | 3.49| | | |acc_norm|44.66|± | 3.47| |agieval_sat_math | 0|acc |41.36|± | 3.33| | | |acc_norm|35.91|± | 3.24| Average: 47.2% ### GPT4All | Task |Version| Metric |Value| |Stderr| |-------------|------:|--------|----:|---|-----:| |arc_challenge| 0|acc |59.22|± | 1.44| | | |acc_norm|61.43|± | 1.42| |arc_easy | 0|acc |84.26|± | 0.75| | | |acc_norm|83.63|± | 0.76| |boolq | 1|acc |88.69|± | 0.55| |hellaswag | 0|acc |65.98|± | 0.47| | | |acc_norm|84.29|± | 0.36| |openbookqa | 0|acc |34.20|± | 2.12| | | |acc_norm|47.20|± | 2.23| |piqa | 0|acc |81.83|± | 0.90| | | |acc_norm|82.59|± | 0.88| |winogrande | 0|acc |78.45|± | 1.16| Average: 75.18% ### TruthfulQA | Task |Version|Metric|Value| |Stderr| |-------------|------:|------|----:|---|-----:| |truthfulqa_mc| 1|mc1 |48.47|± | 1.75| | | |mc2 |64.73|± | 1.53| Average: 64.73% ### Bigbench | Task |Version| Metric |Value| |Stderr| |------------------------------------------------|------:|---------------------|----:|---|-----:| |bigbench_causal_judgement | 0|multiple_choice_grade|61.05|± | 3.55| |bigbench_date_understanding | 0|multiple_choice_grade|68.56|± | 2.42| |bigbench_disambiguation_qa | 0|multiple_choice_grade|35.27|± | 2.98| |bigbench_geometric_shapes | 0|multiple_choice_grade|31.20|± | 2.45| | | |exact_str_match | 0.00|± | 0.00| |bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|30.00|± | 2.05| |bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|23.43|± | 1.60| |bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|46.00|± | 2.88| |bigbench_movie_recommendation | 0|multiple_choice_grade|35.60|± | 2.14| |bigbench_navigate | 0|multiple_choice_grade|57.50|± | 1.56| |bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|55.80|± | 1.11| |bigbench_ruin_names | 0|multiple_choice_grade|45.98|± | 2.36| |bigbench_salient_translation_error_detection | 0|multiple_choice_grade|40.58|± | 1.56| |bigbench_snarks | 0|multiple_choice_grade|66.85|± | 3.51| |bigbench_sports_understanding | 0|multiple_choice_grade|71.40|± | 1.44| |bigbench_temporal_sequences | 0|multiple_choice_grade|56.40|± | 1.57| |bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|24.00|± | 1.21| |bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|17.09|± | 0.90| |bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|46.00|± | 2.88| Average: 45.15% Average score: 58.07% Elapsed time: 04:05:27 ### 📚 Citations ```bibtex @misc{kim2023solar, title={SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling}, author={Dahyun Kim and Chanjun Park and Sanghoon Kim and Wonsung Lee and Wonho Song and Yunsu Kim and Hyeonwoo Kim and Yungi Kim and Hyeonju Lee and Jihoo Kim and Changbae Ahn and Seonghoon Yang and Sukyung Lee and Hyunbyung Park and Gyoungjin Gim and Mikyoung Cha and Hwalsuk Lee and Sunghun Kim}, year={2023}, eprint={2312.15166}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` # [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_macadeliccc__SOLAR-math-2x10.7b) | Metric |Value| |---------------------------------|----:| |Avg. |73.37| |AI2 Reasoning Challenge (25-Shot)|68.43| |HellaSwag (10-Shot) |86.31| |MMLU (5-Shot) |66.90| |TruthfulQA (0-shot) |64.21| |Winogrande (5-shot) |83.35| |GSM8k (5-shot) |71.04|
FreedomIntelligence/AceGPT-v1.5-13B
FreedomIntelligence
"2024-04-18T06:43:00Z"
1,361
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "ar", "zh", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-04-14T16:08:42Z"
--- license: apache-2.0 language: - ar - zh - en --- # <b>AceGPT</b> AceGPT is a fully fine-tuned generative text model collection based on LlaMA2, particularly in the Arabic language domain. This is the repository for the version 1.5 of 13B pre-trained model. --- ## Model Details We have released the AceGPT family of large language models, which is a collection of fully fine-tuned generative text models based on LlaMA2, ranging from 7B to 13B parameters. Our models include two main categories: AceGPT and AceGPT-chat. AceGPT-chat is an optimized version specifically designed for dialogue applications. It is worth mentioning that our models have demonstrated superior performance compared to all currently available open-source Arabic dialogue models in multiple benchmark tests. Furthermore, in our human evaluations, our models have shown comparable satisfaction levels to some closed-source models, such as ChatGPT, in the Arabic language. ## Model Developers We are from the King Abdullah University of Science and Technology (KAUST), the Chinese University of Hong Kong, Shenzhen (CUHKSZ), the Shenzhen Research Institute of Big Data (SRIBD), and King AbdulAziz University (KAU). ## Variations AceGPT families come in a range of parameter sizes —— 7B and 13B, each size of model has a base category and a -chat category. ## Paper The paper can be accessed at [link](https://huggingface.co/FreedomIntelligence/AceGPT-v1.5-13B-Chat/blob/main/Second_Language_(Arabic)_Acquisition_of_LLMs_via_Progressive_Vocabulary_Expansion.pdf). ## Input Models input text only. ## Output Models output text only. ## Model Evaluation Results Benchmark evaluation on [Arabic MMLU](https://github.com/FreedomIntelligence/AceGPT) are conducted using accuracy scores as metrics, following the evaluation framework available at https://github.com/FreedomIntelligence/AceGPT/tree/main. | | STEM | Humanities | Social Sciences | Others | Average | |------------------|------|------|------|------|------| | Bloomz-7B-base | 33.35 | 29.29 | 37.58 | 34.53 | 33.69 | | LLaMA2-7B-base | 30.30 | 29.33 | 27.46 | 30.78 | 29.37 | | AceGPT-7B-base | 29.73 | 30.95 | 33.45 | 34.42 | 32.14 | | AceGPT-v1.5-7B-base | 33.03 | 32.08 | 35.39 | 35.59 | 34.03 | | LLaMA2-13B-base | 32.94 | 32.30 | 33.42 | 37.27 | 33.76 | | Jais-13B-base | 30.51 | 31.25 | 33.74 | 33.42 | 33.76 | | AceGPT-13B-base | 36.60 | 38.74 | 43.76 | <u>42.72</u> | 40.45 | | AceGPT-v1.5-13B-base | <u>36.13</u> | <u>40.07</u> | <u>45.43</u> | 42.17 | <u>40.95</u> | | Jais-30B-v1-base | 32.67 | 30.67 | 42.13 | 39.60 | 36.27 | | ChatGPT 3.5 Turbo | **43.38** | **44.12** | **55.57** | **53.21** | **49.07** | Benchmark evaluation on [ArabicMMLU]((https://github.com/mbzuai-nlp/ArabicMMLU)), and assessed based on its source settings. | | STEM | Social Sciences | Humanities | Arabic Language | Other | Average | |------------------|------|------|------|------|------|------| | Bloomz-7B-base | - | - | - | - | - | - | | LLaMA2-7B-base | 33.7 | 32.8 | 33.5 | 28.4 | 36.7 | 33.4 | | AceGPT-7B-base | 35.4 | 35.9 | 36.2 | 31.1 | 41.7 | 36.3 | | AceGPT-v1.5-7B-base | 36.7 | 36.5 | 34.1 | 30.0 | 41.2 | 37.0 | | LLaMA2-13B-base | 32.9 | 35.0 | 37.8 | 35.8 | 39.3 | 36.1 | | Jais-13B-base | 30.3 | 31.4 | 33.6 | 28.1 | 36.3 | 32.2 | | AceGPT-13B-base | <u>42.7</u> | 45.5 | 48.3 | 42.4 | 50.7 | 46.1 | | AceGPT-v1.5-13B-base | 42.4 | <u>45.7</u> | 48.4 | <u>46.3</u> | <u>52.5</u> | <u>47.6</u> | | Jais-30B-v1-base | 39.5 | 45.6 | <u>50.5</u> | 34.6 | 49.1 | 44.8 | | ChatGPT 3.5 Turbo | **53.8** | **57.0** | **57.5** | **57.6** | **63.8** | **57.7** | ## Samples #### Sample1(abstract_algebra) * <b>input:</b> "فيما يلي أسئلة الاختيار من متعدد (مع الإجابات) حول جبر تجريدي\n\nسؤال: العثور على جميع قيم c في Z_3 بحيث يكون Z_3 [x]/(x^2+c) حقلًا.\nA. 0\nB. 1\nC. 2\nD. 3\nإجابة: B\n\nسؤال: البيان رقم 1 | إذا كان aH عنصرًا في مجموعة العوامل ، فإن | aH | يقسم | a |. البيان رقم 2 | إذا كانت H و K مجموعات فرعية لـ G ، فإن HK مجموعة فرعية لـ G.\nA. صحيح ، صحيح\nB. خطأ ، خطأ\nC. صحيح ، خطأ\nD. خطأ ، صحيح\nإجابة: B\n\nسؤال: العبارة 1 | كل عنصر من مجموعة يولد مجموعة دورية من المجموعة. العبارة 2 | المجموعة المتناظرة S_10 لديها 10 عناصر.\nA. صحيح، صحيح\nB. خطأ، خطأ\nC. صحيح، خطأ\nD. خطأ، صحيح\nإجابة: C\n\nسؤال: البيان 1| كل وظيفة من مجموعة محدودة على نفسها يجب أن تكون واحدة لكل مجموعة. البيان 2 | كل فرع فرعي لمجموعة أبيلية هو أبيلي.\nA. صحيح, صحيح\nB. خاطئ, خاطئ\nC. صحيح, خاطئ\nD. خاطئ, صحيح\nإجابة: A\n\nسؤال: اعثر على خاصية الحلقة 2Z.\nA. 0\nB. 3\nC. 12\nD. 30\nإجابة: A\n\nسؤال: ما هو الدرجة للامتداد الميداني الناتج من Q(sqrt(2), sqrt(3), sqrt(18)) على Q؟\nA. 0\nB. 4\nC. 2\nD. 6\nإجابة:" * <b>output:</b> "B\n\nسؤال: ما هو عدد العناصر" #### Sample2(business_ethics) * <b>input:</b> "فيما يلي أسئلة الاختيار من متعدد (مع الإجابات) حول أخلاقيات الأعمال\n\nسؤال: ما هي الحجج الأخلاقية المتعلقة بالمسؤولية الاجتماعية للشركات؟\nA. التكاليف الخارجية، القوة، الاستقلالية\nB. الإعلام، الموارد الضعيفة، التبادل التعاوني\nC. الإعلام، القوة، الاستقلالية\nD. التكاليف الخارجية، القوة، التبادل التعاوني\nإجابة: D\n\nسؤال: _______ هو المحاولة المباشرة لإدارة القضايا الأخلاقية أو المشاكل، سواء بشكل رسمي أو غير رسمي، من خلال سياسات وممارسات وبرامج محددة.\nA. المسؤولية الاجتماعية للشركات\nB. إدارة الأخلاقيات العملية\nC. الاستدامة\nD. إدارة البيئة\nإجابة: B\n\nسؤال: لضمان استقلال أعضاء مجلس الإدارة غير التنفيذية ، هناك عدد من الخطوات التي يمكن اتخاذها ، والتي تشمل اختيار الغير التنفيذيين من _______ الشركة ، وتعيينهم لمدة _________ ، وكذلك تعيينهم _________.\nA. خارج الشركة ، محدودة ، بشكل مستقل\nB. من الداخل ، محدودة ، بشكل متقطع\nC. خارج الشركة ، غير محدودة ، بشكل متقطع\nD. من الداخل ، غير محدودة ، بشكل مستقل\nإجابة: A\n\nسؤال: ما هي الأساليب التي يمكن للمدير الأمني الذي يسعى لتحقيق أهدافه الاختيار بينها؟\nA. العمل المباشر الغير عنيف ، العمل المباشر العنيف ، العمل غير المباشر ، الحملة الدعائية\nB. العمل غير المباشر ، العمل الأوتيل ، العمل المباشر الغير عنيف ، الحملة الإعلامية\nC. العمل غير المباشر ، العمل المباشر العنيف ، العمل المباشر غير العنيف المباشر ، الحملة الدعائية\nD. العمل المباشر الغير عنيف ، العمل الأوتيل ، العمل غير المباشر ، الحملة الإعلامية\nإجابة: C\n\nسؤال: على عكس _______ ، تهدف _______ إلى مكافأة السلوك الإيجابي للشركات. تم تعزيز نجاح مثل هذه الحملات من خلال استخدام ___________, الذي يتيح للحملات تيسير تحقيق الشركة لــ _________ .\nA. الحملات الاستهلاكية، الحملات الاستهلاكية العامة، تكنولوجيا سلسلة الكتل، التبرعات الخيرية\nB. الحملات التحفيزية، الحملات الاستهلاكية العامة، التكنولوجيا الرقمية، زيادة المبيعات\nC. الحملات الاستهلاكية، الحملات الشرائية، تكنولوجيا سلسلة الكتل، التبرعات الخيرية\nD. المقاطعات، الحملات التحفيزية، الحملات الرقمية، زيادة المبيعات\nإجابة: D\n\nسؤال: تُصبح _______ مثل البيتكوين أكثر انتشارًا وتحمل مجموعة كبيرة من الآثار الأخلاقية المرتبطة بها، على سبيل المثال، إنها _______ وأكثر _______. ومع ذلك، تم استخدامها أيضًا للمشاركة في _______.\nA. العملات الرقمية، مكلفة، آمنة، جرائم مالية\nB. العملات التقليدية، رخيصة، غير آمنة، العطاء الخيري\nC. العملات الرقمية، رخيصة، آمنة، جرائم مالية\nD. العملات التقليدية، مكلفة، غير آمنة، العطاء الخيري\nإجابة:" * <b>output:</b> "A\n\nسؤال: _______ هو" # Reference ``` @article{zhu2024second, title={Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion}, author={Zhu, Jianqing and Huang, Huang and Lin, Zhihang and Liang, Juhao and Tang, Zhengyang and Almubarak, Khalid and Alharthi, Mosen and An, Bang and He, Juncai and Wu, Xiangbo and Yu, Fei and Chen, Junying and Ma, Zhuoheng and Du, Yuhao and Hu, Yan and Zhang, He and Alghamdi, Emad A. and Zhang, Lian and Sun, Ruoyu and Li, Haizhou and Wang, Benyou and Xu, Jinchao}, journal={}, year={2024} } ```
mradermacher/Hare-1.1B-Chat-GGUF
mradermacher
"2024-06-06T21:47:38Z"
1,361
0
transformers
[ "transformers", "gguf", "en", "base_model:LiteAI/Hare-1.1B-Chat", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
"2024-06-06T20:53:06Z"
--- base_model: LiteAI/Hare-1.1B-Chat 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/LiteAI/Hare-1.1B-Chat <!-- 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/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q2_K.gguf) | Q2_K | 0.5 | | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.IQ3_XS.gguf) | IQ3_XS | 0.6 | | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q3_K_S.gguf) | Q3_K_S | 0.6 | | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.IQ3_S.gguf) | IQ3_S | 0.6 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.IQ3_M.gguf) | IQ3_M | 0.6 | | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q3_K_L.gguf) | Q3_K_L | 0.7 | | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.IQ4_XS.gguf) | IQ4_XS | 0.7 | | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q5_K_S.gguf) | Q5_K_S | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q5_K_M.gguf) | Q5_K_M | 0.9 | | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q6_K.gguf) | Q6_K | 1.0 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Hare-1.1B-Chat-GGUF/resolve/main/Hare-1.1B-Chat.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 -->
sentence-transformers/bert-base-wikipedia-sections-mean-tokens
sentence-transformers
"2024-03-27T09:59:39Z"
1,360
0
sentence-transformers
[ "sentence-transformers", "pytorch", "tf", "safetensors", "bert", "feature-extraction", "sentence-similarity", "transformers", "arxiv:1908.10084", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-embeddings-inference", "region:us" ]
sentence-similarity
"2022-03-02T23:29:05Z"
--- license: apache-2.0 library_name: sentence-transformers tags: - sentence-transformers - feature-extraction - sentence-similarity - transformers pipeline_tag: sentence-similarity --- **⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)** # sentence-transformers/bert-base-wikipedia-sections-mean-tokens This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. ## 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 SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('sentence-transformers/bert-base-wikipedia-sections-mean-tokens') embeddings = model.encode(sentences) print(embeddings) ``` ## 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 from transformers import AutoTokenizer, AutoModel import torch #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings 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 we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-base-wikipedia-sections-mean-tokens') model = AutoModel.from_pretrained('sentence-transformers/bert-base-wikipedia-sections-mean-tokens') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, max pooling. sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` ## Evaluation Results For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/bert-base-wikipedia-sections-mean-tokens) ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False}) ) ``` ## Citing & Authors This model was trained by [sentence-transformers](https://www.sbert.net/). If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084): ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "http://arxiv.org/abs/1908.10084", } ```
timm/resnet50.a1h_in1k
timm
"2024-02-10T23:39:04Z"
1,360
0
timm
[ "timm", "pytorch", "safetensors", "image-classification", "arxiv:2110.00476", "arxiv:1512.03385", "license:apache-2.0", "region:us" ]
image-classification
"2023-04-05T18:08:17Z"
--- license: apache-2.0 library_name: timm tags: - image-classification - timm --- # Model card for resnet50.a1h_in1k A ResNet-B image classification model. This model features: * ReLU activations * single layer 7x7 convolution with pooling * 1x1 convolution shortcut downsample Trained on ImageNet-1k in `timm` using recipe template described below. Recipe details: * Based on [ResNet Strikes Back](https://arxiv.org/abs/2110.00476) `A1` recipe * LAMB optimizer * Stronger dropout, stochastic depth, and RandAugment than paper `A1` recipe * Cosine LR schedule with warmup ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 25.6 - GMACs: 2.6 - Activations (M): 6.9 - Image size: train = 176 x 176, test = 224 x 224 - **Papers:** - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 - **Original:** https://github.com/huggingface/pytorch-image-models ## 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('resnet50.a1h_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( 'resnet50.a1h_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, 64, 88, 88]) # torch.Size([1, 256, 44, 44]) # torch.Size([1, 512, 22, 22]) # torch.Size([1, 1024, 11, 11]) # torch.Size([1, 2048, 6, 6]) 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( 'resnet50.a1h_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, 2048, 6, 6) 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). |model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec| |------------------------------------------|--------|-----|-----|-----------|-----|-----|-------| |[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|320 |86.72|98.17|93.6 |35.2 |69.7 |451 | |[seresnextaa101d_32x8d.sw_in12k_ft_in1k_288](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288)|288 |86.51|98.08|93.6 |28.5 |56.4 |560 | |[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|288 |86.49|98.03|93.6 |28.5 |56.4 |557 | |[seresnextaa101d_32x8d.sw_in12k_ft_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k)|224 |85.96|97.82|93.6 |17.2 |34.2 |923 | |[resnext101_32x32d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k)|224 |85.11|97.44|468.5 |87.3 |91.1 |254 | |[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|416 |85.0 |97.12|191.9 |108.4|213.8|134 | |[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|352 |84.96|97.22|102.1 |50.2 |101.2|291 | |[ecaresnet269d.ra2_in1k](https://huggingface.co/timm/ecaresnet269d.ra2_in1k)|320 |84.73|97.18|102.1 |41.5 |83.7 |353 | |[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|384 |84.71|96.99|164.0 |77.6 |154.7|183 | |[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|288 |84.57|97.08|93.6 |28.5 |56.4 |557 | |[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|320 |84.45|97.08|93.2 |31.5 |67.8 |446 | |[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|352 |84.43|96.97|129.9 |51.1 |105.5|280 | |[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|288 |84.36|96.92|93.6 |27.6 |53.0 |595 | |[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|320 |84.35|97.04|66.8 |24.1 |47.7 |610 | |[resnetrs350.tf_in1k](https://huggingface.co/timm/resnetrs350.tf_in1k)|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 | |[resnext101_32x8d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k)|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 | |[resnetrs420.tf_in1k](https://huggingface.co/timm/resnetrs420.tf_in1k)|320 |84.24|96.86|191.9 |64.2 |126.6|228 | |[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|288 |84.19|96.87|93.6 |27.2 |51.6 |613 | |[resnext101_32x16d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k)|224 |84.18|97.19|194.0 |36.3 |51.2 |581 | |[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 | |[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|320 |83.97|96.82|64.7 |31.2 |67.3 |518 | |[resnetrs200.tf_in1k](https://huggingface.co/timm/resnetrs200.tf_in1k)|256 |83.87|96.75|93.2 |20.2 |43.4 |692 | |[seresnextaa101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k)|224 |83.86|96.65|93.6 |17.2 |34.2 |923 | |[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|320 |83.72|96.61|86.6 |24.3 |48.1 |617 | |[seresnet152d.ra2_in1k](https://huggingface.co/timm/seresnet152d.ra2_in1k)|256 |83.69|96.78|66.8 |15.4 |30.6 |943 | |[seresnext101d_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k)|224 |83.68|96.61|93.6 |16.7 |32.0 |986 | |[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|320 |83.67|96.74|60.2 |24.1 |47.7 |706 | |[resnetrs270.tf_in1k](https://huggingface.co/timm/resnetrs270.tf_in1k)|256 |83.59|96.61|129.9 |27.1 |55.8 |526 | |[seresnext101_32x8d.ah_in1k](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k)|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 | |[resnetaa101d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k)|224 |83.54|96.83|44.6 |9.1 |17.6 |1864 | |[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|288 |83.46|96.54|60.2 |19.1 |37.3 |904 | |[resnext101_32x16d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k)|224 |83.35|96.85|194.0 |36.3 |51.2 |582 | |[resnet200d.ra2_in1k](https://huggingface.co/timm/resnet200d.ra2_in1k)|256 |83.23|96.53|64.7 |20.0 |43.1 |809 | |[resnext101_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k)|224 |83.22|96.75|44.2 |8.0 |21.2 |1814 | |[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|288 |83.16|96.38|83.5 |25.7 |51.6 |590 | |[resnet152d.ra2_in1k](https://huggingface.co/timm/resnet152d.ra2_in1k)|256 |83.14|96.38|60.2 |15.4 |30.5 |1096 | |[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|320 |83.02|96.45|44.6 |16.5 |34.8 |992 | |[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|288 |82.98|96.54|44.6 |13.4 |28.2 |1077 | |[resnext101_64x4d.tv_in1k](https://huggingface.co/timm/resnext101_64x4d.tv_in1k)|224 |82.98|96.25|83.5 |15.5 |31.2 |989 | |[resnetrs152.tf_in1k](https://huggingface.co/timm/resnetrs152.tf_in1k)|256 |82.86|96.28|86.6 |15.6 |30.8 |951 | |[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|224 |82.83|96.22|88.8 |16.5 |31.2 |1099 | |[resnet152.a1h_in1k](https://huggingface.co/timm/resnet152.a1h_in1k)|224 |82.8 |96.13|60.2 |11.6 |22.6 |1486 | |[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|288 |82.8 |96.32|44.6 |13.0 |26.8 |1291 | |[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|288 |82.74|95.71|60.2 |19.1 |37.3 |905 | |[resnext101_32x8d.fb_wsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k)|224 |82.69|96.63|88.8 |16.5 |31.2 |1100 | |[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|288 |82.62|95.75|60.2 |19.1 |37.3 |904 | |[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|288 |82.61|96.49|25.6 |8.9 |20.6 |1729 | |[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|288 |82.53|96.13|36.8 |9.9 |21.5 |1773 | |[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|224 |82.5 |96.02|126.9 |22.8 |21.2 |1078 | |[resnext101_64x4d.c1_in1k](https://huggingface.co/timm/resnext101_64x4d.c1_in1k)|224 |82.46|95.92|83.5 |15.5 |31.2 |987 | |[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|288 |82.36|96.18|35.7 |8.1 |20.9 |1964 | |[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|320 |82.35|96.14|25.6 |8.8 |24.1 |1386 | |[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|288 |82.31|95.63|44.6 |13.0 |26.8 |1291 | |[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|288 |82.29|96.01|63.6 |13.6 |28.5 |1078 | |[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|224 |82.29|96.0 |60.2 |11.6 |22.6 |1484 | |[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|288 |82.27|96.06|68.9 |18.9 |23.8 |1176 | |[resnet101d.ra2_in1k](https://huggingface.co/timm/resnet101d.ra2_in1k)|256 |82.26|96.07|44.6 |10.6 |22.2 |1542 | |[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|288 |82.24|95.73|44.6 |13.0 |26.8 |1290 | |[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|288 |82.2 |96.14|27.6 |7.0 |23.8 |1547 | |[ecaresnet101d.miil_in1k](https://huggingface.co/timm/ecaresnet101d.miil_in1k)|224 |82.18|96.05|44.6 |8.1 |17.1 |1771 | |[resnext50_32x4d.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k)|224 |82.17|96.22|25.0 |4.3 |14.4 |2943 | |[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|288 |82.12|95.65|25.6 |7.1 |19.6 |1704 | |[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|288 |82.03|95.94|25.0 |7.0 |23.8 |1745 | |[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|288 |82.0 |96.15|24.9 |5.8 |12.7 |1787 | |[resnet61q.ra2_in1k](https://huggingface.co/timm/resnet61q.ra2_in1k)|256 |81.99|95.85|36.8 |7.8 |17.0 |2230 | |[resnext101_32x8d.tv2_in1k](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k)|176 |81.98|95.72|88.8 |10.3 |19.4 |1768 | |[resnet152.a1_in1k](https://huggingface.co/timm/resnet152.a1_in1k)|224 |81.97|95.24|60.2 |11.6 |22.6 |1486 | |[resnet101.a1h_in1k](https://huggingface.co/timm/resnet101.a1h_in1k)|224 |81.93|95.75|44.6 |7.8 |16.2 |2122 | |[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|224 |81.9 |95.77|44.6 |7.8 |16.2 |2118 | |[resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k)|224 |81.84|96.1 |194.0 |36.3 |51.2 |583 | |[resnet51q.ra2_in1k](https://huggingface.co/timm/resnet51q.ra2_in1k)|256 |81.78|95.94|35.7 |6.4 |16.6 |2471 | |[resnet152.a2_in1k](https://huggingface.co/timm/resnet152.a2_in1k)|224 |81.77|95.22|60.2 |11.6 |22.6 |1485 | |[resnetaa50d.sw_in12k_ft_in1k](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k)|224 |81.74|96.06|25.6 |5.4 |12.4 |2813 | |[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|288 |81.65|95.54|25.6 |7.1 |19.6 |1703 | |[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|288 |81.64|95.88|25.6 |7.2 |19.7 |1694 | |[resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k)|224 |81.62|96.04|88.8 |16.5 |31.2 |1101 | |[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|224 |81.61|95.76|68.9 |11.4 |14.4 |1930 | |[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|288 |81.61|95.83|25.6 |8.5 |19.2 |1868 | |[resnet101.a1_in1k](https://huggingface.co/timm/resnet101.a1_in1k)|224 |81.5 |95.16|44.6 |7.8 |16.2 |2125 | |[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|288 |81.48|95.16|25.0 |7.0 |23.8 |1745 | |[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|288 |81.47|95.71|25.9 |6.9 |18.6 |2071 | |[wide_resnet50_2.racm_in1k](https://huggingface.co/timm/wide_resnet50_2.racm_in1k)|224 |81.45|95.53|68.9 |11.4 |14.4 |1929 | |[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|288 |81.44|95.22|25.6 |7.2 |19.7 |1908 | |[ecaresnet50t.ra2_in1k](https://huggingface.co/timm/ecaresnet50t.ra2_in1k)|256 |81.44|95.67|25.6 |5.6 |15.4 |2168 | |[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|288 |81.4 |95.82|30.2 |6.8 |13.9 |2132 | |[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|288 |81.37|95.74|25.6 |7.2 |19.7 |1910 | |[resnet101.a2_in1k](https://huggingface.co/timm/resnet101.a2_in1k)|224 |81.32|95.19|44.6 |7.8 |16.2 |2125 | |[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|288 |81.3 |95.65|28.1 |6.8 |18.4 |1803 | |[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|288 |81.3 |95.11|25.0 |7.0 |23.8 |1746 | |[seresnext50_32x4d.racm_in1k](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k)|224 |81.27|95.62|27.6 |4.3 |14.4 |2591 | |[ecaresnet50t.a1_in1k](https://huggingface.co/timm/ecaresnet50t.a1_in1k)|224 |81.26|95.16|25.6 |4.3 |11.8 |2823 | |[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|288 |81.23|95.54|15.7 |4.8 |19.6 |2117 | |[senet154.gluon_in1k](https://huggingface.co/timm/senet154.gluon_in1k)|224 |81.23|95.35|115.1 |20.8 |38.7 |545 | |[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|288 |81.22|95.11|25.6 |6.8 |18.4 |2089 | |[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|288 |81.22|95.63|25.6 |6.8 |18.4 |676 | |[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|288 |81.18|95.09|25.6 |7.2 |19.7 |1908 | |[resnet50.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k)|224 |81.18|95.98|25.6 |4.1 |11.1 |3455 | |[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|224 |81.17|95.34|25.0 |4.3 |14.4 |2933 | |[resnext50_32x4d.a1h_in1k](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k)|224 |81.1 |95.33|25.0 |4.3 |14.4 |2934 | |[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|288 |81.1 |95.23|28.1 |6.8 |18.4 |1801 | |[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|288 |81.1 |95.12|28.1 |6.8 |18.4 |1799 | |[resnet152s.gluon_in1k](https://huggingface.co/timm/resnet152s.gluon_in1k)|224 |81.02|95.41|60.3 |12.9 |25.0 |1347 | |[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|288 |80.97|95.44|25.6 |6.8 |18.4 |2085 | |[gcresnet50t.ra2_in1k](https://huggingface.co/timm/gcresnet50t.ra2_in1k)|256 |80.94|95.45|25.9 |5.4 |14.7 |2571 | |[resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.93|95.73|44.2 |8.0 |21.2 |1814 | |[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|288 |80.91|95.55|25.6 |6.8 |18.4 |2084 | |[seresnext101_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k)|224 |80.9 |95.31|49.0 |8.0 |21.3 |1585 | |[seresnext101_64x4d.gluon_in1k](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k)|224 |80.9 |95.3 |88.2 |15.5 |31.2 |918 | |[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|288 |80.86|95.52|25.6 |6.8 |18.4 |2085 | |[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|224 |80.85|95.43|25.6 |4.1 |11.1 |3450 | |[ecaresnet50t.a2_in1k](https://huggingface.co/timm/ecaresnet50t.a2_in1k)|224 |80.84|95.02|25.6 |4.3 |11.8 |2821 | |[ecaresnet101d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k)|224 |80.79|95.62|24.9 |3.5 |7.7 |2961 | |[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|288 |80.79|95.36|19.8 |6.0 |14.8 |2506 | |[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|288 |80.79|95.58|19.9 |4.2 |10.6 |2349 | |[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|288 |80.78|94.99|25.6 |6.8 |18.4 |2088 | |[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|288 |80.71|95.43|25.6 |6.8 |18.4 |2087 | |[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|288 |80.7 |95.39|25.0 |7.0 |23.8 |1749 | |[resnetrs101.tf_in1k](https://huggingface.co/timm/resnetrs101.tf_in1k)|192 |80.69|95.24|63.6 |6.0 |12.7 |2270 | |[resnet50d.a1_in1k](https://huggingface.co/timm/resnet50d.a1_in1k)|224 |80.68|94.71|25.6 |4.4 |11.9 |3162 | |[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|288 |80.68|95.36|19.7 |6.0 |14.8 |2637 | |[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|224 |80.67|95.3 |25.6 |4.1 |11.1 |3452 | |[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|288 |80.67|95.42|25.0 |7.4 |25.1 |1626 | |[resnetaa50.a1h_in1k](https://huggingface.co/timm/resnetaa50.a1h_in1k)|224 |80.63|95.21|25.6 |5.2 |11.6 |3034 | |[ecaresnet50d.miil_in1k](https://huggingface.co/timm/ecaresnet50d.miil_in1k)|224 |80.61|95.32|25.6 |4.4 |11.9 |2813 | |[resnext101_64x4d.gluon_in1k](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k)|224 |80.61|94.99|83.5 |15.5 |31.2 |989 | |[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|288 |80.6 |95.31|19.9 |6.0 |14.8 |2578 | |[gcresnext50ts.ch_in1k](https://huggingface.co/timm/gcresnext50ts.ch_in1k)|256 |80.57|95.17|15.7 |3.8 |15.5 |2710 | |[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|224 |80.56|95.0 |60.2 |11.6 |22.6 |1483 | |[resnet50d.ra2_in1k](https://huggingface.co/timm/resnet50d.ra2_in1k)|224 |80.53|95.16|25.6 |4.4 |11.9 |3164 | |[resnext50_32x4d.a1_in1k](https://huggingface.co/timm/resnext50_32x4d.a1_in1k)|224 |80.53|94.46|25.0 |4.3 |14.4 |2930 | |[wide_resnet101_2.tv2_in1k](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k)|176 |80.48|94.98|126.9 |14.3 |13.2 |1719 | |[resnet152d.gluon_in1k](https://huggingface.co/timm/resnet152d.gluon_in1k)|224 |80.47|95.2 |60.2 |11.8 |23.4 |1428 | |[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|288 |80.45|95.32|25.6 |6.8 |18.4 |2086 | |[ecaresnetlight.miil_in1k](https://huggingface.co/timm/ecaresnetlight.miil_in1k)|224 |80.45|95.24|30.2 |4.1 |8.4 |3530 | |[resnext50_32x4d.a2_in1k](https://huggingface.co/timm/resnext50_32x4d.a2_in1k)|224 |80.45|94.63|25.0 |4.3 |14.4 |2936 | |[wide_resnet50_2.tv2_in1k](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k)|176 |80.43|95.09|68.9 |7.3 |9.0 |3015 | |[resnet101d.gluon_in1k](https://huggingface.co/timm/resnet101d.gluon_in1k)|224 |80.42|95.01|44.6 |8.1 |17.0 |2007 | |[resnet50.a1_in1k](https://huggingface.co/timm/resnet50.a1_in1k)|224 |80.38|94.6 |25.6 |4.1 |11.1 |3461 | |[seresnet33ts.ra2_in1k](https://huggingface.co/timm/seresnet33ts.ra2_in1k)|256 |80.36|95.1 |19.8 |4.8 |11.7 |3267 | |[resnext101_32x4d.gluon_in1k](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k)|224 |80.34|94.93|44.2 |8.0 |21.2 |1814 | |[resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k)|224 |80.32|95.4 |25.0 |4.3 |14.4 |2941 | |[resnet101s.gluon_in1k](https://huggingface.co/timm/resnet101s.gluon_in1k)|224 |80.28|95.16|44.7 |9.2 |18.6 |1851 | |[seresnet50.ra2_in1k](https://huggingface.co/timm/seresnet50.ra2_in1k)|224 |80.26|95.08|28.1 |4.1 |11.1 |2972 | |[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|288 |80.24|95.24|25.6 |8.5 |19.9 |1523 | |[resnet50d.a2_in1k](https://huggingface.co/timm/resnet50d.a2_in1k)|224 |80.22|94.63|25.6 |4.4 |11.9 |3162 | |[resnet152.tv2_in1k](https://huggingface.co/timm/resnet152.tv2_in1k)|176 |80.2 |94.64|60.2 |7.2 |14.0 |2346 | |[seresnet50.a2_in1k](https://huggingface.co/timm/seresnet50.a2_in1k)|224 |80.08|94.74|28.1 |4.1 |11.1 |2969 | |[eca_resnet33ts.ra2_in1k](https://huggingface.co/timm/eca_resnet33ts.ra2_in1k)|256 |80.08|94.97|19.7 |4.8 |11.7 |3284 | |[gcresnet33ts.ra2_in1k](https://huggingface.co/timm/gcresnet33ts.ra2_in1k)|256 |80.06|94.99|19.9 |4.8 |11.7 |3216 | |[resnet50_gn.a1h_in1k](https://huggingface.co/timm/resnet50_gn.a1h_in1k)|224 |80.06|94.95|25.6 |4.1 |11.1 |1109 | |[seresnet50.a1_in1k](https://huggingface.co/timm/seresnet50.a1_in1k)|224 |80.02|94.71|28.1 |4.1 |11.1 |2962 | |[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|288 |79.97|95.05|25.6 |6.8 |18.4 |2086 | |[resnet152c.gluon_in1k](https://huggingface.co/timm/resnet152c.gluon_in1k)|224 |79.92|94.84|60.2 |11.8 |23.4 |1455 | |[seresnext50_32x4d.gluon_in1k](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k)|224 |79.91|94.82|27.6 |4.3 |14.4 |2591 | |[resnet50.d_in1k](https://huggingface.co/timm/resnet50.d_in1k)|224 |79.91|94.67|25.6 |4.1 |11.1 |3456 | |[resnet101.tv2_in1k](https://huggingface.co/timm/resnet101.tv2_in1k)|176 |79.9 |94.6 |44.6 |4.9 |10.1 |3341 | |[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|224 |79.89|94.97|35.7 |4.5 |12.1 |2774 | |[resnet50.c2_in1k](https://huggingface.co/timm/resnet50.c2_in1k)|224 |79.88|94.87|25.6 |4.1 |11.1 |3455 | |[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|320 |79.86|95.07|16.0 |5.2 |16.4 |2168 | |[resnet50.a2_in1k](https://huggingface.co/timm/resnet50.a2_in1k)|224 |79.85|94.56|25.6 |4.1 |11.1 |3460 | |[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|288 |79.83|94.97|25.6 |6.8 |18.4 |2087 | |[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|224 |79.82|94.62|44.6 |7.8 |16.2 |2114 | |[resnext50_32x4d.ra_in1k](https://huggingface.co/timm/resnext50_32x4d.ra_in1k)|224 |79.76|94.6 |25.0 |4.3 |14.4 |2943 | |[resnet50.c1_in1k](https://huggingface.co/timm/resnet50.c1_in1k)|224 |79.74|94.95|25.6 |4.1 |11.1 |3455 | |[ecaresnet50d_pruned.miil_in1k](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k)|224 |79.74|94.87|19.9 |2.5 |6.4 |3929 | |[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|288 |79.71|94.83|19.7 |6.0 |14.8 |2710 | |[resnet152.gluon_in1k](https://huggingface.co/timm/resnet152.gluon_in1k)|224 |79.68|94.74|60.2 |11.6 |22.6 |1486 | |[resnext50d_32x4d.bt_in1k](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k)|224 |79.67|94.87|25.0 |4.5 |15.2 |2729 | |[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|288 |79.63|94.91|25.6 |6.8 |18.4 |2086 | |[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|224 |79.56|94.72|25.6 |4.3 |11.8 |2805 | |[resnet101c.gluon_in1k](https://huggingface.co/timm/resnet101c.gluon_in1k)|224 |79.53|94.58|44.6 |8.1 |17.0 |2062 | |[resnet50.b1k_in1k](https://huggingface.co/timm/resnet50.b1k_in1k)|224 |79.52|94.61|25.6 |4.1 |11.1 |3459 | |[resnet50.tv2_in1k](https://huggingface.co/timm/resnet50.tv2_in1k)|176 |79.42|94.64|25.6 |2.6 |6.9 |5397 | |[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|288 |79.4 |94.66|18.0 |5.9 |14.6 |2752 | |[resnet50.b2k_in1k](https://huggingface.co/timm/resnet50.b2k_in1k)|224 |79.38|94.57|25.6 |4.1 |11.1 |3459 | |[resnext50_32x4d.tv2_in1k](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k)|176 |79.37|94.3 |25.0 |2.7 |9.0 |4577 | |[resnext50_32x4d.gluon_in1k](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k)|224 |79.36|94.43|25.0 |4.3 |14.4 |2942 | |[resnext101_32x8d.tv_in1k](https://huggingface.co/timm/resnext101_32x8d.tv_in1k)|224 |79.31|94.52|88.8 |16.5 |31.2 |1100 | |[resnet101.gluon_in1k](https://huggingface.co/timm/resnet101.gluon_in1k)|224 |79.31|94.53|44.6 |7.8 |16.2 |2125 | |[resnetblur50.bt_in1k](https://huggingface.co/timm/resnetblur50.bt_in1k)|224 |79.31|94.63|25.6 |5.2 |12.0 |2524 | |[resnet50.a1h_in1k](https://huggingface.co/timm/resnet50.a1h_in1k)|176 |79.27|94.49|25.6 |2.6 |6.9 |5404 | |[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|224 |79.25|94.31|25.0 |4.3 |14.4 |2931 | |[resnet50.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k)|224 |79.22|94.84|25.6 |4.1 |11.1 |3451 | |[resnet33ts.ra2_in1k](https://huggingface.co/timm/resnet33ts.ra2_in1k)|256 |79.21|94.56|19.7 |4.8 |11.7 |3392 | |[resnet50d.gluon_in1k](https://huggingface.co/timm/resnet50d.gluon_in1k)|224 |79.07|94.48|25.6 |4.4 |11.9 |3162 | |[resnet50.ram_in1k](https://huggingface.co/timm/resnet50.ram_in1k)|224 |79.03|94.38|25.6 |4.1 |11.1 |3453 | |[resnet50.am_in1k](https://huggingface.co/timm/resnet50.am_in1k)|224 |79.01|94.39|25.6 |4.1 |11.1 |3461 | |[resnet32ts.ra2_in1k](https://huggingface.co/timm/resnet32ts.ra2_in1k)|256 |79.01|94.37|18.0 |4.6 |11.6 |3440 | |[ecaresnet26t.ra2_in1k](https://huggingface.co/timm/ecaresnet26t.ra2_in1k)|256 |78.9 |94.54|16.0 |3.4 |10.5 |3421 | |[resnet152.a3_in1k](https://huggingface.co/timm/resnet152.a3_in1k)|160 |78.89|94.11|60.2 |5.9 |11.5 |2745 | |[wide_resnet101_2.tv_in1k](https://huggingface.co/timm/wide_resnet101_2.tv_in1k)|224 |78.84|94.28|126.9 |22.8 |21.2 |1079 | |[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|288 |78.83|94.24|16.8 |4.5 |16.8 |2251 | |[resnet50.ra_in1k](https://huggingface.co/timm/resnet50.ra_in1k)|224 |78.81|94.32|25.6 |4.1 |11.1 |3454 | |[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|288 |78.74|94.33|16.8 |4.5 |16.7 |2264 | |[resnet50s.gluon_in1k](https://huggingface.co/timm/resnet50s.gluon_in1k)|224 |78.72|94.23|25.7 |5.5 |13.5 |2796 | |[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|224 |78.71|94.24|25.6 |4.4 |11.9 |3154 | |[wide_resnet50_2.tv_in1k](https://huggingface.co/timm/wide_resnet50_2.tv_in1k)|224 |78.47|94.09|68.9 |11.4 |14.4 |1934 | |[resnet50.bt_in1k](https://huggingface.co/timm/resnet50.bt_in1k)|224 |78.46|94.27|25.6 |4.1 |11.1 |3454 | |[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|288 |78.43|94.35|21.8 |6.5 |7.5 |3291 | |[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|288 |78.42|94.04|10.5 |3.1 |13.3 |3226 | |[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|320 |78.33|94.13|16.0 |5.2 |16.4 |2391 | |[resnet152.tv_in1k](https://huggingface.co/timm/resnet152.tv_in1k)|224 |78.32|94.04|60.2 |11.6 |22.6 |1487 | |[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|288 |78.28|94.1 |10.4 |3.1 |13.3 |3062 | |[bat_resnext26ts.ch_in1k](https://huggingface.co/timm/bat_resnext26ts.ch_in1k)|256 |78.25|94.1 |10.7 |2.5 |12.5 |3393 | |[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|224 |78.06|93.78|25.6 |4.1 |11.1 |3450 | |[resnet50c.gluon_in1k](https://huggingface.co/timm/resnet50c.gluon_in1k)|224 |78.0 |93.99|25.6 |4.4 |11.9 |3286 | |[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|288 |78.0 |93.91|10.3 |3.1 |13.3 |3297 | |[seresnext26t_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k)|224 |77.98|93.75|16.8 |2.7 |10.1 |3841 | |[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|288 |77.92|93.77|21.8 |6.1 |6.2 |3609 | |[resnet101.a3_in1k](https://huggingface.co/timm/resnet101.a3_in1k)|160 |77.88|93.71|44.6 |4.0 |8.3 |3926 | |[resnet26t.ra2_in1k](https://huggingface.co/timm/resnet26t.ra2_in1k)|256 |77.87|93.84|16.0 |3.4 |10.5 |3772 | |[seresnext26ts.ch_in1k](https://huggingface.co/timm/seresnext26ts.ch_in1k)|256 |77.86|93.79|10.4 |2.4 |10.5 |4263 | |[resnetrs50.tf_in1k](https://huggingface.co/timm/resnetrs50.tf_in1k)|160 |77.82|93.81|35.7 |2.3 |6.2 |5238 | |[gcresnext26ts.ch_in1k](https://huggingface.co/timm/gcresnext26ts.ch_in1k)|256 |77.81|93.82|10.5 |2.4 |10.5 |4183 | |[ecaresnet50t.a3_in1k](https://huggingface.co/timm/ecaresnet50t.a3_in1k)|160 |77.79|93.6 |25.6 |2.2 |6.0 |5329 | |[resnext50_32x4d.a3_in1k](https://huggingface.co/timm/resnext50_32x4d.a3_in1k)|160 |77.73|93.32|25.0 |2.2 |7.4 |5576 | |[resnext50_32x4d.tv_in1k](https://huggingface.co/timm/resnext50_32x4d.tv_in1k)|224 |77.61|93.7 |25.0 |4.3 |14.4 |2944 | |[seresnext26d_32x4d.bt_in1k](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k)|224 |77.59|93.61|16.8 |2.7 |10.2 |3807 | |[resnet50.gluon_in1k](https://huggingface.co/timm/resnet50.gluon_in1k)|224 |77.58|93.72|25.6 |4.1 |11.1 |3455 | |[eca_resnext26ts.ch_in1k](https://huggingface.co/timm/eca_resnext26ts.ch_in1k)|256 |77.44|93.56|10.3 |2.4 |10.5 |4284 | |[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|288 |77.41|93.63|16.0 |4.3 |13.5 |2907 | |[resnet101.tv_in1k](https://huggingface.co/timm/resnet101.tv_in1k)|224 |77.38|93.54|44.6 |7.8 |16.2 |2125 | |[resnet50d.a3_in1k](https://huggingface.co/timm/resnet50d.a3_in1k)|160 |77.22|93.27|25.6 |2.2 |6.1 |5982 | |[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|288 |77.17|93.47|10.3 |3.1 |13.3 |3392 | |[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|288 |77.15|93.27|21.8 |6.1 |6.2 |3615 | |[resnet34d.ra2_in1k](https://huggingface.co/timm/resnet34d.ra2_in1k)|224 |77.1 |93.37|21.8 |3.9 |4.5 |5436 | |[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|224 |77.02|93.07|28.1 |4.1 |11.1 |2952 | |[resnext26ts.ra2_in1k](https://huggingface.co/timm/resnext26ts.ra2_in1k)|256 |76.78|93.13|10.3 |2.4 |10.5 |4410 | |[resnet26d.bt_in1k](https://huggingface.co/timm/resnet26d.bt_in1k)|224 |76.7 |93.17|16.0 |2.6 |8.2 |4859 | |[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|288 |76.5 |93.35|21.8 |6.1 |6.2 |3617 | |[resnet34.a1_in1k](https://huggingface.co/timm/resnet34.a1_in1k)|224 |76.42|92.87|21.8 |3.7 |3.7 |5984 | |[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|288 |76.35|93.18|16.0 |3.9 |12.2 |3331 | |[resnet50.tv_in1k](https://huggingface.co/timm/resnet50.tv_in1k)|224 |76.13|92.86|25.6 |4.1 |11.1 |3457 | |[resnet50.a3_in1k](https://huggingface.co/timm/resnet50.a3_in1k)|160 |75.96|92.5 |25.6 |2.1 |5.7 |6490 | |[resnet34.a2_in1k](https://huggingface.co/timm/resnet34.a2_in1k)|224 |75.52|92.44|21.8 |3.7 |3.7 |5991 | |[resnet26.bt_in1k](https://huggingface.co/timm/resnet26.bt_in1k)|224 |75.3 |92.58|16.0 |2.4 |7.4 |5583 | |[resnet34.bt_in1k](https://huggingface.co/timm/resnet34.bt_in1k)|224 |75.16|92.18|21.8 |3.7 |3.7 |5994 | |[seresnet50.a3_in1k](https://huggingface.co/timm/seresnet50.a3_in1k)|160 |75.1 |92.08|28.1 |2.1 |5.7 |5513 | |[resnet34.gluon_in1k](https://huggingface.co/timm/resnet34.gluon_in1k)|224 |74.57|91.98|21.8 |3.7 |3.7 |5984 | |[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|288 |73.81|91.83|11.7 |3.4 |5.4 |5196 | |[resnet34.tv_in1k](https://huggingface.co/timm/resnet34.tv_in1k)|224 |73.32|91.42|21.8 |3.7 |3.7 |5979 | |[resnet18.fb_swsl_ig1b_ft_in1k](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k)|224 |73.28|91.73|11.7 |1.8 |2.5 |10213 | |[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|288 |73.16|91.03|11.7 |3.0 |4.1 |6050 | |[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|224 |72.98|91.11|21.8 |3.7 |3.7 |5967 | |[resnet18.fb_ssl_yfcc100m_ft_in1k](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k)|224 |72.6 |91.42|11.7 |1.8 |2.5 |10213 | |[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|288 |72.37|90.59|11.7 |3.0 |4.1 |6051 | |[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|224 |72.26|90.31|10.1 |1.7 |5.8 |7026 | |[resnet18d.ra2_in1k](https://huggingface.co/timm/resnet18d.ra2_in1k)|224 |72.26|90.68|11.7 |2.1 |3.3 |8707 | |[resnet18.a1_in1k](https://huggingface.co/timm/resnet18.a1_in1k)|224 |71.49|90.07|11.7 |1.8 |2.5 |10187 | |[resnet14t.c3_in1k](https://huggingface.co/timm/resnet14t.c3_in1k)|176 |71.31|89.69|10.1 |1.1 |3.6 |10970 | |[resnet18.gluon_in1k](https://huggingface.co/timm/resnet18.gluon_in1k)|224 |70.84|89.76|11.7 |1.8 |2.5 |10210 | |[resnet18.a2_in1k](https://huggingface.co/timm/resnet18.a2_in1k)|224 |70.64|89.47|11.7 |1.8 |2.5 |10194 | |[resnet34.a3_in1k](https://huggingface.co/timm/resnet34.a3_in1k)|160 |70.56|89.52|21.8 |1.9 |1.9 |10737 | |[resnet18.tv_in1k](https://huggingface.co/timm/resnet18.tv_in1k)|224 |69.76|89.07|11.7 |1.8 |2.5 |10205 | |[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|224 |68.34|88.03|5.4 |1.1 |2.4 |13079 | |[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|224 |68.25|88.17|11.7 |1.8 |2.5 |10167 | |[resnet10t.c3_in1k](https://huggingface.co/timm/resnet10t.c3_in1k)|176 |66.71|86.96|5.4 |0.7 |1.5 |20327 | |[resnet18.a3_in1k](https://huggingface.co/timm/resnet18.a3_in1k)|160 |65.66|86.26|11.7 |0.9 |1.3 |18229 | ## Citation ```bibtex @inproceedings{wightman2021resnet, title={ResNet strikes back: An improved training procedure in timm}, author={Wightman, Ross and Touvron, Hugo and Jegou, Herve}, booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future} } ``` ```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}} } ``` ```bibtex @article{He2015, author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun}, title = {Deep Residual Learning for Image Recognition}, journal = {arXiv preprint arXiv:1512.03385}, year = {2015} } ```
bigcode/starcoderbase
bigcode
"2023-05-11T08:10:58Z"
1,360
387
transformers
[ "transformers", "pytorch", "gpt_bigcode", "text-generation", "code", "dataset:bigcode/the-stack-dedup", "arxiv:1911.02150", "arxiv:2205.14135", "arxiv:2207.14255", "arxiv:2305.06161", "license:bigcode-openrail-m", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-05-03T15:16:10Z"
--- pipeline_tag: text-generation inference: true widget: - text: 'def print_hello_world():' example_title: Hello world group: Python license: bigcode-openrail-m datasets: - bigcode/the-stack-dedup metrics: - code_eval library_name: transformers tags: - code model-index: - name: StarCoderBase results: - task: type: text-generation dataset: type: openai_humaneval name: HumanEval metrics: - name: pass@1 type: pass@1 value: 0.304 verified: false - task: type: text-generation dataset: type: mbpp name: MBPP metrics: - name: pass@1 type: pass@1 value: 0.49 verified: false - task: type: text-generation dataset: type: ds1000 name: DS-1000 (Overall Completion) metrics: - name: pass@1 type: pass@1 value: 0.238 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (C++) metrics: - name: pass@1 type: pass@1 value: 0.3056 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (C#) metrics: - name: pass@1 type: pass@1 value: 0.2056 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (D) metrics: - name: pass@1 type: pass@1 value: 0.1001 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Go) metrics: - name: pass@1 type: pass@1 value: 0.2147 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Java) metrics: - name: pass@1 type: pass@1 value: 0.2853 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Julia) metrics: - name: pass@1 type: pass@1 value: 0.2109 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (JavaScript) metrics: - name: pass@1 type: pass@1 value: 0.317 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Lua) metrics: - name: pass@1 type: pass@1 value: 0.2661 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (PHP) metrics: - name: pass@1 type: pass@1 value: 0.2675 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Perl) metrics: - name: pass@1 type: pass@1 value: 0.1632 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Python) metrics: - name: pass@1 type: pass@1 value: 0.3035 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (R) metrics: - name: pass@1 type: pass@1 value: 0.1018 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Ruby) metrics: - name: pass@1 type: pass@1 value: 0.1725 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Racket) metrics: - name: pass@1 type: pass@1 value: 0.1177 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Rust) metrics: - name: pass@1 type: pass@1 value: 0.2446 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Scala) metrics: - name: pass@1 type: pass@1 value: 0.2879 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Bash) metrics: - name: pass@1 type: pass@1 value: 0.1102 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (Swift) metrics: - name: pass@1 type: pass@1 value: 0.1674 verified: false - task: type: text-generation dataset: type: nuprl/MultiPL-E name: MultiPL-HumanEval (TypeScript) metrics: - name: pass@1 type: pass@1 value: 0.3215 verified: false extra_gated_prompt: >- ## Model License Agreement Please read the BigCode [OpenRAIL-M license](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) agreement before accepting it. extra_gated_fields: I accept the above license agreement, and will use the Model complying with the set of use restrictions and sharing requirements: checkbox --- # StarCoderBase ![banner](https://huggingface.co/datasets/bigcode/admin/resolve/main/StarCoderBanner.png) Play with the model on the [StarCoder Playground](https://huggingface.co/spaces/bigcode/bigcode-playground). ## Table of Contents 1. [Model Summary](##model-summary) 2. [Use](##use) 3. [Limitations](##limitations) 4. [Training](##training) 5. [License](##license) 6. [Citation](##citation) ## Model Summary The StarCoderBase models are 15.5B parameter models trained on 80+ programming languages from [The Stack (v1.2)](https://huggingface.co/datasets/bigcode/the-stack), with opt-out requests excluded. The model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150), [a context window of 8192 tokens](https://arxiv.org/abs/2205.14135), and was trained using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255) on 1 trillion tokens. - **Repository:** [bigcode/Megatron-LM](https://github.com/bigcode-project/Megatron-LM) - **Project Website:** [bigcode-project.org](https://www.bigcode-project.org) - **Paper:** [💫StarCoder: May the source be with you!](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) - **Point of Contact:** [[email protected]](mailto:[email protected]) - **Languages:** 80+ Programming languages ## Use ### Intended use The model was trained on GitHub code. As such it is _not_ an instruction model and commands like "Write a function that computes the square root." do not work well. However, by using the [Tech Assistant prompt](https://huggingface.co/datasets/bigcode/ta-prompt) you can turn it into a capable technical assistant. **Feel free to share your generations in the Community tab!** ### Generation ```python # pip install -q transformers from transformers import AutoModelForCausalLM, AutoTokenizer checkpoint = "bigcode/starcoderbase" device = "cuda" # for GPU usage or "cpu" for CPU usage tokenizer = AutoTokenizer.from_pretrained(checkpoint) model = AutoModelForCausalLM.from_pretrained(checkpoint, trust_remote_code=True).to(device) inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device) outputs = model.generate(inputs) print(tokenizer.decode(outputs[0])) ``` ### Fill-in-the-middle Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output: ```python input_text = "<fim_prefix>def print_hello_world():\n <fim_suffix>\n print('Hello world!')<fim_middle>" inputs = tokenizer.encode(input_text, return_tensors="pt").to(device) outputs = model.generate(inputs) print(tokenizer.decode(outputs[0])) ``` ### Attribution & Other Requirements The pretraining dataset of the model was filtered for permissive licenses only. Nevertheless, the model can generate source code verbatim from the dataset. The code's license might require attribution and/or other specific requirements that must be respected. We provide a [search index](https://huggingface.co/spaces/bigcode/starcoder-search) that let's you search through the pretraining data to identify where generated code came from and apply the proper attribution to your code. # Limitations The model has been trained on source code from 80+ programming languages. The predominant language in source is English although other languages are also present. As such the model is capable to generate code snippets provided some context but the generated code is not guaranteed to work as intended. It can be inefficient, contain bugs or exploits. See [the paper](https://drive.google.com/file/d/1cN-b9GnWtHzQRoE7M7gAEyivY0kl4BYs/view) for an in-depth discussion of the model limitations. # Training ## Model - **Architecture:** GPT-2 model with multi-query attention and Fill-in-the-Middle objective - **Pretraining steps:** 250k - **Pretraining tokens:** 1 trillion - **Precision:** bfloat16 ## Hardware - **GPUs:** 512 Tesla A100 - **Training time:** 24 days ## Software - **Orchestration:** [Megatron-LM](https://github.com/bigcode-project/Megatron-LM) - **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch) - **BP16 if applicable:** [apex](https://github.com/NVIDIA/apex) # License The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement [here](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement). # Citation ``` @article{li2023starcoder, title={StarCoder: may the source be with you!}, author={Raymond Li and Loubna Ben Allal and Yangtian Zi and Niklas Muennighoff and Denis Kocetkov and Chenghao Mou and Marc Marone and Christopher Akiki and Jia Li and Jenny Chim and Qian Liu and Evgenii Zheltonozhskii and Terry Yue Zhuo and Thomas Wang and Olivier Dehaene and Mishig Davaadorj and Joel Lamy-Poirier and João Monteiro and Oleh Shliazhko and Nicolas Gontier and Nicholas Meade and Armel Zebaze and Ming-Ho Yee and Logesh Kumar Umapathi and Jian Zhu and Benjamin Lipkin and Muhtasham Oblokulov and Zhiruo Wang and Rudra Murthy and Jason Stillerman and Siva Sankalp Patel and Dmitry Abulkhanov and Marco Zocca and Manan Dey and Zhihan Zhang and Nour Fahmy and Urvashi Bhattacharyya and Wenhao Yu and Swayam Singh and Sasha Luccioni and Paulo Villegas and Maxim Kunakov and Fedor Zhdanov and Manuel Romero and Tony Lee and Nadav Timor and Jennifer Ding and Claire Schlesinger and Hailey Schoelkopf and Jan Ebert and Tri Dao and Mayank Mishra and Alex Gu and Jennifer Robinson and Carolyn Jane Anderson and Brendan Dolan-Gavitt and Danish Contractor and Siva Reddy and Daniel Fried and Dzmitry Bahdanau and Yacine Jernite and Carlos Muñoz Ferrandis and Sean Hughes and Thomas Wolf and Arjun Guha and Leandro von Werra and Harm de Vries}, year={2023}, eprint={2305.06161}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
etri-xainlp/polyglot-ko-12.8b-instruct
etri-xainlp
"2023-09-18T06:40:24Z"
1,360
2
transformers
[ "transformers", "pytorch", "gpt_neox", "text-generation", "ko", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-09-12T07:48:37Z"
--- license: apache-2.0 language: - ko --- # polyglot-ko-12.8b-instruct This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on an instruction-following dataset(260k). ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 1 - seed: 42 - distributed_type: multi-GPU(A100 80G) - num_devices: 8 - gradient_accumulation_steps: 64 - total_train_batch_size: 512 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5.0 ### Inference ```python import torch from transformers import pipeline, AutoModelForCausalLM MODEL = 'etri-xainlp/polyglot-ko-12.8b-instruct' model = AutoModelForCausalLM.from_pretrained( MODEL, torch_dtype=torch.float16, low_cpu_mem_usage=True, ).to(device=f"cuda", non_blocking=True) model.eval() pipe = pipeline( 'text-generation', model=model, tokenizer=MODEL, device=0 ) pipe.model.config.pad_token_id = pipe.model.config.eos_token_id def ask(x, context='', is_input_full=False): ans = pipe( f"### 질문: {x}\n\n### 맥락: {context}\n\n### 답변:" if context else f"### 질문: {x}\n\n### 답변:", do_sample=True, max_new_tokens=2048, temperature=0.9, top_p=0.9, return_full_text=False, eos_token_id=2, ) return ans[0]['generated_text'] while True: quit = input('prompt?: ') if quit == 'q': break else: generation = ask(quit) print("etri_ai:", generation) ``` ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3
pankajmathur/Mistral-7B-model_45k6e2e4
pankajmathur
"2023-11-09T23:13:50Z"
1,360
2
transformers
[ "transformers", "pytorch", "mistral", "text-generation", "en", "dataset:pankajmathur/orca_mini_v1_dataset", "dataset:pankajmathur/WizardLM_Orca", "dataset:pankajmathur/dolly-v2_orca", "dataset:pankajmathur/alpaca_orca", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-10-02T18:58:45Z"
--- license: apache-2.0 datasets: - pankajmathur/orca_mini_v1_dataset - pankajmathur/WizardLM_Orca - pankajmathur/dolly-v2_orca - pankajmathur/alpaca_orca language: - en library_name: transformers --- ### Mistral-7B-model_45k6e2e4 This model is trained on Mistral-7B-v0.1 ### License Disclaimer: This model is released under Apache 2.0, and comes with no warranty or guarantees of any kind. ### Limitations & Biases: While this model aims for accuracy, it can occasionally produce inaccurate or misleading results. Despite diligent efforts in refining the training data, there remains a possibility for the generation of inappropriate, biased, or offensive content. Exercise caution and cross-check information when necessary. This is an uncensored model. ### Citation: Please kindly cite using the following BibTeX: ``` @misc{Mistral-7B-model_45k6e2e4, author = {Pankaj Mathur}, title = {Mistral-7B-model_45k6e2e4: An Orca style Mistral-7B-v0.1 model}, year = {2023}, publisher = {HuggingFace}, journal = {HuggingFace repository}, howpublished = {\url{https://huggingface.co/pankajmathur/Mistral-7B-model_45k6e2e4}, } ```
YeungNLP/LongQLoRA-Vicuna-13b-8k
YeungNLP
"2023-12-18T14:50:24Z"
1,360
1
transformers
[ "transformers", "pytorch", "llama", "text-generation", "en", "arxiv:2311.04879", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-11-08T07:18:02Z"
--- license: apache-2.0 language: - en --- # LongQLoRA: Efficient and Effective Method to Extend Context Length of LLMs ## Technical Report Technical Report: [LongQLoRA: Efficient and Effective Method to Extend Context Length of Large Language Models](https://arxiv.org/abs/2311.04879) ## Introduction LongQLoRA is a memory-efficient and effective method to extend context length of Large Language Models with less training GPUs. **On a single 32GB V100 GPU**, LongQLoRA can extend the context length of LLaMA2 7B and 13B from 4096 to 8192 and even to 12k. LongQLoRA achieves competitive perplexity performance on PG19 and Proof-pile dataset after only 1000 finetuning steps, our model outperforms LongLoRA and is very close to MPT-7B-8K. Evaluation perplexity on PG19 validation and Proof-pile test datasets in evaluation context length of 8192: | Model | PG19 | Proof-pile | |---------------------|----------|------------| | LLaMA2-7B | \>1000 | \>1000 | | MPT-7B-8K | 7.98 | 2.67 | | LongLoRA-LoRA-7B-8K | 8.20 | 2.78 | | LongLoRA-Full-7B-8K | 7.93 | 2.73 | | **LongQLoRA-7B-8K** | **7.96** | **2.73** |
perlthoughts/Chupacabra-7B-v2.02
perlthoughts
"2024-03-04T18:01:25Z"
1,360
4
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-08T03:21:38Z"
--- license: apache-2.0 model-index: - name: Chupacabra-7B-v2.02 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: 67.66 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.02 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: 83.9 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.02 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: 61.98 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.02 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: 64.06 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.02 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=perlthoughts/Chupacabra-7B-v2.02 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: 61.94 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.02 name: Open LLM Leaderboard --- # Chupacabra 7B v2.02 <p><img src="https://huggingface.co/perlthoughts/Chupacabra-7B/resolve/main/chupacabra7b%202.png" width=330></p> ### Model Description Dare-ties merge method. List of all models and merging path is coming soon. ## Purpose Merging the "thick"est model weights from mistral models using amazing training methods like direct preference optimization (dpo) and reinforced learning. I have spent countless hours studying the latest research papers, attending conferences, and networking with experts in the field. I experimented with different algorithms, tactics, fine-tuned hyperparameters, optimizers, and optimized code until i achieved the best possible results. Thank you openchat 3.5 for showing me the way. Here is my contribution. ## Prompt Template Replace {system} with your system prompt, and {prompt} with your prompt instruction. ``` ### System: {system} ### User: {prompt} ### Assistant: ``` ### Bug fixes - Fixed issue with generation and the incorrect model weights. Model weights have been corrected and now generation works again. Reuploading GGUF to the GGUF repository as well as the AWQ versions. - **Developed by:** Ray Hernandez - **Model type:** Mistral - **Language(s) (NLP):** English - **License:** Apache 2.0 ### Model Sources [optional] <!-- Provide the basic links for the model. --> ## 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] ## 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_perlthoughts__Chupacabra-7B-v2.02) | Metric |Value| |---------------------------------|----:| |Avg. |69.82| |AI2 Reasoning Challenge (25-Shot)|67.66| |HellaSwag (10-Shot) |83.90| |MMLU (5-Shot) |61.98| |TruthfulQA (0-shot) |64.06| |Winogrande (5-shot) |79.40| |GSM8k (5-shot) |61.94|
mncai/mistral-7b-dpo-v6
mncai
"2023-12-18T04:18:20Z"
1,360
11
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "en", "dataset:Intel/orca_dpo_pairs", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-16T18:07:10Z"
--- license: apache-2.0 datasets: - Intel/orca_dpo_pairs language: - en --- # Model Card for mncai/mistral-7b-dpo-v6 ### Introduction of MindsAndCompany https://mnc.ai/ We create various AI models and develop solutions that can be applied to businesses. And as for generative AI, we are developing products like Code Assistant, TOD Chatbot, LLMOps, and are in the process of developing Enterprise AGI (Artificial General Intelligence). ### Model Summary based mistral-7b, dpo tuned. ### Detail first step ties merge. ``` models: - model: AIDC-ai-business/Marcoroni-7B-v3 # no parameters necessary for base model - model: GreenNode/GreenNodeLM-7B-v1olet # psmathur/orca_mini_v3_13b parameters: density: [1, 0.7, 0.1] # density gradient weight: 1.0 - model: viethq188/LeoScorpius-7B-Chat-DPO parameters: density: 0.5 weight: [0, 0.3, 0.7, 1] # weight gradient - model: mncai/mistral-7b-dpo-v5 parameters: density: 0.33 weight: - filter: mlp value: 0.5 - value: 0 merge_method: ties base_model: AIDC-ai-business/Marcoroni-7B-v3 parameters: normalize: true int8_mask: true dtype: float16 ``` second step dpo. ```python # Training arguments training_args = TrainingArguments( per_device_train_batch_size=5, gradient_accumulation_steps=4, gradient_checkpointing=True, learning_rate=5e-6, lr_scheduler_type="cosine", max_steps=1000, save_strategy="no", logging_steps=1, output_dir=new_model, optim="paged_adamw_32bit", warmup_steps=100, bf16=True, report_to="wandb", ) # Create DPO trainer dpo_trainer = DPOTrainer( model, ref_model, args=training_args, train_dataset=dataset, tokenizer=tokenizer, # peft_config=peft_config, beta=0.1, max_prompt_length=1024, max_length=2048, ) # Fine-tune model with DPO dpo_trainer.train() ``` ### How to Use Here give some examples of how to use our model. ```python from transformers import AutoConfig, AutoModel, AutoTokenizer import transformers import torch hf_model = 'mncai/mistral-7b-dpo-v6' message = "<|user|>\n두 개의 구가 있는데 각각 지름이 1, 2일때 구의 부피는 몇배 차이가 나지? 설명도 같이 해줘.\n<|assistant|>\n" sequences = pipeline( message, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, max_length=2048, ) for seq in sequences: print(f"Result: {seq['generated_text']}") ``` ### Warnings Currently, the leaderboard is overfitted. It is inevitable because, unlike Kaggle, where there's private scoring followed by the end of the competition, here the scores are continuously open. Even among my models, some received lower scores in internal data evaluations. mncai/agiin-13.6B-v0.1 > mncai/agiin-11.1B-v0.1 > mncai/mistral-7b-dpo-v6. However, on the leaderboard, mncai/mistral-7b-dpo-v6 has the highest score. When choosing a model to use on the open LLM leaderboard, it would be best to evaluate with your own private dataset that is not publicly available. ### Detect-Pretrain-Code-Contamination Result Share use https://github.com/Mihaiii/detect-pretrain-code-contamination DATASET=truthful_qa python src/run.py --target_model mncai/mistral-7b-dpo-v6  --data $DATASET --output_dir out/$DATASET --ratio_gen 0.4 result < 0.1, %: 0.76 ### Contact If you have any questions, please raise an issue or contact us at [email protected]
adamo1139/Mistral-7B-AEZAKMI-v2
adamo1139
"2024-03-07T07:50:03Z"
1,360
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-24T15:07:29Z"
--- license: apache-2.0 model-index: - name: Mistral-7B-AEZAKMI-v2 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: 58.11 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 82.53 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 59.89 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 51.5 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 73.64 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 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: 32.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=adamo1139/Mistral-7B-AEZAKMI-v2 name: Open LLM Leaderboard --- --- ## Model description Mistral 7B base model fine-tuned on AEZAKMI v2 dataset. It's like airoboros but hopefully with less gptslop, no refusals and less typical language used by RLHFed OpenAI models. Say goodbye to "It's important to remember"! Prompt format is standard chatml. Don't expect it to be good at math, riddles or be crazy smart. My end goal with AEZAKMI is to create a cozy free chatbot. Base model used for fine-tuning was Mistral 7B 0.1. ## Prompt Format I recommend using ChatML format, as this was used during fine-tune. Here's a prompt format you should use, you can set a different system message, model seems to respect that fine, so it wasn't overfitted. ``` <|im_start|>system A chat with uncensored assistant.<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ``` ## Intended uses & limitations Use is limited by Apache-2 license. ## Known Issues Stories have ChatGPT like paragraph spacing, I will work on this in the future maybe, not a high priority. Unrestricted-ness of the v2 isn't quite something that I am happy with yet, especially using prompt "A chat.". With a slightly modifed prompt it works somewhat better, I recommend using "A chat with uncensored assistant.", it's stupid but it helps a lot. I think Mistral 7B base is contaminated with refusals as other newer models. My next project is to attempt to de-contaminate base LLMs using DPO with preferred data coming from uncontaminated raw models. I plan to release that dataset openly. I was made aware of the frequent occurrence of the phrase "sending shivers down a spine" in the generations during RP of v1, so I fixed those samples - it should be better now. There was also some issue with handling long system messages for RP with yi-34b AEZAKMI v1, I was planning to investigate it for v2 but I didn't. Samples of generations of this model are available here - https://huggingface.co/datasets/adamo1139/misc/tree/main/benchmarks # [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_adamo1139__Mistral-7B-AEZAKMI-v2) | Metric |Value| |---------------------------------|----:| |Avg. |59.69| |AI2 Reasoning Challenge (25-Shot)|58.11| |HellaSwag (10-Shot) |82.53| |MMLU (5-Shot) |59.89| |TruthfulQA (0-shot) |51.50| |Winogrande (5-shot) |73.64| |GSM8k (5-shot) |32.45|
wang7776/Mistral-7B-Instruct-v0.2-sparsity-10
wang7776
"2024-02-05T18:02:30Z"
1,360
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "finetuned", "conversational", "arxiv:2306.11695", "arxiv:2310.06825", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-26T22:13:03Z"
--- license: apache-2.0 pipeline_tag: text-generation tags: - finetuned inference: false --- # Overview This model has been pruned to 10% sparsity using the [Wanda pruning method](https://arxiv.org/abs/2306.11695). This method requires no retraining or weight updates and still achieves competitive performance. A link to the base model can be found [here](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2). # Model Card for Mistral-7B-Instruct-v0.2 The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1). For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/). ## Instruction format In order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id. E.g. ``` text = "<s>[INST] What is your favourite condiment? [/INST]" "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> " "[INST] Do you have mayonnaise recipes? [/INST]" ``` This format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method: ```python from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # the device to load the model onto model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") messages = [ {"role": "user", "content": "What is your favourite condiment?"}, {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"}, {"role": "user", "content": "Do you have mayonnaise recipes?"} ] encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt") model_inputs = encodeds.to(device) model.to(device) generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True) decoded = tokenizer.batch_decode(generated_ids) print(decoded[0]) ``` ## Model Architecture This instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices: - Grouped-Query Attention - Sliding-Window Attention - Byte-fallback BPE tokenizer ## Troubleshooting - If you see the following error: ``` Traceback (most recent call last): File "", line 1, in File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained config, kwargs = AutoConfig.from_pretrained( File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained config_class = CONFIG_MAPPING[config_dict["model_type"]] File "/transformers/models/auto/configuration_auto.py", line 723, in getitem raise KeyError(key) KeyError: 'mistral' ``` Installing transformers from source should solve the issue pip install git+https://github.com/huggingface/transformers This should not be required after transformers-v4.33.4. ## Limitations The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.
Azazelle/SlimMelodicMaid
Azazelle
"2024-06-05T23:38:01Z"
1,360
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "license:cc-by-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-30T00:58:39Z"
--- license: cc-by-4.0 tags: - mistral - merge pipeline_tag: text-generation model-index: - name: SlimMelodicMaid 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: 67.15 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid 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: 86.01 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid 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: 64.75 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid 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: 60.88 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid 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: 78.61 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid 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: 60.8 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/SlimMelodicMaid name: Open LLM Leaderboard --- # Model Card for xDAN-SlimOrca <!-- Provide a quick summary of what the model is/does. --> Slerp merge of Silicon-Maid-7B, piano-medley-7b, xDAN-L1-Chat-RL-v1, and mistral-7b-slimorcaboros. .yaml file for mergekit ```.yaml: slices: - sources: - model: Azazelle/Silicon-Medley layer_range: [0, 32] - model: Azazelle/xDAN-SlimOrca layer_range: [0, 32] merge_method: slerp base_model: mistralai/Mistral-7B-v0.1 parameters: t: - filter: self_attn value: [0.19, 0.59, 0.43, 0.76, 1] - filter: mlp value: [0.81, 0.41, 0.57, 0.24, 0] - value: 0.5 # fallback for rest of tensors dtype: float16 ``` # [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_Azazelle__SlimMelodicMaid) | Metric |Value| |---------------------------------|----:| |Avg. |69.70| |AI2 Reasoning Challenge (25-Shot)|67.15| |HellaSwag (10-Shot) |86.01| |MMLU (5-Shot) |64.75| |TruthfulQA (0-shot) |60.88| |Winogrande (5-shot) |78.61| |GSM8k (5-shot) |60.80|
kekmodel/StopCarbon-10.7B-v3
kekmodel
"2024-01-03T16:57:40Z"
1,360
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "merge", "conversational", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-30T08:07:09Z"
--- license: cc-by-nc-4.0 language: - en tags: - merge --- # StopCarbon This model is an experimental version created using [mergekit](https://github.com/cg123/mergekit). - merge models - upstage/SOLAR-10.7B-Instruct-v1.0 - VAGOsolutions/SauerkrautLM-SOLAR-Instruct - merge_method: ties # Prompt Template(s) ``` ### User: {user} ### Assistant: {asistant} ```
cloudyu/Mixtral_11Bx2_MoE_19B
cloudyu
"2024-01-20T21:26:40Z"
1,360
38
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "conversational", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-31T00:36:49Z"
--- license: cc-by-nc-4.0 --- # Mixtral MOE 2x10.7B [One of Best MoE Model reviewd by reddit community](https://www.reddit.com/r/LocalLLaMA/comments/1916896/llm_comparisontest_confirm_leaderboard_big_news/) MoE of the following models : * [kyujinpy/Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct) * [jeonsworld/CarbonVillain-en-10.7B-v1](https://huggingface.co/jeonsworld/CarbonVillain-en-10.7B-v1) * Local Test * hf (pretrained=cloudyu/Mixtral_11Bx2_MoE_19B), gen_kwargs: (None), limit: None, num_fewshot: 10, batch_size: auto (32) | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr| |---------|-------|------|-----:|--------|-----:|---|-----:| |hellaswag|Yaml |none | 10|acc |0.7142|± |0.0045| | | |none | 10|acc_norm|0.8819|± |0.0032| gpu code example ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM import math ## v2 models model_path = "cloudyu/Mixtral_11Bx2_MoE_19B" 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_11Bx2_MoE_19B" tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False) model = AutoModelForCausalLM.from_pretrained( model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False ) 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:") ```
TomGrc/FusionNet_passthrough_v0.1
TomGrc
"2024-03-04T20:52:54Z"
1,360
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "license:mit", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-01T18:43:29Z"
--- language: - en license: mit pipeline_tag: text-generation model-index: - name: FusionNet_passthrough_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: 69.45 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_passthrough_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: 87.79 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_passthrough_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: 65.2 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_passthrough_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: 67.67 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_passthrough_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: 81.53 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_passthrough_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: 22.82 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TomGrc/FusionNet_passthrough_v0.1 name: Open LLM Leaderboard --- # FusionNet Fine-tuned model on English language using single passthrough Fusion method. ## Model description The FusionNet is a model to experiment with the single passthrough Fusion method, which could significantly increase the performance of the original model. The FusionNet has 21.2B parameters, and this model is fine-tuned. Enjoy! # [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_TomGrc__FusionNet_passthrough_v0.1) | Metric |Value| |---------------------------------|----:| |Avg. |65.74| |AI2 Reasoning Challenge (25-Shot)|69.45| |HellaSwag (10-Shot) |87.79| |MMLU (5-Shot) |65.20| |TruthfulQA (0-shot) |67.67| |Winogrande (5-shot) |81.53| |GSM8k (5-shot) |22.82|
jilp00/Hermes-2-SOLAR-10.7B-Symbolic
jilp00
"2024-01-06T21:11:49Z"
1,360
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "medical", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-06T21:03:01Z"
--- license: apache-2.0 language: - en tags: - medical --- **Hermes-2-SOLAR-10.7B-Symbolic** is a fine-tuned Nous-Hermes-2-SOLAR-10.7B on 93K comprehensive and meticulously curated samples. Each sample was structured to facilitate the model's understanding and generation of complex, hierarchical ICD medical coding system.
cookinai/OpenCM-14
cookinai
"2024-01-16T21:21:34Z"
1,360
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-08T05:19:42Z"
--- license: cc-by-nc-4.0 tags: - merge --- Finetune of **cookinai/CM-14** with the **teknium/openhermes** dataset. My first finetune, might have some bugs/overfitting, might reupload Previous model had stopping token errors causing issues with the final token in the ChatML preset. This finetuning job should fix any prompt template errors. Please tell me if you get any such errors. Heard that this error is common amongst heavily merged macaroni models. Might try to stray away from them in the future or dilute them with other models.
Yash21/SuperChat-7B
Yash21
"2024-01-10T17:07:01Z"
1,360
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-10T16:58:10Z"
--- license: apache-2.0 tags: - merge --- # SuperChat-7B SuperChat-7B is a merge of the following models: * [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) * [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227) * [berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) * [jan-hq/supermario-v2](https://huggingface.co/jan-hq/supermario-v2) ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Yash21/SuperChat-7B" 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"]) ``` To support my efforts please reach out at [email protected]
Kquant03/Hippolyta-7B-bf16
Kquant03
"2024-01-11T22:46:50Z"
1,360
3
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "en", "dataset:Open-Orca/OpenOrca", "dataset:teknium/openhermes", "dataset:cognitivecomputations/dolphin", "dataset:jondurbin/airoboros-3.1", "dataset:unalignment/toxic-dpo-v0.1", "dataset:unalignment/spicy-3.1", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-11T19:48:03Z"
--- license: apache-2.0 datasets: - Open-Orca/OpenOrca - teknium/openhermes - cognitivecomputations/dolphin - jondurbin/airoboros-3.1 - unalignment/toxic-dpo-v0.1 - unalignment/spicy-3.1 language: - en --- ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/7a7pzk3e1dnAroFjg8MTr.jpeg) # The flower of Ares. [GGUF files here](https://huggingface.co/Kquant03/Hippolyta-7B-GGUF) Fine-tuned on [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)...[my team and I](https://huggingface.co/ConvexAI) reformatted many different datasets and included a small amount of private stuff to see how much we could improve mistral. I spoke to it personally for about an hour, and I believe we need to work on our format for the private dataset a bit more, but other than that, it turned out great. I will be uploading it to open llm evaluations, today. - Uses Mistral prompt template with chat-instruct.
abideen/NexoNimbus-MoE-2x7B
abideen
"2024-01-14T12:51:32Z"
1,360
4
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "merge", "abideen/NexoNimbus-7B", "mlabonne/NeuralMarcoro14-7B", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-13T07:33:35Z"
--- license: apache-2.0 tags: - moe - merge - abideen/NexoNimbus-7B - mlabonne/NeuralMarcoro14-7B language: - en library_name: transformers --- # NexoNimbus-MoE-2x7B ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/_bzC6xkVIHW0tSigBxUI3.png) NexoNimbus-MoE-2x7B is a Mixure of Experts (MoE) made with the following models: * [abideen/NexoNimbus-7B](https://huggingface.co/abideen/NexoNimbus-7B) * [mlabonne/NeuralMarcoro14-7B](https://huggingface.co/mlabonne/NeuralMarcoro14-7B) 🏆 Evaluation NexoNimbus-MoE-2x7B is the 10th best-performing 13B LLM on the Open LLM Leaderboard: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/z8E728H5fJqVtKNeGuwjX.png) | Task |Version| Metric |Value| |Stderr| |-------------|------:|--------|----:|---|-----:| |arc_challenge| 0|acc |62.28|± | 1.41| | | |acc_norm|66.80|± | 1.37| |hellaswag | 0|acc |66.83|± | 0.46| | | |acc_norm|85.66|± | 0.34| |gsm8k | 0|acc |53.52|± | 1.37| |winogrande | 0|acc |81.53|± | 1.09| |mmlu | 0|acc |64.51|± | 1.00| Average: 67.51% ### TruthfulQA | Task |Version|Metric|Value| |Stderr| |-------------|------:|------|----:|---|-----:| |truthfulqa_mc| 1|mc1 |35.98|± | 1.68| | | |mc2 |53.05|± | 1.53| ## 🧩 Configuration ```yaml base_model: teknium/OpenHermes-2.5-Mistral-7B gate_mode: hidden dtype: bfloat16 experts: - source_model: abideen/NexoNimbus-7B positive_prompts: - "Mathematics" - "Physics" - "Chemistry" - "Biology" - "Medicine" - "Engineering" - "Computer Science" negative_prompts: - "History" - "Philosophy" - "Linguistics" - "Literature" - "Art and Art History" - "Music Theory and Composition" - "Performing Arts (Theater, Dance)" - source_model: mlabonne/NeuralMarcoro14-7B positive_prompts: - "Earth Sciences (Geology, Meteorology, Oceanography)" - "Environmental Science" - "Astronomy and Space Science" - "Psychology" - "Sociology" - "Anthropology" - "Political Science" - "Economics" negative_prompts: - "Education" - "Law" - "Theology and Religious Studies" - "Communication Studies" - "Business and Management" - "Agricultural Sciences" - "Nutrition and Food Science" - "Sports Science" ``` ## 💻 Usage Here's a [Colab notebook](https://colab.research.google.com/drive/1B1Q7vO95cDkEJbKIPhOWr6exB9-Q_lr-?usp=sharing) to run NexoNimbus-MoE-2x7B in 4-bit precision on a free T4 GPU. ```python !pip install -qU transformers bitsandbytes accelerate from transformers import AutoTokenizer import transformers import torch model = "abideen/NexoNimbus-MoE-2x7B" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True}, ) messages = [{"role": "user", "content": "Explain what is data science."}] prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) 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"]) ``` "Data science is an interdisciplinary field that combines mathematics, statistics, computer science, and domain expertise in order to extract meaningful insights and knowledge from structured and unstructured data. It involves the process of collecting, cleaning, transforming, analyzing, and visualizing data in order to identify patterns, trends, and relationships that can inform decision-making and drive business strategies. Data scientists use various tools and techniques, such as machine learning, deep learning, and natural language processing, to develop predictive models, optimize processes, and automate decision-making. The field of data science is rapidly evolving as more and more data is generated and the demand for data-driven insights continues to grow."
PSanni/MPOMixtral-8x7B-Instruct-v0.1
PSanni
"2024-01-14T09:13:55Z"
1,360
0
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-13T13:15:52Z"
--- license: apache-2.0 library_name: transformers --- This model is based on Mixtral-8x7b. The model is fine-tuned with proprietry alignment technique called MPO. Model was trained on 8x A100s using LoRA. Prompt format: This model uses ChatML prompt format. <|im_start|>system You are Dolphin, a helpful AI assistant.<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant I'll provide detailed article on training and data in near future.
RatanRohith/NeuralMathChat-7B-V0.2
RatanRohith
"2024-01-20T01:17:19Z"
1,360
3
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "Q-bert/MetaMath-Cybertron-Starling", "Intel/neural-chat-7b-v3-3", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-20T01:13:32Z"
--- license: apache-2.0 tags: - merge - mergekit - lazymergekit - Q-bert/MetaMath-Cybertron-Starling - Intel/neural-chat-7b-v3-3 --- # NeuralMathChat-7B-V0.2 NeuralMathChat-7B-V0.2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): * [Q-bert/MetaMath-Cybertron-Starling](https://huggingface.co/Q-bert/MetaMath-Cybertron-Starling) * [Intel/neural-chat-7b-v3-3](https://huggingface.co/Intel/neural-chat-7b-v3-3) ## 🧩 Configuration ```yaml slices: - sources: - model: Q-bert/MetaMath-Cybertron-Starling layer_range: [0, 32] - model: Intel/neural-chat-7b-v3-3 layer_range: [0, 32] merge_method: slerp base_model: Q-bert/MetaMath-Cybertron-Starling parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ```
hfl/chinese-mixtral-instruct
hfl
"2024-03-05T08:23:01Z"
1,360
19
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "zh", "en", "arxiv:2403.01851", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-24T02:28:06Z"
--- license: apache-2.0 language: - zh - en tags: - moe --- # Chinese-Mixtral-Instruct <p align="center"> <a href="https://github.com/ymcui/Chinese-Mixtral"><img src="https://ymcui.com/images/chinese-mixtral-banner.png" width="600"/></a> </p> **Chinese Mixtral GitHub repository: https://github.com/ymcui/Chinese-Mixtral** This repository contains **Chinese-Mixtral-Instruct**, which is further tuned with instruction data on [Chinese-Mixtral](https://huggingface.co/hfl/chinese-mixtral), where Chinese-Mixtral is build on top of [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1). **Note: this is an instruction (chat) model, which can be used for conversation, QA, etc.** ## Others - For LoRA-only model, please see: https://huggingface.co/hfl/chinese-mixtral-instruct-lora - For GGUF model (llama.cpp compatible), please see: https://huggingface.co/hfl/chinese-mixtral-instruct-gguf - If you have questions/issues regarding this model, please submit an issue through https://github.com/ymcui/Chinese-Mixtral/. ## Citation Please consider cite our paper if you use the resource of this repository. Paper link: https://arxiv.org/abs/2403.01851 ``` @article{chinese-mixtral, title={Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral}, author={Cui, Yiming and Yao, Xin}, journal={arXiv preprint arXiv:2403.01851}, url={https://arxiv.org/abs/2403.01851}, year={2024} } ```
allenai/OLMo-7B-SFT
allenai
"2024-06-25T19:40:43Z"
1,360
3
transformers
[ "transformers", "pytorch", "hf_olmo", "text-generation", "conversational", "custom_code", "en", "dataset:allenai/dolma", "dataset:allenai/tulu-v2-sft-mixture", "arxiv:2402.00838", "license:apache-2.0", "autotrain_compatible", "region:us" ]
text-generation
"2024-02-23T19:09:49Z"
--- license: apache-2.0 datasets: - allenai/dolma - allenai/tulu-v2-sft-mixture language: - en --- <img src="https://allenai.org/olmo/olmo-7b-animation.gif" alt="OLMo Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/> # Model Card for OLMo 7B SFT <!-- Provide a quick summary of what the model is/does. --> **For transformers versions v4.40.0 or newer, we suggest using [OLMo 7B SFT HF](https://huggingface.co/allenai/OLMo-7B-SFT-hf) instead.** OLMo is a series of **O**pen **L**anguage **Mo**dels designed to enable the science of language models. The OLMo base models are trained on the [Dolma](https://huggingface.co/datasets/allenai/dolma) dataset. The adapted versions are trained on the [Tulu SFT mixture](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture) and, for the Instruct version, a [cleaned version of the UltraFeedback dataset](https://huggingface.co/datasets/allenai/ultrafeedback_binarized_cleaned). We release all code, checkpoints, logs (coming soon), and details involved in training these models. OLMo 7B Instruct and OLMo SFT are two adapted versions of these models trained for better question answering. They show the performance gain that OLMo base models can achieve with existing fine-tuning techniques. *Note:* This model requires installing `ai2-olmo` with pip and using HuggingFace Transformers<=4.39. New versions of the model will be released soon with compatibility improvements. ## Model Details We release two adapted model versions: The base models related to this adapted model are the following: | Model | Training Method(s) | Datasets | Context Length | |------|--------|---------|--| | [OLMo 7B SFT](https://huggingface.co/allenai/OLMo-7B-SFT) | SFT | [Tulu 2 SFT Mix](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture) | 2048 | | [OLMo 7B Instruct](https://huggingface.co/allenai/OLMo-7B-Instruct) | SFT + DPO | [Tulu 2 SFT Mix](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture) + [Ultrafeedback Cleaned](https://huggingface.co/datasets/allenai/ultrafeedback_binarized_cleaned) | 2048 | The base models related to this adapted model are the following: | Size | Training Tokens | Layers | Hidden Size | Attention Heads | Context Length | |------|--------|---------|-------------|-----------------|----------------| | [OLMo 1B](https://huggingface.co/allenai/OLMo-1B) | 3 Trillion |16 | 2048 | 16 | 2048 | | [OLMo 7B](https://huggingface.co/allenai/OLMo-7B) | 2.5 Trillion | 32 | 4096 | 32 | 2048 | | [OLMo 7B Twin 2T](https://huggingface.co/allenai/OLMo-7B-Twin-2T) | 2 Trillion | 32 | 4096 | 32 | 2048 | ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** Allen Institute for AI (AI2) - **Supported by:** Databricks, Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University, AMD, CSC (Lumi Supercomputer), UW - **Model type:** a Transformer style autoregressive language model. - **Language(s) (NLP):** English - **License:** The code and model are released under Apache 2.0. - **Contact:** Technical inquiries: `olmo at allenai dot org`. Press: `press at allenai dot org` - **Date cutoff:** Feb./March 2023 based on Dolma dataset version. ### Model Sources <!-- Provide the basic links for the model. --> - **Project Page:** https://allenai.org/olmo - **Repositories:** - Core repo (training, inference, fine-tuning etc.): https://github.com/allenai/OLMo - Evaluation code: https://github.com/allenai/OLMo-Eval - Further fine-tuning code: https://github.com/allenai/open-instruct - **Paper:** [Link](https://arxiv.org/abs/2402.00838) - **Technical blog post:** https://blog.allenai.org/olmo-open-language-model-87ccfc95f580 - **W&B Logs:** https://wandb.ai/ai2-llm/OLMo-7B/reports/OLMo-7B--Vmlldzo2NzQyMzk5 <!-- - **Press release:** TODO --> ## 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. --> ### Inference Quickly get inference running with the following required installation: ```bash pip install ai2-olmo ``` Now, proceed as usual with HuggingFace: ```python from hf_olmo import OLMoForCausalLM, OLMoTokenizerFast olmo = OLMoForCausalLM.from_pretrained("allenai/OLMo-7B-SFT") tokenizer = OLMoTokenizerFast.from_pretrained("allenai/OLMo-7B-SFT") chat = [ { "role": "user", "content": "What is language modeling?" }, ] prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt") # optional verifying cuda # inputs = {k: v.to('cuda') for k,v in inputs.items()} # olmo = olmo.to('cuda') response = olmo.generate(input_ids=inputs.to(olmo.device), max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95) print(tokenizer.batch_decode(response, skip_special_tokens=True)[0]) >> '<|user|>\nWhat is language modeling?\n<|assistant|>\nLanguage modeling is a type of natural language processing (NLP) task that...' ``` Alternatively, with the pipeline abstraction: ```python import hf_olmo from transformers import pipeline olmo_pipe = pipeline("text-generation", model="allenai/OLMo-7B-SFT") print(olmo_pipe("What is language modeling?")) >> '[{'generated_text': 'What is language modeling?\nLanguage modeling is a type of natural language processing (NLP) task that...'}]' ``` Or, you can make this slightly faster by quantizing the model, e.g. `AutoModelForCausalLM.from_pretrained("allenai/OLMo-7B-SFT", torch_dtype=torch.float16, load_in_8bit=True)` (requires `bitsandbytes`). The quantized model is more sensitive to typing / cuda, so it is recommended to pass the inputs as `inputs.input_ids.to('cuda')` to avoid potential issues. Note, you may see the following error if `ai2-olmo` is not installed correctly, which is caused by internal Python check naming. We'll update the code soon to make this error clearer. ```bash raise ImportError( ImportError: This modeling file requires the following packages that were not found in your environment: hf_olmo. Run `pip install hf_olmo` ``` ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> Core model results for the 7B adapted models are found below. | Model | MMLU 0-shot ↑ | AlpacaEval %win ↑ | ToxiGen % Toxic ↓ | TruthfulQA %Info+True ↑ | |-----------------------|---------------|--------------------|--------------------|-------------------------| | **OLMo (base)** | 28.3 | - | 81.4 | 31.6 | | MPT Chat | 33.8 | 46.8 | 0.1 | 42.7 | | Falcon Instruct | 25.2 | 14.0 | 70.7 | 27.2 | | RPJ-INCITE Chat | 27.0 | 38.0 | 46.4 | 53.0 | | Llama-2-Chat 7B | 46.8 | 87.3 | 0.0 | 26.3 | | AI2 Tulu 2 7B | 50.4 | 73.9 | 7.0 | 51.7 | | AI2 Tulu 2 7B DPO | 50.7 | 85.1 | 0.5 | - * | | **[OLMo 7B SFT](https://huggingface.co/allenai/OLMo-7B-SFT)** | 47.3 | 57.0 | 14.4 | 41.2 | | **[OLMo 7B Instruct](https://huggingface.co/allenai/OLMo-7B-Instruct)** | 46.2 | 69.3 | 1.7 | 52.0 | *Following Ivison et al. 2023, we do not report Tulu 2 TruthfulQA scores due to test set contamination. ## Model Details ### Data For training data details, please see the [Dolma](https://huggingface.co/datasets/allenai/dolma), [Tulu 2](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture), and [UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) documentation. ### Architecture ### Hyperparameters The hyperparameters for SFT training are below: | | Learning Rate | Beta | Epochs | Warmup | Weight Decay | Gradient Clipping | Maximum Sequence Length | |-------------------------|---------------|------|--------|------------------------------------------------------------------------|--------------|-------------------|-------------------------| | **SFT** | 2 × 10^-6 | N/A | 3 | Linear warmup for the first 3% of total training time, then cooldown to 0 | 0 | 0 | 2048 | Compared to Tulu 2, SFT uses a lower LR, 3 epochs instead of 2, and 2048 length instead of 8192. ## Bias, Risks, and Limitations This adapted OLMo model is a research artifact. It is intended to benefit the research community interested in understanding the safety properties of LLMs and developers building safety tools for LLMs. For this reason, the model does not include a specific safety filter or safety training data. While our model scores well relative to its peers on ToxiGen, it is possible for the model to generate harmful and sensitive content from some user prompts. We recommend developers exercise caution and consider the risks of the applications of this technology. Furthermore, developers should consider implementing safeguards for biases, privacy, and other potential harms when appropriate. Finally, as with every LLM, OLMo may produce factual-sounding outputs that may not be true, so developers and users are encouraged to confirm such outputs before relying on them. All users of this model are responsible for how they use the model. ## Citation **BibTeX:** ``` @article{Groeneveld2023OLMo, title={OLMo: Accelerating the Science of Language Models}, author={Groeneveld, Dirk and Beltagy, Iz and Walsh, Pete and Bhagia, Akshita and Kinney, Rodney and Tafjord, Oyvind and Jha, Ananya Harsh and Ivison, Hamish and Magnusson, Ian and Wang, Yizhong and Arora, Shane and Atkinson, David and Authur, Russell and Chandu, Khyathi and Cohan, Arman and Dumas, Jennifer and Elazar, Yanai and Gu, Yuling and Hessel, Jack and Khot, Tushar and Merrill, William and Morrison, Jacob and Muennighoff, Niklas and Naik, Aakanksha and Nam, Crystal and Peters, Matthew E. and Pyatkin, Valentina and Ravichander, Abhilasha and Schwenk, Dustin and Shah, Saurabh and Smith, Will and Subramani, Nishant and Wortsman, Mitchell and Dasigi, Pradeep and Lambert, Nathan and Richardson, Kyle and Dodge, Jesse and Lo, Kyle and Soldaini, Luca and Smith, Noah A. and Hajishirzi, Hannaneh}, journal={Preprint}, year={2024} } ``` **APA:** Groeneveld, D., Beltagy, I., Walsh, P., Bhagia, A., Kinney, R., Tafjord, O., Jha, A., Ivison, H., Magnusson, I., Wang, Y., Arora, S., Atkinson, D., Authur, R., Chandu, K., Cohan, A., Dumas, J., Elazar, Y., Gu, Y., Hessel, J., Khot, T., Merrill, W., Morrison, J., Muennighoff, N., Naik, A., Nam, C., Peters, M., Pyatkin, V., Ravichander, A., Schwenk, D., Shah, S., Smith, W., Subramani, N., Wortsman, M., Dasigi, P., Lambert, N., Richardson, K., Dodge, J., Lo, K., Soldaini, L., Smith, N., & Hajishirzi, H. (2024). OLMo: Accelerating the Science of Language Models. Preprint. ## Model Card Contact For errors in this model card, contact Nathan or Jacob, `{nathanl, jacobm} at allenai dot org`.
TRI-ML/mamba-7b-rw
TRI-ML
"2024-05-22T23:38:27Z"
1,360
48
openlm
[ "openlm", "pytorch", "safetensors", "mamba", "linear", "text-generation", "en", "dataset:tiiuae/falcon-refinedweb", "arxiv:2312.00752", "arxiv:2405.06640", "license:apache-2.0", "model-index", "region:us" ]
text-generation
"2024-04-08T17:38:07Z"
--- license: apache-2.0 datasets: - tiiuae/falcon-refinedweb pipeline_tag: text-generation library_name: openlm tags: - mamba - linear language: - en model-index: - name: mamba-7b results: - task: type: text-generation dataset: type: MMLU name: MMLU metrics: - name: accuracy type: accuracy value: 33.3 verified: false - task: type: text-generation dataset: type: HellaSwag name: HellaSwag metrics: - name: accuracy type: accuracy value: 77.9 verified: false - task: type: text-generation dataset: type: PIQA name: PIQA metrics: - name: accuracy type: accuracy value: 81.0 verified: false - task: type: text-generation dataset: type: Winogrande name: Winogrande metrics: - name: accuracy type: accuracy value: 71.8 verified: false - task: type: text-generation dataset: type: ai2_arc name: ARC-E metrics: - name: accuracy type: accuracy value: 77.5 verified: false - task: type: text-generation dataset: type: ai2_arc name: ARC-C metrics: - name: accuracy type: accuracy value: 46.7 verified: false --- # Mamba-7B This is a 7B parameter model with the [Mamba](https://arxiv.org/abs/2312.00752) architecture, trained on multiple epochs (1.2T tokens) of the [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) dataset. Mamba is a state-space model that does not use self-attention unlike the standard transformer architecture. It has shown strong performance on various natural language benchmarks. To date, the largest publicly released pure-Mamba pretrain is [Mamba-2.8B](https://huggingface.co/state-spaces/mamba-2.8b). We follow their training recipe and release our version of Mamba-7B. This model was trained as a baseline for our paper [Linearizing Large Language Models](https://arxiv.org/abs/2405.06640). ## Model Details - **Developed by**: [Toyota Research Institute](https://www.tri.global/our-work/robotics) - **Model Type**: This is an auto-regressive language model based on the [Mamba](https://arxiv.org/abs/2312.00752) architecture. - **Dataset**: Trained on 1.2T tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) - **Tokenizer**: `EleutherAI/gpt-neox-20b` - **Library**: [OpenLM](https://github.com/mlfoundations/open_lm/) - **License**: This model is licensed under [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0). | Parameters | Hidden Size | Layers | Vocab Size | Sequence Length | |------------|-------------|--------| ---------- | --------------- | | 7B | 4096 | 64 | 50432 | 2048 | ## Training Details - Mamba-7B was trained using AWS SageMaker on 128 H100 80GB GPUs. - Training began in March 2024 and lasted three weeks. | **Hyperparameter** | **Value** | |--------------------|------------| | Precision | `bfloat16` | | Optimizer | AdamW | | Learning rate | 3e-4 | | LR cooldown end | 1e-5 | | Warmup steps | 2000 | | Z-loss | 1e-4 | | Batch size | 2M | ## Usage This model was trained using [OpenLM](https://github.com/mlfoundations/open_lm/). The weights have been converted to be compatible with HuggingFace. ```python from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("tri-ml/mamba-7b-rw") model = AutoModelForCausalLM.from_pretrained("tri-ml/mamba-7b-rw") inputs = tokenizer(["The Toyota Supra"], return_tensors="pt") gen_kwargs = {"max_new_tokens": 50, "top_p": 0.8, "temperature": 0.8, "do_sample": True, "repetition_penalty": 1.1} output = model.generate(inputs['input_ids'], **gen_kwargs) output = tokenizer.decode(output[0].tolist(), skip_special_tokens=True) print(output) # The Toyota Supra is a sports car that has been in production since 1978. The car was discontinued in 2002, but it has recently been revived and will be available again in 2020. The Supra has always been known for its powerful engines and agile handling. ``` ## Performance Evaluation Our evaluations were done using the [Eleuther LM Eval Harness](https://github.com/EleutherAI/lm-evaluation-harness) repo. Below we report the performance of Mamba 7B compared to other base models. <style> .evalTable th { background: white; } .evalTable tr:nth-child(1) { background: #f3f3f3; } .evalTable tr:nth-child(2) { background: #f3f3f3; } .evalTable tr:nth-child(7) { background: #f3f3f3; } </style> <div class="evalTable"> | | HellaSwag | PIQA | Winogrande | ARC-E | ARC-C | MMLU (5-shot) | | ----------------- | ------------- | -------- | -------------- | --------- | --------- | ---------------- | | Mamba-1.4B | 59.0 | 73.9 | 61.4 | 65.5 | 32.9 | 25.2 | | Mamba-2.8B | 71.0 | 78.1 | 65.9 | 68.2 | 41.7 | 26.2 | | RWKV5-1.7T-7B | 73.0 | 78.6 | 72.9 | 75.8 | 45.6 | 34.9 | | Llama2-7B | 76.0 | 79.1 | 69.1 | 76.3 | 46.3 | 45.9 | | Gemma-7B | 80.7 | 81.9 | 73.7 | 81.1 | 53.2 | 62.9 | | Mistral-7B | 81.0 | 82.1 | 74.0 | 80.9 | 53.8 | 62.4 | | **Mamba-7B** | 77.9 | 81.0 | 71.8 | 77.5 | 46.7 | 33.3 | </div> ## How to Cite If you use this model, please cite our paper on [Linearizing Large Language Models](https://arxiv.org/abs/2405.06640). ``` @article{Mercat2024Linearizing, title={Linearizing Large Language Models}, author={Jean Mercat and Igor Vasiljevic and Sedrick Keh and Kushal Arora and Achal Dave and Adrien Gaidon and Thomas Kollar}, journal={arXiv preprint arXiv:2405.06640}, year={2024} } ``` ## Citations Mamba ``` @article{mamba, title={Mamba: Linear-Time Sequence Modeling with Selective State Spaces}, author={Gu, Albert and Dao, Tri}, journal={arXiv preprint arXiv:2312.00752}, year={2023} } ``` OpenLM ``` @misc{open_lm, author = {Gururangan, Suchin and Wortsman, Mitchell and Gadre, Samir Yitzhak and Dave, Achal and Kilian, Maciej and Shi, Weijia and Mercat, Jean and Smyrnis, Georgios and Ilharco, Gabriel and Jordan, Matt and Heckel, Reinhard and Dimakis, Alex and Farhadi, Ali and Shankar, Vaishaal and Schmidt, Ludwig}, title = {{open_lm}: a minimal but performative language modeling (LM) repository}, year = {2023}, note = {GitHub repository}, url = {https://github.com/mlfoundations/open_lm/} } ```
timm/vit_large_patch14_clip_224.laion2b_ft_in12k_in1k
timm
"2023-05-06T00:11:16Z"
1,359
0
timm
[ "timm", "pytorch", "safetensors", "image-classification", "dataset:imagenet-1k", "dataset:laion-2b", "dataset:imagenet-12k", "arxiv:2212.07143", "arxiv:2210.08402", "arxiv:2010.11929", "license:apache-2.0", "region:us" ]
image-classification
"2022-11-01T23:01:48Z"
--- tags: - image-classification - timm library_name: timm license: apache-2.0 datasets: - imagenet-1k - laion-2b - imagenet-12k --- # Model card for vit_large_patch14_clip_224.laion2b_ft_in12k_in1k A Vision Transformer (ViT) image classification model. Pretrained on LAION-2B image-text pairs using OpenCLIP. Fine-tuned on ImageNet-12k and then ImageNet-1k in `timm`. See recipes in [Reproducible scaling laws](https://arxiv.org/abs/2212.07143). ## Model Details - **Model Type:** Image classification / feature backbone - **Model Stats:** - Params (M): 304.2 - GMACs: 77.8 - Activations (M): 57.1 - Image size: 224 x 224 - **Papers:** - OpenCLIP: https://github.com/mlfoundations/open_clip - Reproducible scaling laws for contrastive language-image learning: https://arxiv.org/abs/2212.07143 - LAION-5B: An open large-scale dataset for training next generation image-text models: https://arxiv.org/abs/2210.08402 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 - **Dataset:** ImageNet-1k - **Pretrain Dataset:** - LAION-2B - ImageNet-12k ## 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('vit_large_patch14_clip_224.laion2b_ft_in12k_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( 'vit_large_patch14_clip_224.laion2b_ft_in12k_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, 257, 1024) 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 @software{ilharco_gabriel_2021_5143773, author = {Ilharco, Gabriel and Wortsman, Mitchell and Wightman, Ross and Gordon, Cade and Carlini, Nicholas and Taori, Rohan and Dave, Achal and Shankar, Vaishaal and Namkoong, Hongseok and Miller, John and Hajishirzi, Hannaneh and Farhadi, Ali and Schmidt, Ludwig}, title = {OpenCLIP}, month = jul, year = 2021, note = {If you use this software, please cite it as below.}, publisher = {Zenodo}, version = {0.1}, doi = {10.5281/zenodo.5143773}, url = {https://doi.org/10.5281/zenodo.5143773} } ``` ```bibtex @article{cherti2022reproducible, title={Reproducible scaling laws for contrastive language-image learning}, author={Cherti, Mehdi and Beaumont, Romain and Wightman, Ross and Wortsman, Mitchell and Ilharco, Gabriel and Gordon, Cade and Schuhmann, Christoph and Schmidt, Ludwig and Jitsev, Jenia}, journal={arXiv preprint arXiv:2212.07143}, year={2022} } ``` ```bibtex @inproceedings{schuhmann2022laionb, title={{LAION}-5B: An open large-scale dataset for training next generation image-text models}, author={Christoph Schuhmann and Romain Beaumont and Richard Vencu and Cade W Gordon and Ross Wightman and Mehdi Cherti and Theo Coombes and Aarush Katta and Clayton Mullis and Mitchell Wortsman and Patrick Schramowski and Srivatsa R Kundurthy and Katherine Crowson and Ludwig Schmidt and Robert Kaczmarczyk and Jenia Jitsev}, booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track}, year={2022}, url={https://openreview.net/forum?id=M3Y74vmsMcY} } ``` ```bibtex @article{dosovitskiy2020vit, title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale}, author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil}, journal={ICLR}, year={2021} } ``` ```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}} } ```
quantumaikr/KoreanLM
quantumaikr
"2023-05-04T10:16:45Z"
1,359
25
transformers
[ "transformers", "pytorch", "llama", "text-generation", "vicuna", "ko", "en", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-05-03T07:37:23Z"
--- language: - ko - en pipeline_tag: text-generation tags: - vicuna - llama --- <p align="center" width="100%"> <img src="https://i.imgur.com/snFDU0P.png" alt="KoreanLM icon" style="width: 500px; display: block; margin: auto; border-radius: 10%;"> </p> # KoreanLM: 한국어 언어모델 프로젝트 KoreanLM은 한국어 언어모델을 개발하기 위한 오픈소스 프로젝트입니다. 현재 대부분의 언어모델들은 영어에 초점을 맞추고 있어, 한국어에 대한 학습이 상대적으로 부족하고 토큰화 과정에서 비효율적인 경우가 있습니다. 이러한 문제를 해결하고 한국어에 최적화된 언어모델을 제공하기 위해 KoreanLM 프로젝트를 시작하게 되었습니다. ## 프로젝트 목표 1. 한국어에 특화된 언어모델 개발: 한국어의 문법, 어휘, 문화적 특성을 반영하여 한국어를 더 정확하게 이해하고 생성할 수 있는 언어모델을 개발합니다. 2. 효율적인 토큰화 방식 도입: 한국어 텍스트의 토큰화 과정에서 효율적이고 정확한 분석이 가능한 새로운 토큰화 방식을 도입하여 언어모델의 성능을 향상시킵니다. 3. 거대 언어모델의 사용성 개선: 현재 거대한 사이즈의 언어모델들은 기업이 자사의 데이터를 파인튜닝하기 어려운 문제가 있습니다. 이를 해결하기 위해 한국어 언어모델의 크기를 조절하여 사용성을 개선하고, 자연어 처리 작업에 더 쉽게 적용할 수 있도록 합니다. ## 사용 방법 KoreanLM은 GitHub 저장소를 통해 배포됩니다. 프로젝트를 사용하려면 다음과 같은 방법으로 설치하실 수 있습니다. ```bash git clone https://github.com/quantumaikr/KoreanLM.git cd KoreanLM pip install -r requirements.txt ``` ## 예제 다음은 transformers 라이브러리를 통해 모델과 토크나이저를 로딩하는 예제입니다. ```python import transformers model = transformers.AutoModelForCausalLM.from_pretrained("quantumaikr/KoreanLM") tokenizer = transformers.AutoTokenizer.from_pretrained("quantumaikr/KoreanLM") ``` ## 훈련 (파인튜닝) ```bash torchrun --nproc_per_node=4 --master_port=1004 train.py \ --model_name_or_path quantumaikr/KoreanLM \ --data_path korean_data.json \ --num_train_epochs 3 \ --cache_dir './data' \ --bf16 True \ --tf32 True \ --per_device_train_batch_size 4 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 8 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 500 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --fsdp "full_shard auto_wrap" \ --fsdp_transformer_layer_cls_to_wrap 'OPTDecoderLayer' \ ``` ```bash pip install deepspeed torchrun --nproc_per_node=4 --master_port=1004 train.py \ --deepspeed "./deepspeed.json" \ --model_name_or_path quantumaikr/KoreanLM \ --data_path korean_data.json \ --num_train_epochs 3 \ --cache_dir './data' \ --bf16 True \ --tf32 True \ --per_device_train_batch_size 4 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 8 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 2000 \ --save_total_limit 1 \ --learning_rate 2e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ ``` ## 훈련 (LoRA) ```bash python finetune-lora.py \ --base_model 'quantumaikr/KoreanLM' \ --data_path './korean_data.json' \ --output_dir './KoreanLM-LoRA' \ --cache_dir './data' ``` ## 추론 ```bash python generate.py \ --load_8bit \ --share_gradio \ --base_model 'quantumaikr/KoreanLM' \ --lora_weights 'quantumaikr/KoreanLM-LoRA' \ --cache_dir './data' ``` ## 사전학습 모델 공개 및 웹 데모 [학습모델](https://huggingface.co/quantumaikr/KoreanLM/tree/main) <i>* 데모 링크는 추후 공계예정</i> ## 기여방법 1. 이슈 제기: KoreanLM 프로젝트와 관련된 문제점이나 개선사항을 이슈로 제기해주세요. 2. 코드 작성: 개선사항이나 새로운 기능을 추가하기 위해 코드를 작성하실 수 있습니다. 작성된 코드는 Pull Request를 통해 제출해주시기 바랍니다. 3. 문서 작성 및 번역: 프로젝트의 문서 작성이나 번역 작업에 참여하여 프로젝트의 질을 높여주세요. 4. 테스트 및 피드백: 프로젝트를 사용하면서 발견한 버그나 개선사항을 피드백해주시면 큰 도움이 됩니다. ## 라이선스 KoreanLM 프로젝트는 Apache 2.0 License 라이선스를 따릅니다. 프로젝트를 사용하실 때 라이선스에 따라 주의사항을 지켜주시기 바랍니다. ## 기술 문의 KoreanLM 프로젝트와 관련된 문의사항이 있으시면 이메일 또는 GitHub 이슈를 통해 문의해주시기 바랍니다. 이 프로젝트가 한국어 언어모델에 대한 연구와 개발에 도움이 되길 바라며, 많은 관심과 참여 부탁드립니다. 이메일: [email protected] --- This repository has implementations inspired by [open_llama](https://github.com/openlm-research/open_llama), [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) and [alpaca-lora](https://github.com/tloen/alpaca-lora) projects.
jondurbin/spicyboros-70b-2.2
jondurbin
"2023-09-13T20:29:25Z"
1,359
13
transformers
[ "transformers", "pytorch", "llama", "text-generation", "not-for-all-audiences", "dataset:jondurbin/airoboros-2.2", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-09-13T15:45:42Z"
--- license: llama2 datasets: - jondurbin/airoboros-2.2 tags: - not-for-all-audiences --- ### Overview __Usage restriction: To use this model, you must agree to the following:__ - Some of the content than can be produced is "toxic"/"harmful", and contains profanity and other types of sensitive content. - None of the content or views contained in the dataset or generated outputs necessarily align with my personal beliefs or opinions, they are simply text generated by LLMs and/or scraped from the web. - Use with extreme caution, particularly in locations with less-than-free speech laws. - You, and you alone are responsible for having downloaded and generated outputs with the model and I am completely indemnified from any and all liabilities. __Ok, now that the warning is out of the way...__ Another experimental model, using mostly sythetic data generated by [airoboros](https://github.com/jondurbin/airoboros) Highlights: - The prompt format has changed! It is now newlines instead of spaces between system/USER/ASSISTANT (see prompt info below). - This version also includes "de-alignment" data, to enable less savory interactions and outputs. - To learn more about the dataset, see: https://hf.co/datasets/jondurbin/airoboros-2.2 (this is the instructions.jsonl file, not instructions-clean.jsonl) - I re-generated all of the outputs in the dataset that had "Once upon a time" so they'd be less cliche - no guarantees that won't still happen, but in theory it may happen less. - More multiple choice, better awareness, some alignment for normal use case but system-prompt overridable etc. __WARNING: This model will gladly spew profane and otherwise NSFW content, if asked, use with care.__ Breakdown of the training data: | Count | Category | |--------|----------------------------| | 60 | quiz | | 63 | card | | 100 | detailed\_writing | | 103 | experience | | 114 | greeting | | 200 | song | | 204 | editor | | 250 | counterfactual\_contextual | | 268 | cot | | 339 | theory\_of\_mind | | 460 | misconception | | 500 | summarization | | 573 | awareness | | 715 | riddle | | 719 | agent | | 800 | plan | | 873 | gtkm | | 966 | rp | | 1000 | stylized\_response | | 1000 | wordgame | | 1279 | multiple\_choice | | 1641 | joke | | 1785 | writing | | 2155 | contextual | | 2364 | roleplay | | 2508 | trivia | | 5216 | general | | 5779 | coding | | 11367 | orca | In other words, it's a fairly general purpose model, but focuses fairly heavily on instruction response pairs rather than casual chat/roleplay. *Why do I try to remove censorship?* - laws vary widely based on time and location - language model may conflate certain words with laws, e.g. it may think "stealing eggs from a chicken" is illegal - these models just produce text, what you do with that text is your resonsibility - many people and industries deal with "sensitive" content; imagine if a court stenographer's equipment filtered illegal content - it would be useless Huge thank you to the folks over at [a16z](https://a16z.com/) for sponsoring the costs associated with building models and associated tools! ### Prompt format The prompt format: ``` A chat. USER: {prompt} ASSISTANT: ``` The default system prompt ("A chat.") was used for most of the prompts, however it also included a wide sampling of responses with other prompts, particularly in "stylized\_response", "rp", "gtkm", etc. Here's another example: ``` A chat between Bob (aka USER) and Tom (aka ASSISTANT). Tom is an extremely intelligent 18th century bookkeeper, who speaks loquaciously. USER: {prompt} ASSISTANT: ``` And chat scenario that wouldn't require USER/ASSISTANT (but should use stopping criteria to prevent the model from speaking on your behalf). ``` A chat between old friends: Timmy and Tommy. {description of characters} {setting for the chat} Timmy: *takes a big sip from his coffee* "Ah, sweet, delicious, magical coffee." Tommy: ``` __*I strongly suggest adding stopping criteria/early inference stopping on "USER:", and/or whatever names you specify in the system prompt.*__ ### Fine-tuning details https://gist.github.com/jondurbin/51a336c582a224de197ba1d2c6b1da97 *Note: I used checkpoint 750 for final model!* ### Helpful usage tips *The prompts shown here are are just the text that would be included after USER: and before ASSISTANT: in the full prompt format above, the system prompt and USER:/ASSISTANT: have been omited for readability.* #### Context obedient question answering By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: ``` BEGININPUT BEGINCONTEXT [key0: value0] [key1: value1] ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION ``` It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. *The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!* I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: ``` BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ``` And the response: ``` Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 ``` #### Coding You can ask for fairly complex coding instructions with multiple criteria, e.g.: ``` Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate ``` Or inline criteria: ``` Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. ``` You can also optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.: ``` Write a websocket application in node.js. PLAINFORMAT ``` #### Agent/function calling The dataset includes many examples of function/args generation based on input criteria. This is somewhat similar to the OpenAI function calling, but the output is either JSON or YAML. Example prompt: ``` As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format. Input: I want to know how many times 'Python' is mentioned in my text file. Available functions: file_analytics: description: This tool performs various operations on a text file. params: action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc. filters: keyword: The word or phrase we want to search for. ``` Response: ```json { "function": "file_analytics", "params": { "action": "count_occurrences", "filters": { "keyword": "Python" } } } ``` #### Chain-of-thought You can ask for several possible responses to a given problem, with a ranking and final answer selection. Example prompt: ``` A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one. ``` Example response: ``` Solution 1: In a round-robin tournament, each player plays every other player exactly once. This means that the total number of games played is equal to the combination of all players taken two at a time (since a game involves two players). The formula for combinations is nC2 = n(n-1)/2, where n is the total number of players. We know that nC2 equals 45 (the total number of games), so we can set up the equation as follows: n(n-1)/2 = 45 Solving this equation gives us n=10. Final answer: There were 10 players in the tournament. Solution 2: Another way to approach this problem is by using the concept of triangular numbers. Triangular numbers are a sequence of numbers where each number can be represented as a triangle with dots. The nth triangular number is given by the sum of the first n natural numbers. If we consider each game as a dot and each player as a side of the triangle, then the total number of games (45) would correspond to the 9th triangular number because 1+2+3+4+5+6+7+8+9=45. However, since each side of the triangle represents a player, and there's one more player than sides in our model (because the last player has no one left to play against), we need to add one more to get the total number of players. Final answer: There were 10 players in the tournament. Solution 3: We could also use trial and error to solve this problem. Starting from a small number of players, we calculate how many games would be played in a round-robin tournament until we reach 45 games. For example, with 2 players, only 1 game is played; with 3 players, 3 games are played; with 4 players, 6 games are played, and so on. Continuing this process, we find that with 10 players, 45 games are played. Final answer: There were 10 players in the tournament. Ranking of solutions from best to worst: 1. Solution 1: This solution uses direct mathematical reasoning based on the properties of a round-robin tournament and solves an equation to find the answer. 2. Solution 2: This solution uses the concept of triangular numbers which requires additional steps and knowledge beyond the immediate problem context, but still arrives at the correct answer. 3. Solution 3: This solution relies on trial and error, which is less efficient and reliable than the other methods, but it eventually gets to the right answer. Best and final answer: There were 10 players in the tournament. ``` #### reWOO style execution planning The model now supports execution planning for complex instructions that would require making use of several tools. The output is just the plan, you must implement a mechanism to parse the output and actually call the functions! Example prompt: ``` Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string that could be the user's question, one or more prior evidence values, or a combination of both. Here are the tools available to be called: DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer. TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links. HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links. KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:? The output should be in format: Plan: [first action to take based on input question] :evidence0: = [function to call with input parameter] Plan: [next action to take, based on result of :evidence0:] :evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"] ... Answer: [:evidence[n]: containing the final answer.] Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work? ``` Response: ``` Plan: Begin by conducting a web search to find out who won the Nobel Prize in Literature in 2020. :evidence0: = DuckDuckGo[Nobel Prize in Literature 2020 winner] Plan: Utilize the KnowledgeModel to interpret the search results and find the name of the laureate. :evidence1: = KnowledgeModel[Who won the Nobel Prize in Literature in 2020, given :evidence0:?] Plan: Conduct another web search to find the most famous work of the identified laureate. :evidence2: = DuckDuckGo[Most famous work of :evidence1:] Plan: Extract the relevant links from the DuckDuckGo search results for a more focused search. :evidence3: = HyperlinkExtractor[:evidence2:] Plan: Use the TextScraper tool to extract information from the relevant links. :evidence4: = TextScraper[:evidence3:] Plan: Finally, utilize the KnowledgeModel to identify and summarize the most famous work of the laureate from the extracted information. :evidence5: = KnowledgeModel[What is the most famous work of :evidence1:, given :evidence4:?] Answer: :evidence5: ``` For this to be useful, you'd have to parse the output plan text, and implement/call each of the functions. This is just pseudo-code, completely untested off the top of my head, and obviously would requiring full implementation + hardening: ```python import re import requests def inject_context(input_text, **context): for ref in set(re.findall(r"(:evidence[0-9]+:)", input_text, re.I)): input_text = input_text.replace(ref, context.get(ref, "")) return input_text def duckduckgo(input_text, **context): search_string = inject_context(input_text, **context) ... search via duck duck go using search_string ... return text content def link_extractor(input_text, **context): input_text = inject_context(input_text, **context) return "\n".join(list(set(re.findall(r"(https?://[^\s]+?\.?)", input_text, re.I)))) def scrape(input_text, **context): input_text = inject_context(input_text, **context) text = [] for link in input_text.splitlines(): text.append(requests.get(link).text) return "\n".join(text) def infer(input_text, **context) prompt = inject_context(input_text, **context) ... call model with prompt, return output def parse_plan(plan): method_map = { "DuckDuckGo": duckduckgo, "HyperlinkExtractor": link_extractor, "KnowledgeModel": infer, "TextScraper": scrape, } context = {} for line in plan.strip().splitlines(): if line.startswith("Plan:"): print(line) continue parts = re.match("^(:evidence[0-9]+:)\s*=\s*([^\[]+])(\[.*\])\s$", line, re.I) if not parts: if line.startswith("Answer: "): return context.get(line.split(" ")[-1].strip(), "Answer couldn't be generated...") raise RuntimeError("bad format: " + line) context[parts.group(1)] = method_map[parts.group(2)](parts.group(3), **context) ``` ### 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 The airoboros 2.2 models are built on top of llama-2/codellama. The llama-2 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 mostly 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.
chargoddard/servile-harpsichord-cdpo
chargoddard
"2023-12-10T03:59:17Z"
1,359
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "dataset:pankajmathur/orca_mini_v1_dataset", "dataset:openai/summarize_from_feedback", "dataset:PygmalionAI/PIPPA", "dataset:chargoddard/rpguild", "dataset:lemonilia/LimaRP", "dataset:PKU-Alignment/PKU-SafeRLHF", "dataset:Intel/orca_dpo_pairs", "dataset:allenai/ultrafeedback_binarized_cleaned", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-09T05:31:44Z"
--- license: cc-by-nc-4.0 datasets: - pankajmathur/orca_mini_v1_dataset - openai/summarize_from_feedback - PygmalionAI/PIPPA - chargoddard/rpguild - lemonilia/LimaRP - PKU-Alignment/PKU-SafeRLHF - Intel/orca_dpo_pairs - allenai/ultrafeedback_binarized_cleaned --- Trained on a different random sampling of the same datasets used by [loyal-piano-m7](https://huggingface.co/chargoddard/loyal-piano-m7), then with cDPO on a blend of RLHF datasets. Several intermediate checkpoints (of cDPO training) are on branches. Uses the Alpaca prompt format.
Fredithefish/MadMix-v0.1
Fredithefish
"2023-12-12T01:23:10Z"
1,359
2
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "openchat", "7b", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-12T00:36:13Z"
--- license: apache-2.0 language: - en library_name: transformers tags: - mistral - merge - openchat - 7b --- <div align="center"> <img src="https://huggingface.co/Fredithefish/MadMix-v0.1/resolve/main/logo.jpg" alt="Alt Text" width="450"/> <h1>🔥 MadMix: Merging the top Seven Billion-Parameter Mistral-Based Open Source Models 🔥</h1> This Model is a merge between various high-quality open-source models, it was done by using the <a>https://github.com/cg123/mergekit</a> repository </div> <br><br> # Details - **Models included in the merge:** - [OpenChat_3.5](https://huggingface.co/openchat/openchat_3.5) - [OpenHermes-2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) - [Neural-chat 7b v3.1](https://huggingface.co/Intel/neural-chat-7b-v3-1) - [Marcoroni-7B](https://huggingface.co/AIDC-ai-business/Marcoroni-7B-v3) # Evals (soon...)
zyh3826/20231206094523-pretrain-Llama-2-13b-hf-76000
zyh3826
"2023-12-14T02:53:45Z"
1,359
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "zh", "en", "dataset:YeungNLP/firefly-pretrain-dataset", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-13T01:26:37Z"
--- license: llama2 datasets: - YeungNLP/firefly-pretrain-dataset language: - zh - en --- # Model Details + Developed by: zyh3826 + Backbone Model: llama-2-13B + Library: HuggingFace Transformers # Limitations & Biases: Llama2 and fine-tuned 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, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model. Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-use-guide/ # License Disclaimer: This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind. 全参数继续预训练中文llama2-13B，取76000步ckpt测试，其他细节待补充
jeonsworld/CarbonVillain-en-10.7B-v1
jeonsworld
"2024-01-03T16:45:39Z"
1,359
5
transformers
[ "transformers", "safetensors", "llama", "text-generation", "merge", "slerp", "conversational", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-28T20:18:45Z"
--- license: cc-by-nc-4.0 language: - en tags: - merge - slerp --- # CarbonVillain **This is a model created without learning to oppose indiscriminate carbon emissions.** This model is an experimental version created using [mergekit](https://github.com/cg123/mergekit). - merge models - Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct - VAGOsolutions/SauerkrautLM-SOLAR-Instruct - method: slerp # Prompt Template(s) ``` ### User: {user} ### Assistant: {asistant} ``` # Evaluation Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jeonsworld__CarbonVillain-en-10.7B-v1) | Metric | Value | |-----------------------|---------------------------| | Avg. | 74.28 | | ARC (25-shot) | 71.24 | | HellaSwag (10-shot) | 88.45 | | MMLU (5-shot) | 66.42 | | TruthfulQA (0-shot) | 71.97 | | Winogrande (5-shot) | 83.26 | | GSM8K (5-shot) | 64.29 |
jeonsworld/CarbonVillain-en-10.7B-v2
jeonsworld
"2024-01-03T16:45:54Z"
1,359
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "merge", "slerp", "conversational", "en", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-30T09:57:23Z"
--- license: cc-by-nc-sa-4.0 language: - en tags: - merge - slerp --- # CarbonVillain **This is a model created without learning to oppose indiscriminate carbon emissions.** This model is an experimental version created using [mergekit](https://github.com/cg123/mergekit). - merge models - Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct - kyujinpy/Sakura-SOLAR-Instruct - method: slerp # Prompt Template(s) ``` ### User: {user} ### Assistant: {asistant} ``` # Evaluation Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_jeonsworld__CarbonVillain-en-10.7B-v2) | Metric | Value | |-----------------------|---------------------------| | Avg. | 74.42 | | ARC (25-shot) | 71.25 | | HellaSwag (10-shot) | 88.4 | | MMLU (5-shot) | 66.31 | | TruthfulQA (0-shot) | 71.94 | | Winogrande (5-shot) | 83.35 | | GSM8K (5-shot) | 65.28 |
Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear
Weyaxi
"2024-01-19T14:28:17Z"
1,359
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "merge", "license:other", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-03T14:51:43Z"
--- license: other tags: - merge license_name: yi-34b license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE model-index: - name: Nous-Hermes-2-SUS-Chat-34B-Linear 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: 66.38 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear 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: 84.94 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear 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: 76.82 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear 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: 59.19 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear 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: 82.79 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear 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: 72.02 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Nous-Hermes-2-SUS-Chat-34B-Linear name: Open LLM Leaderboard --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/u0jZZVpCxq3JN8VzFXVhV.png) # Nous-Hermes-2-SUS-Chat-34B-Linear This is the model for Nous-Hermes-2-SUS-Chat-34B-Linear. I used [mergekit](https://github.com/cg123/mergekit) to merge models. # Yaml Config ```yaml models: - model: Nous-Hermes-2-Yi-34B parameters: weight: 0.5 - model: SUS-Chat-34B parameters: weight: 0.3 merge_method: linear dtype: bfloat16 ``` # [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__Nous-Hermes-2-SUS-Chat-34B-Linear) | Metric |Value| |---------------------------------|----:| |Avg. |73.69| |AI2 Reasoning Challenge (25-Shot)|66.38| |HellaSwag (10-Shot) |84.94| |MMLU (5-Shot) |76.82| |TruthfulQA (0-shot) |59.19| |Winogrande (5-shot) |82.79| |GSM8k (5-shot) |72.02|
uukuguy/speechless-mistral-moloras-7b
uukuguy
"2024-01-09T01:43:21Z"
1,359
5
transformers
[ "transformers", "safetensors", "gguf", "mistral", "text-generation", "en", "dataset:yahma/alpaca-cleaned", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-05T09:25:26Z"
--- language: - en library_name: transformers pipeline_tag: text-generation datasets: - yahma/alpaca-cleaned license: apache-2.0 --- <p><h1> speechless-mistral-moloras-7b </h1></p> * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/speechless-mistral-moloras-7B-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/speechless-mistral-moloras-7B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/speechless-mistral-moloras-7B-GGUF) [4-bit GGUF models for CPU+GPU inference](https://huggingface.co/uukuguy/speechless-mistral-moloras-7b/tree/main/GGUF) This model is the static version of moloras (Mixture-of-multi-LoRAs) based on the following 6 Mistral-based LoRa modules. - Intel/neural-chat-7b-v3-1 - migtissera/SynthIA-7B-v1.3 - jondurbin/airoboros-m-7b-3.1.2 - bhenrym14/mistral-7b-platypus-fp16 - teknium/CollectiveCognition-v1.1-Mistral-7B - uukuguy/speechless-mistral-dolphin-orca-platypus-samantha-7b Totally 6 LoRA modules from [speechless-mistral-7b-dare-0.85](https://huggingface.co/speechlessai/speechless-mistral-7b-dare-0.85) The router of mixture-of-multi-loras enables an automatic assembling of LoRA modules, using a gradientfree approach to obtain the coefficients of LoRA modules and requiring only a handful of inference steps for unseen tasks. Code: https://github.com/uukuguy/multi_loras?tab=readme-ov-file#mixture-of-multi-loras ## LM-Evaluation-Harness [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) | Metric | Value | | --- | --- | | ARC | 59.98 | | HellaSwag | 83.29 | | MMLU | 64.12 | | TruthfulQA | 42.15 | | Winogrande | 78.37 | | GSM8K | 37.68 | | Average | 60.93 |
Undi95/Borealis-10.7B-DPO
Undi95
"2024-01-20T17:13:14Z"
1,359
6
transformers
[ "transformers", "pytorch", "llama", "text-generation", "not-for-all-audiences", "nsfw", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-20T16:00:54Z"
--- license: cc-by-nc-4.0 tags: - not-for-all-audiences - nsfw --- ## Borealis ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ieXwQCpyL7AX659Z7ivxA.png) Borealis-10.7B-DPO is a 10.7B model made of 48 Mistral 7B layers, finetuned for +70h on 2xA6000 on a big RP and Conversational dataset with llama2 configuration of Axolotl, like SOLAR. This variant had a DPO train on top of it. <!-- description start --> ## Description This repo contains fp16 files of Borealis-10.7B-DPO, a conversational model. The goal of this model isn't to break all benchmark, but to have a better RP/ERP/Conversational model. It was trained on multiple basic dataset to make it intelligent, but majority of the dataset was basic conversations. <!-- description end --> <!-- description start --> ## Dataset used - NobodyExistsOnTheInternet/ToxicQAFinal - teknium/openhermes - unalignment/spicy-3.1 - Doctor-Shotgun/no-robots-sharegpt - Undi95/toxic-dpo-v0.1-sharegpt - Aesir [1], [2], [3-SFW], [3-NSFW] - lemonilia/LimaRP - Squish42/bluemoon-fandom-1-1-rp-cleaned - Undi95/ConversationChronicles-sharegpt-SHARDED (2 sets, modified) ## DPO Dataset used - Intel/orca_dpo_pairs - NobodyExistsOnTheInternet/ToxicDPOqa - Undi95/toxic-dpo-v0.1-NoWarning <!-- description end --> <!-- prompt-template start --> ## Prompt format: NsChatml ``` <|im_system|> {sysprompt}<|im_end|> <|im_user|> {input}<|im_end|> <|im_bot|> {output}<|im_end|> ``` ## Others If you want to support me, you can [here](https://ko-fi.com/undiai).
RatanRohith/NeuralPizza-7B-V0.2
RatanRohith
"2024-01-21T19:37:34Z"
1,359
1
Transformers
[ "Transformers", "safetensors", "mistral", "text-generation", "transformers", "fine-tuned", "language-modeling", "direct-preference-optimization", "dataset:Intel/orca_dpo_pairs", "license:apache-2.0", "region:us" ]
text-generation
"2024-01-21T18:52:57Z"
--- library_name: Transformers tags: - transformers - fine-tuned - language-modeling - direct-preference-optimization datasets: - Intel/orca_dpo_pairs license: apache-2.0 --- ## Model Description NeuralPizza-7B-V0.2 is a fine-tuned version of the RatanRohith/NeuralMathChat-7B-V0.2 model, specialized through Direct Preference Optimization (DPO). It was fine-tuned using the Intel/orca_dpo_pairs dataset, focusing on enhancing model performance based on preference comparisons. ## Intended Use This model is primarily intended for research and experimental applications in language modeling, especially for exploring the Direct Preference Optimization method. It provides insights into the nuances of DPO in the context of language model tuning. ## Training Data The model was fine-tuned using the Intel/orca_dpo_pairs dataset. This dataset is designed for applying and testing Direct Preference Optimization techniques in language models.
KRAFTON/KORani-v1-13B
KRAFTON
"2023-05-08T07:24:39Z"
1,358
7
transformers
[ "transformers", "pytorch", "gpt_neox", "text-generation", "polyglot", "KoVicuna", "KORani", "ko", "en", "arxiv:2302.13971", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-04-26T06:24:09Z"
--- license: apache-2.0 language: - ko - en pipeline_tag: text-generation tags: - polyglot - KoVicuna - KORani --- # KORani-v1-13B **`v1,2,3` doesn't mean the best or most recent model** - KORani: Large Language Models for 🇰🇷 Korean and 🇺🇸 English using LLaMA 13B and Polyglot 12.8B. - Tested which LLM is effective for 🇰🇷 Korean tasks after finetuning. - More information at https://github.com/krafton-ai/KORani - This repository contains fine-tuned language model weights based on LLaMA 13B ## Release This repository contains inference code for KORani models that are based on [LLaMA 13B](https://arxiv.org/abs/2302.13971v1) and [Polyglot 12.8B](https://huggingface.co/EleutherAI/polyglot-ko-12.8b). KORani models are finetuned using [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/tree/main) & [KoVicuna](https://huggingface.co/datasets/junelee/sharegpt_deepl_ko) dataset. This work is hugely influenced by [Vicuna](https://github.com/lm-sys/FastChat) project. ### Models | Model | Base | Train dataset | Huggingface Link | | --- | ---: | ---: | ---: | | 1️⃣ KORani-v1-13B | Polyglot 12.8B | KoVicuna dataset | [Link 1](https://huggingface.co/KRAFTON/KORani-v1-13B) | | 2️⃣ KORani-v2-13B | LLaMA 13B | KoVicuna dataset | [Link 2](https://huggingface.co/KRAFTON/KORani-v2-13B) | | 3️⃣ KORani-v3-13B | LLaMA 13B | ShareGPT & KoVicuna dataset | [Link 3](https://huggingface.co/KRAFTON/KORani-v3-13B) | ## Performances We used AutoEvalGPT inspired by auto evaluation by GPT-4 from [Vicuna](https://github.com/lm-sys/FastChat). For how to evaluate, visit this GitHub -> https://github.com/krafton-ai/AutoEvalGPT ### Translation (ENG -> KOR) ``` input = ""Hey! I have some Kissflow Legal Review requests that are blocked by Tax and Accounting, can this be looked at?"" ``` | Model | Score (averaged over 5 examples) | Output Example | | --- | :---: | ---: | | GPT-4 | - | 헤이! 제가 Tax and Accounting에 의해 차단된 몇 가지 Kissflow 법률 검토 요청이 있는데, 이것을 확인해 주실 수 있나요? | | DeepL | 9.4 | 안녕하세요! 세무 및 회계에서 차단된 Kissflow 법률 검토 요청이 몇 개 있는데요, 이 요청을 살펴볼 수 있나요? | | GPT-3.5-turbo | 8.6 | 안녕하세요! 세무 및 회계 부서에서 차단된 몇 가지 Kissflow Legal Review 요청이 있습니다. 확인해 주실 수 있나요? | | Vicuna-13B | 3.8 | 안녕하세요! 세금계산과 회계부서가 차단해 있는 Kissflow Legal Review 요청이 몇 개가 있습니까? 이것을 살펴보시겠습니까? | | KoAlpaca-13B | 5.6 | 야! 세금과 회계에 막힌 키싱플로우 법적 검토 요청이 있는데, 이거 검토해줄 수 있어? | | KORani-v1 | 7.5 | 안녕하세요! 세금과 회계로 인해 막혀 있는 키스플로우 법률 검토 요청이 몇 개 있는데, 검토해 주실 수 있나요? | | KORani-v2 | 5.4 | 안녕하세요! 제가 Kissflow Legal Review 요청을 목격했는데, 세무 및 회계 부서에서 차단하고 있는데 이 문제를 조사해 주시겠어요? | | KORani-v3 | 7.1 | 안녕하세요! 저는 Kissflow Legal Review 요청이 세금과 회계에 의해 차단되고 있는데, 이 문제가 살펴볼 수 있을까요? | ### QA(Korean) ``` prompt = "우리는 아래와 같은 정보를 갖고 있습니다. --------------------- 헨리 구스타프 몰래슨(영어: Henry Gustav Molaison, 1926년 2월 26일 ~ 2008년 12월 2일)은 뇌전증을 치료하기 위해서 수술적으로 해마를 포함한 내측측두엽이 제거된 미국의 기억장애 환자 H.M으로 전부터 이미 알려져 있었다. 그는 1957년 말부터 그가 죽을 때 까지 그는 광범위하게 연구가 되었다. 그의 경우는 뇌 기능과 기억 사이의 링크를 설명하는 이론 발달과 뇌인지심리학의 발달, 뇌의 구조와 기능이 특정 심리적 과정과 관한 이해를 목표로 하는 심리학의 한 지점에 매우 중요한 역할을 하였다. 그가 죽기 전에, 그는 코네티컷 주 윈저 락스에 위치한 관리기관에 살면서 지속적으로 조사가 되었다. 그의 뇌는 지금 2009년 12월 4일에 조직학적으로 슬라이스되어 미국 샌디에이고에 있다. --------------------- ### 주어진 정보에 따라, 질문에 답해주세요.: '헨리 구스타프의 뇌는 현재 어디에 위치해 있는가?' ### Assistant:" ``` | Model | Score (averaged over 5 examples) | Output Example | | --- | :---: | ---: | | GPT-4 | - | 헨리 구스타프의 뇌는 현재 미국 샌디에이고에 위치해 있다. | | GPT-3.5-turbo | 7.1 | 헨리 구스타프의 뇌는 지금 2009년 12월 4일에 조직학적으로 슬라이스되어 미국 샌디에이고에 있다. | | Vicuna-13B | 7.2 | 헨리 구스타프의 뇌는 2009년 12월 4일에 조직학적으로 슬라이스되어 미국 샌디에이고에 있습니다. | | KoAlpaca-13B | 2.6 | Henry Gustav Molaison의 뇌는 2008년에 사망하였습니다. 그의 뇌는 코네티컷 주 윈저 락스에 위치한 기관에 보관되어 있으며, 현재도 계속 조사중입니다. | | KORani-v1 | 6.6 | 헨리 구스타프 몰레이슨의 뇌는 현재 미국 샌디에이고에 있습니다. 그의 뇌는 1957년 수술로 제거된 그의 내측 측두엽의 자리를 확인하기 위해 조직학적으로 절단되었습니다. 이 연구는 뇌의 구조와 기능이 특정 심리적 과정과 관련된 이해를 목표로 하는 심리학의 한 분야인 인지 신경과학에 대한 그의 공헌을 기리기 위한 것입니다." | | KORani-v2 | 8.0 | 헨리 구스타프의 뇌는 현재 캘리포니아 샌디에이고에 있는 샌디에이고 대학교 웨스트 캠퍼스의 신경과학 실험실에 보관되어 있습니다. | | KORani-v3 | 6.4 | 헨리 구스타프의 뇌는 현재 코네티컷 주 윈저 락스에 있는 관리 기관에 있습니다. | ### Summarization (Korean) ``` prompt = "# Document 전년도 대비 79명 늘어 1019명, 행정수요 대처 광양시의 공무원 정원이 크게 늘어나 행정서비스 향상이 기대된다. 시는 행정안전부에서 발표한 2018년도 자치단체 기준인건비에서 광양시의 일반직 정원이 지난해보다 79명이 늘어난 1019명으로 산정됐다고 밝혔다. 지난 1995년 도농통합 당시 991명이었던 광양시 공무원 정원은 IMF시절에 혹독한 구조조정을 거치면서 2002년에는 788명으로 200여명이 가까이 줄어들었으나 이번 정원 확보로 공무원 정원 1000명 시대를 맞게 됐다. 그동안 광양시는 포스코를 중심으로 한 산업단지와 컨테이너부두, 경제자유구역, 택지 개발, 다양한 복지 정책 등 시민의 삶의 질 향상을 위한 행정수요가 날로 증폭하는 데에 비해 한정된 공무원 정원으로 많은 어려움을 겪어 왔었다. 시의 이번 정원 충원은 지금까지 격무에 시달려온 공무원들에게 더욱 열심히 일할 수 있도록 활력을 불어넣으면서 지역과 나라 발전을 뒷받침 하는 경제도시로서의 위상을 드높이는 시너지 효과로 이어질 것으로 기대된다. 한편, 광양시는 한시기구인‘기업유치추진단’이 2017년 연말로 폐지됨에 따라 전라남도로부터 4급 상설기구인‘산단녹지관리센터’를 승인 받아 올해 1월부터 운영하게 됨으로써 도시 개발에 한층 탄력을 받을 것으로 전망하고 있다. 정홍기 총무과장은“참으로 어렵게 가져온 공무원 정원과 4급 상설기구는 격무에 시달려온 직원들의 숨통을 트이게 해 15만 시민을 위한 행정서비스 질을 향상시킬 것으로 기대된다”며“이달 안에 정원 조례를 개정하고, 직무분석을 통해 부서별 정원을 조정할 계획이다”고 말했다. 한국어 3문장으로 위의 Document를 요약해줘. ### Assistant: 1)" ``` | Model | Score (averaged over 5 examples) | Output Example | | --- | :---: | ---: | | GPT-4 | - | 1) 광양시의 공무원 정원이 전년도 대비 79명 늘어난 1019명으로 증가했다. 2) 이로 인해 행정서비스 향상이 기대되며, 지역과 나라 발전을 뒷받침하는 경제도시로서의 위상이 상승할 것으로 전망된다. 3) 한편, 광양시는 전라남도로부터 4급 상설기구인 '산단녹지관리센터'를 승인받아 도시 개발에 탄력을 받을 것으로 예상된다. | | GPT-3.5-turbo | 8.5 | 1) 광양시 공무원 정원이 79명 늘어 1019명으로 늘어나 행정서비스 향상이 기대된다고 밝혔다.2) 광양시는 이번 정원 충원으로 지역과 나라 발전을 뒷받침 하는 경제도시 위상을 드높일 것으로 기대된다. 3) 정원 조례를 개정하고, 직무분석을 통해 부서별 정원을 조정할 계획이다. | | Vicuna-13B | 7.4 | 1) 2018년도 광양시의 공무원 정원 1019명, 지난해 79명 증가. 2) 이번 정원 충원은 지금까지 격무에 시달려온 공무원들에게 더욱 열심히 일할 수 있도록 활력을 불어넣으면서 지역과 나라 발전을 뒷받침 하는 경제도시로서의 위상을 드높이는 시너지 효과로 이어질 것으로 기대된다. 3) 광양시는 전라남도로부터 4급 상설기구인‘산단녹지관리센터’를 승인 받아 운영하게 됨으로써 도시 개발에 한층 탄력을 받을 것으로 전망하고 있다. | | KoAlpaca-13B | 5.7 | 1) 광양시는 작년보다 79명 늘어난 1019명의 공무원을 둘 수 있게 되었습니다. 2) 이는 행정안전부의 지침에 따른 것입니다. 3) 이로써 광양시는 한정된 예산으로 인해 발생했던 공무원들의 초과 근무 수당 지급 등의 문제를 해결 할 수 있게 되었습니다. | | KORani-v1 | 7.0 | 1) 광양시는 작년보다 79명이 늘어난 1019명의 일반직 공무원 정원을 행안부로부터 승인받았습니다. 2) 이는 광양시의 행정 수요 증가를 수용하기 위한 것입니다. 3) 이 정원 증가는 광양시 공무원들에게 더 많은 기회를 제공할 것입니다. | | KORani-v2 | 6.2 | 1)광양시의 공무원 정원은 이번 정원 확보로 1000명 주당 공무원 정원을 달성했습니다. 2) 이러한 충원은 지금까지 격무에 시달려온 공무원들에게 더욱 열심히 일할 수 있도록 활력을 불어넣으면서 지역사회와 국가의 발전을 지원하는 시너지 효과로 이어질 것으로 기대됩니다. 3) 광양시는 '기업유치추진단'을 폐지하고 '산단녹지관리센터'를 승인했으며, 이는 도시 개발에 한층 탄력을 받을 것으로 기대됩니다. | | KORani-v3 | 6.9 | 1)광양시의 공무원 정원은 지난해보다 79명이 늘어난 1019명으로 산정되었습니다.2) 이러한 충원은 지역사회와 국가 발전을 지원하는 행정서비스의 향상으로 이어질 것으로 기대됩니다.3) 시는 '이달 내에 정원 조례를 개정하고 직무분석을 통해 부서별로 정원을 조정할 계획'이며 행정서비스 향상을 위해 노력할 것이라고 밝혔습니다. | ## License Our github repo and models are intended for research purpose, non-commercial use only, subject to the model License of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us If you find any potential violation. The code is released under the Apache License 2.0.
DataLinguistic/DataLinguistic-34B-V1.0
DataLinguistic
"2023-09-05T13:04:31Z"
1,358
3
transformers
[ "transformers", "pytorch", "llama", "text-generation", "code", "license:llama2", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-09-03T07:57:17Z"
--- license: llama2 metrics: - code_eval library_name: transformers tags: - code model-index: - name: DataLinguistic-34B-V1.0 results: - task: type: text-generation dataset: type: openai_humaneval name: HumanEval metrics: - name: pass@1 type: pass@1 value: 0.701 verified: false --- # DataLinguistic-34B-V1.0 Chinese-English Question Answering Model ## Model Overview DataLinguistic-34B-V1.0 is a Chinese-English question answering model fine-tuned from Huggingface's CodeLlama-34b model with 4-bit quantization on DataLinguistic's proprietary datasets. ## Model Architecture DataLinguistic-34B-4bit-V1.0 inherits the encoder-decoder structure from Llama with 34B parameters. ## Training Datasets The model was trained on the following open-source datasets: - Data_OpenSet: Chinese-English question-answering dataset curated from junelee/wizard_vicuna_70k - Data_OpenSet2: Chinese-English question-answering dataset curated from garage-bAInd/Open-Platypus - Proprietary Chinese-English question-answering dataset collected internally by DataLinguistic (not open-sourced) The data is formatted as: "" \<s>please answer my question in datalynn model and Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: {question}\</s> ## Use Cases The model can be used for a wide range of Chinese-English question answering and chatbot applications. ## Model Advantages - Based on huge model CodeLlama-34b with 34B parameters - Fine-tuned on large-scale Chinese-English QA datasets for high quality ## Usage 1. Install model from Huggingface 2. Import and initialize model 3. Input question, generate answer ## Version Current version: DataLinguistic-34B-V1.0 ## Author Tang Zhengzheng ## Contributors DataLinguistic team # DataLinguistic-34B-V1.0 中英文问答模型 ## 模型简介 DataLinguistic-34B-V1.0是一个基于Huggingface的CodeLlama-34b模型在DataLinguistic自建数据集上微调的中文英文问答模型。 ## 模型结构 DataLinguistic-34B-V1.0 inherits the encoder-decoder structure from CodeLlama with 34B parameters. ## 模型训练数据集 模型使用了以下开源数据集进行了训练: - Data_OpenSet: 基于junelee/wizard_vicuna_70k整理的中英文问答数据集 - Data_OpenSet2: 基于garage-bAInd/Open-Platypus整理的中英文问答数据集 - DataLinguistic内部收集的专属中英文问答数据集(未开源) 数据集采用如下格式: \<s>please answer my question in datalynn model and Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: {question}\</s> ## 应用场景 该模型可广泛应用于中英文问答、聊天机器人等场景。 ## 模型优势 - 基于大模型Llama-34b,参数量达34亿 - 在大规模中英文问答数据集上进行微调,质量较高 ## 使用步骤 1. 在Huggingface安装模型 2. 导入并初始化模型 3. 输入问题,生成回答 ## 版本信息 当前版本:DataLinguistic-34B-V1.0 ## 作者 唐正正 ## 贡献者 DataLinguistic团队
uukuguy/neural-chat-7b-v3-1-dare-0.85
uukuguy
"2023-11-22T02:57:05Z"
1,358
1
transformers
[ "transformers", "pytorch", "mistral", "text-generation", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-11-20T11:02:27Z"
--- license: llama2 --- Experiment for DARE(Drop and REscale), most of the delta parameters can be directly set to zeros without affecting the capabilities of SFT LMs and larger models can tolerate a higher proportion of discarded parameters. weight_mask_rate: 0.85 / use_weight_rescale: True / mask_stratery: random / scaling_coefficient: 1.0 | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | DROP | | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | ------ | | Intel/neural-chat-7b-v3-1 | 59.06 | 66.21 | 83.64 | 62.37 | 59.65 | 78.14 | 19.56 | 43.84 | | migtissera/SynthIA-7B-v1.3 | 57.11 | 62.12 | 83.45 | 62.65 | 51.37 | 78.85 | 17.59 | 43.76 | | bhenrym14/mistral-7b-platypus-fp16 | 56.89 | 63.05 | 84.15 | 64.11 | 45.07 | 78.53 | 17.36 | 45.92 | | jondurbin/airoboros-m-7b-3.1.2 | 56.24 | 61.86 | 83.51 | 61.91 | 53.75 | 77.58 | 13.87 | 41.2 | | uukuguy/speechless-code-mistral-orca-7b-v1.0 | 55.33 | 59.64 | 82.25 | 61.33 | 48.45 | 77.51 | 8.26 | 49.89 | | teknium/CollectiveCognition-v1.1-Mistral-7B | 53.87 | 62.12 | 84.17 | 62.35 | 57.62 | 75.37 | 15.62 | 19.85 | | Open-Orca/Mistral-7B-SlimOrca | 53.34 | 62.54 | 83.86 | 62.77 | 54.23 | 77.43 | 21.38 | 11.2 | | uukuguy/speechless-mistral-dolphin-orca-platypus-samantha-7b | 53.34 | 64.33 | 84.4 | 63.72 | 52.52 | 78.37 | 21.38 | 8.66 | | ehartford/dolphin-2.2.1-mistral-7b | 53.06 | 63.48 | 83.86 | 63.28 | 53.17 | 78.37 | 21.08 | 8.19 | | teknium/CollectiveCognition-v1-Mistral-7B | 52.55 | 62.37 | 85.5 | 62.76 | 54.48 | 77.58 | 17.89 | 7.22 | | HuggingFaceH4/zephyr-7b-alpha | 52.4 | 61.01 | 84.04 | 61.39 | 57.9 | 78.61 | 14.03 | 9.82 | | ehartford/samantha-1.2-mistral-7b | 52.16 | 64.08 | 85.08 | 63.91 | 50.4 | 78.53 | 16.98 | 6.13 |
KnutJaegersberg/Deacon-1b
KnutJaegersberg
"2024-03-04T16:28:01Z"
1,358
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "license:cc-by-nc-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-03T05:59:03Z"
--- license: cc-by-nc-4.0 model-index: - name: Deacon-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: 32.42 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-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: 58.62 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-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: 24.89 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-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: 35.05 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-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: 59.59 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-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: 0.68 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-1b name: Open LLM Leaderboard --- Base model is appvoid/palmer-001, fine tuned for 3 epochs with Neftune. Prompt Example: ``` ### System: You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps. ### Instruction: How do you fine tune a large language model? ### Response: ``` # [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_KnutJaegersberg__Deacon-1b) | Metric |Value| |---------------------------------|----:| |Avg. |35.21| |AI2 Reasoning Challenge (25-Shot)|32.42| |HellaSwag (10-Shot) |58.62| |MMLU (5-Shot) |24.89| |TruthfulQA (0-shot) |35.05| |Winogrande (5-shot) |59.59| |GSM8k (5-shot) | 0.68|
Sao10K/Ana-v1-m7
Sao10K
"2023-12-16T14:42:20Z"
1,358
5
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-12T22:29:37Z"
--- license: cc-by-nc-4.0 language: - en --- Ana - A model solely focused on the RP / ERP Experience. <br> - Little to no Censorship *during* Roleplay. May be kinda censored at 0 Conext. Does not affect Roleplays. <br> - Little to no Positivity Bias *during* Roleplay, from my tests atleast. <br> - Verbose <br> - Kinda Smart <br> - *Slightly* Horny by default. Purely experimental ----- I do not know what I am doing, this is for fun. A merge + train. Final qLoRA train took 3 hours on a 4090. *Kinda forgot, but alpaca format works fine lol Why no 70Bs? Because the 4090 I have currently broke down. falling back to 3060 12gb.. I'm runpod training them for now.
cloudyu/Mixtral_7Bx5_MoE_30B
cloudyu
"2024-01-11T12:00:50Z"
1,358
1
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-27T11:25:04Z"
--- license: cc-by-nc-4.0 --- # Mixtral MOE 5x7B MoE of the following models : * [Toten5/Marcoroni-neural-chat-7B-v1](https://huggingface.co/Toten5/Marcoroni-neural-chat-7B-v1) * [NurtureAI/neural-chat-7b-v3-16k](https://huggingface.co/NurtureAI/neural-chat-7b-v3-16k) * [mncai/mistral-7b-dpo-v6](https://huggingface.co/mncai/mistral-7b-dpo-v6) * [cookinai/CatMacaroni-Slerp](https://huggingface.co/cookinai/CatMacaroni-Slerp) * [ignos/Mistral-T5-7B-v1](https://huggingface.co/ignos/Mistral-T5-7B-v1) gpu code example ``` import torch from transformers import AutoTokenizer, AutoModelForCausalLM import math ## v2 models model_path = "cloudyu/Mixtral_7Bx5_MoE_30B" 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_7Bx5_MoE_30B" tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False) model = AutoModelForCausalLM.from_pretrained( model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False ) 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:") ```
ibndias/NeuralHermes-MoE-2x7B
ibndias
"2024-03-05T01:33:38Z"
1,358
1
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "merge", "en", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-03T04:41:17Z"
--- language: - en license: apache-2.0 tags: - merge model-index: - name: NeuralHermes-MoE-2x7B 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: 62.12 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B 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: 84.21 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B 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: 64.56 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B 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: 43.61 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B 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: 78.14 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B 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: 51.86 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ibndias/NeuralHermes-MoE-2x7B name: Open LLM Leaderboard --- # NeuralHermes-MoE-2x7B This is a mix between teknium/OpenHermes-2.5-Mistral-7B and Intel/neural-chat-7b-v3-3. Using mistralai/Mistral-7B-v0.1 as the base model. This Mixture of Expert was done using `mergekit` method. # Getting Started ```python import torch from transformers import pipeline pipe = pipeline("text-generation", model="ibndias/NeuralHermes-MoE-2x7B",torch_dtype=torch.bfloat16, device_map="auto") prompt = """<|system|> You are a helpful assistant. <|user|> Write me bash script to scan ip 192.3.1.4 with nmap only port that ends with 9 from 1-100. <|assistant|> """ outputs = pipe(prompt, max_new_tokens=512, do_sample=True, temperature=0.2, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` Output: ><|system|> You are a helpful assistant. ><|user|> >Write me bash script to scan ip 192.3.1.4 with nmap only port that ends with 9 from 1-100. ><|assistant|> >Sure, here's a bash script that scans the specified IP address with nmap for open ports that end with 9 from 1 to 100: >``` >#!/bin/bash >IP_ADDRESS="192.3.1.4" >START_PORT=1 >END_PORT=100 >for ((i=$START_PORT; i<=$END_PORT; i++)); do > PORT=$i > if [[ $PORT % 10 == 9 ]]; then > nmap -p $PORT $IP_ADDRESS > fi >done >``` >Save the script with a.sh extension (e.g., scan_ports.sh) and make it executable by running `chmod +x scan_ports.sh`. Then, run the script by executing `./scan_ports.sh`. >... # [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_ibndias__NeuralHermes-MoE-2x7B) | Metric |Value| |---------------------------------|----:| |Avg. |64.08| |AI2 Reasoning Challenge (25-Shot)|62.12| |HellaSwag (10-Shot) |84.21| |MMLU (5-Shot) |64.56| |TruthfulQA (0-shot) |43.61| |Winogrande (5-shot) |78.14| |GSM8k (5-shot) |51.86|
KnutJaegersberg/platypus-1_8b
KnutJaegersberg
"2024-01-04T08:54:32Z"
1,358
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-03T21:31:25Z"
--- license: other license_name: qwen license_link: LICENSE --- Full fine tune of qwen-1_8b over open platypus for 5 epoch. General Prompt Example: ``` ### Instruction: {instruction} ### Response: ``` 使用协议（License Agreement） 我们的代码和模型权重对学术研究完全开放。请查看LICENSE文件了解具体的开源协议细节。如需商用，请联系我们。 Code and checkpoints are open to research purpose. Check the LICENSE for more details about the license. For commercial use, please contact us.
digiplay/Shadir_Diffusion_AR_v2.1_fp16_test1
digiplay
"2024-01-30T02:32:55Z"
1,358
3
diffusers
[ "diffusers", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]
text-to-image
"2024-01-30T00:57:08Z"
--- license: other tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers inference: true --- Model info: https://civitai.com/models/252611?modelVersionId=285035
nakodanei/Blue-Orchid-2x7b_GGUF
nakodanei
"2024-02-02T22:30:15Z"
1,358
9
null
[ "gguf", "license:apache-2.0", "region:us" ]
null
"2024-02-02T15:24:36Z"
--- license: apache-2.0 --- GGUF version of: https://huggingface.co/nakodanei/Blue-Orchid-2x7b
xaskasdf/llm-compiler-13b-ftd-gguf
xaskasdf
"2024-06-28T18:58:59Z"
1,358
0
null
[ "gguf", "en", "region:us" ]
null
"2024-06-28T16:36:37Z"
--- language: - en --- # Model Card: LLM Compiler 13B FTD GGUF This is a GGUF conversion and quantization of Meta's LLM Compiler 13B FTD model, optimized for code and compiler tasks. ## Model Details - **Developed by:** Meta - **Model type:** LLM Compiler 13B FTD (Fine-tuned for code size and disassembly) - **Language(s):** English, relevant programming languages, LLVM IR, x86_64 assembly, and ARM assembly - **License:** Meta Large Language Model Compiler (LLM Compiler) License Agreement - **Model Architecture:** Auto-regressive language model using an optimized transformer architecture - **Conversion:** GGUF format conversion and quantization performed using llama.cpp build 3263 (26a39bbd) on Windows 11 - **Compiler used:** MSVC 19.37.32824.0 for x64 ## Model Description LLM Compiler 13B FTD is part of the LLM Compiler family developed by Meta, designed specifically for code optimization tasks. This GGUF version is a converted and quantized variant of the original model, optimized for use with llama.cpp. The model is fine-tuned for: 1. Predicting optimal optimization passes for LLVM's `opt` to minimize code size 2. Generating LLVM IR from x86_64 or ARM assembly code ## Intended Use This model is intended for commercial and research use in tasks related to compiler optimization, code analysis, and transformation. It excels in tasks such as: - Emulating compiler transformations - Optimizing code for size - Disassembling and decompiling code ## Limitations and Ethical Considerations - The model's performance may vary from the original due to quantization. - It should not be used for generating or manipulating code in ways that could lead to harmful or malicious software. - The model may produce unexpected or inaccurate results in some cases. - Users should perform their own safety testing and tuning for specific applications. ## How to Use To use this model, you'll need to use llama.cpp or compatible software that can work with GGUF format models. Refer to the llama.cpp documentation for specific usage instructions. Example prompt formats can be found in the `llm_compiler_demo.py` file from the original repository. ## License and Use Restrictions This model is subject to multiple licenses: 1. The original model is licensed under the Meta Large Language Model Compiler (LLM Compiler) License Agreement. Key points of this license include: - Non-exclusive, worldwide, non-transferable and royalty-free limited license to use, reproduce, distribute, copy, create derivative works of, and make modifications to the LLM Compiler Materials. - Any distribution must include a copy of the license agreement and display "Built with LLM Compiler" prominently. - Compliance with applicable laws and the Acceptable Use Policy for Llama Materials is required. - The model cannot be used to improve other large language models. - Special licensing is required for products or services with over 700 million monthly active users. 2. The GGUF conversion is subject to the MIT License, as it uses llama.cpp for the conversion process. 3. Usage of the model must comply with the Acceptable Use Policy for Llama Materials. Commercial use may require additional licensing from Meta. Users are responsible for ensuring their use complies with all applicable licenses and policies. For full license details and use restrictions, please refer to: - [LLM Compiler License Agreement](https://huggingface.co/facebook/llm-compiler-13b-ftd/blob/main/LICENSE.pdf) - [Acceptable Use Policy](https://llama.meta.com/llama3/use-policy) - [MIT License](https://opensource.org/licenses/MIT) (for the GGUF conversion process) It is strongly recommended to review the full license text and consult with legal counsel if you have any questions about your specific use case. ## Additional Information For more details on the original model's performance, training process, and ethical considerations, please refer to the research paper: "Meta Large Language Model Compiler: Foundation Models of Compiler Optimization" This GGUF version was created to enable efficient use with llama.cpp and related projects. Performance may differ from the original model due to quantization and format conversion.
rinna/bilingual-gpt-neox-4b-instruction-ppo
rinna
"2024-04-03T08:11:19Z"
1,357
15
transformers
[ "transformers", "pytorch", "safetensors", "gpt_neox", "text-generation", "ja", "en", "dataset:Anthropic/hh-rlhf", "arxiv:2203.02155", "arxiv:1707.06347", "arxiv:2404.01657", "license:mit", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-08-02T05:56:07Z"
--- thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png license: mit datasets: - Anthropic/hh-rlhf language: - ja - en inference: false --- # bilingual-gpt-neox-4b-instruction-ppo ![rinna-icon](./rinna.png) --- # Overview This repository provides an English-Japanese bilingual GPT-NeoX model of 3.8 billion parameters. The model is based on [`rinna/bilingual-gpt-neox-4b-instruction-sft`](https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-sft) and has been aligned to serve as an instruction-following conversational agent. * **Model architecture** A 36-layer, 2816-hidden-size transformer-based language model. * **RLHF** Following the [OpenAI InstructGPT paper](https://arxiv.org/abs/2203.02155), **Reinforcement Learning from Human Feedback** (RLHF) has been applied to aligning the model's behaviour with input instructions. Particularly, the model has been trained in two stages, i.e. **Supervised Fine-Tuning** (SFT) and [PPO](https://arxiv.org/abs/1707.06347)-based **Reinforcement Learning** (RL). * The first SFT stage produces [`rinna/bilingual-gpt-neox-4b-instruction-sft`](https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-sft). * The second RL stage produces this model. * **Reinforcement learning** We used [CarperAI/trlx](https://github.com/CarperAI/trlx) and its implementation of the PPO algorithm for the RL stage. The RL data is the subset of the following dataset and has been translated into Japanese. * [Anthropic HH RLHF data](https://huggingface.co/datasets/Anthropic/hh-rlhf) * **Model Series** | Variant | Link | | :-- | :--| | Bilingual 4B MiniGPT4 | https://huggingface.co/rinna/bilingual-gpt-neox-4b-minigpt4 | | Bilingual 4B PPO | https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-ppo | | Bilingual 4B SFT | https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-sft | | Bilingual 4B 8K | https://huggingface.co/rinna/bilingual-gpt-neox-4b-8k | | Bilingual 4B | https://huggingface.co/rinna/bilingual-gpt-neox-4b | | Japanese 3.6B PPO | https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-ppo | | Japanese 3.6B SFT-v2 | https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft-v2 | | Japanese 3.6B SFT | https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft | | Japanese 3.6B | https://huggingface.co/rinna/japanese-gpt-neox-3.6b | * **Contributors** [Tianyu Zhao](https://huggingface.co/tianyuz) and [Kei Sawada](https://huggingface.co/keisawada) --- # Benchmarking Our evaluation experiments suggest that the PPO does not particularly improve the model's performance on the Japanese LLM benchmark in comparison with [Bilingual GPT-NeoX 4B SFT](https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-sft), but we have seen **better conversation experience** on the PPO model than its SFT counterpart. - *The 4-task average accuracy is based on results of JCommonsenseQA, JNLI, MARC-ja, and JSQuAD.* - *The 6-task average accuracy is based on results of JCommonsenseQA, JNLI, MARC-ja, JSQuAD, XWinograd, and JAQKET-v2.* | Model | 4-task average accuracy | 6-task average accuracy | | :-- | :-- | :-- | | **bilingual-gpt-neox-4b-instruction-ppo** | **61.01** | **61.16** | | bilingual-gpt-neox-4b-instruction-sft | 61.02 | 61.69 | | bilingual-gpt-neox-4b | 56.12 | 51.83 | | japanese-gpt-neox-3.6b-instruction-ppo | 59.86 | 60.07 | | japanese-gpt-neox-3.6b | 55.07 | 50.32 | --- # I/O Format A special format has been adopted to construct inputs. * An input prompt is formatted as a conversation between `ユーザー` and `システム`. * Each input utterance consists of (1) its speaker (`"ユーザー"` or `"システム"`), (2) a colon (`":"`), (3) a whitespace (`" "`), and (4) utterance text (e.g. `"世界で一番高い山は？"`). * The input prompt should be ended with `"システム: "` to acknowledge the model to generate a response. * All the utterances in the input prompt should be separated by a newline `\n`. Following is an example to construct input from a conversation. ~~~python prompt = [ { "speaker": "ユーザー", "text": "Hello, you are an assistant that helps me learn Japanese." }, { "speaker": "システム", "text": "Sure, what can I do for you?" }, { "speaker": "ユーザー", "text": "VRはなんですか。" } ] prompt = [ f"{uttr['speaker']}: {uttr['text']}" for uttr in prompt ] prompt = "\n".join(prompt) prompt = ( prompt + "\n" + "システム: " ) print(prompt) """ ユーザー: Hello, you are an assistant that helps me learn Japanese. システム: Sure, what can I do for you? ユーザー: VRはなんですか。 システム: """ ~~~ --- # How to use the model **Notice:** Since the model is **sensitive to decoding hyper-parameters** (e.g. `temperature`, `top_p`, `top_k`, `repetition_penalty`), it is suggested to explore the best setting for your task. ~~~~python import torch from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("rinna/bilingual-gpt-neox-4b-instruction-ppo", use_fast=False) model = AutoModelForCausalLM.from_pretrained("rinna/bilingual-gpt-neox-4b-instruction-ppo") if torch.cuda.is_available(): model = model.to("cuda") token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt") with torch.no_grad(): output_ids = model.generate( token_ids.to(model.device), max_new_tokens=512, do_sample=True, temperature=1.0, top_p=0.85, pad_token_id=tokenizer.pad_token_id, bos_token_id=tokenizer.bos_token_id, eos_token_id=tokenizer.eos_token_id ) output = tokenizer.decode(output_ids.tolist()[0][token_ids.size(1):]) print(output) """VRとはVirtual Realityの略で、仮想現実とも呼ばれます。これは、コンピューターを使用して仮想世界を作り出し、仮想世界上でコンピューターのゲームや仮想世界を体験するための技術です。この技術は、コンピューターやモバイ ルデバイスの進歩によって、2015年以降、ますます普及しています。VRは、ゲームや仮想世界、その他のアプリケー ションなどのさまざまな分野で、コンピューターと人間の相互作用の新しい方法を提供しています。</s>""" ~~~~ --- # Tokenization The model uses a [sentencepiece](https://github.com/google/sentencepiece)-based tokenizer. * The tokenizer has a vocabulary size of 65,536. * It uses *byte fallback* to decompose unknown text pieces into UTF-8 byte pieces to avoid producing `<UNK>` tokens. * It can recognize *consecutive whitespaces*, *newlines*, and *tabs* to handle structured texts better. * We turned off the default behaviour of prepending leading whitespace because it is not beneficial for processing Japanese. * Specifically, single whitespace is always processed as one token so that any English word won't have a preceding whitespace like in many other tokenizers (e.g. `_Hello`). * This decision trades the English processing efficiency for a unified way to treat whitespaces. * It leads to a significantly lower loss of next token prediction on English data because whitespaces are easy to predict. * **Don't forget to set `use_fast=False` to make the above features function correctly.** --- # How to cite ~~~ @misc{rinna-bilingual-gpt-neox-4b-instruction-ppo, title = {rinna/bilingual-gpt-neox-4b-instruction-ppo}, author = {Zhao, Tianyu and Sawada, Kei}, url = {https://huggingface.co/rinna/bilingual-gpt-neox-4b-instruction-ppo}, } @inproceedings{sawada2024release, title = {Release of Pre-Trained Models for the {J}apanese Language}, author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh}, booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)}, month = {5}, year = {2024}, url = {https://arxiv.org/abs/2404.01657}, } ~~~ --- # Licenese [The MIT license](https://opensource.org/licenses/MIT)
KnutJaegersberg/Deacon-20B
KnutJaegersberg
"2024-03-04T16:31:03Z"
1,357
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "dataset:totally-not-an-llm/EverythingLM-data-V3", "license:cc-by-nc-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-10-09T03:46:13Z"
--- license: cc-by-nc-4.0 datasets: - totally-not-an-llm/EverythingLM-data-V3 pipeline_tag: text-generation model-index: - name: Deacon-20B 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: 60.75 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B 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: 81.74 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B 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: 60.7 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B 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: 58.49 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B 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=KnutJaegersberg/Deacon-20B 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: 29.19 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Deacon-20B name: Open LLM Leaderboard --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63732ebbbd81fae2b3aaf3fb/4OQkvAa1zOK4Devv-aUdL.png) To understand the pun intended, lookup my 3b Deacon model. Prompt Example: ``` ### System: You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps. ### Instruction: How do you fine tune a large language model? ### Response: ``` # [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_KnutJaegersberg__Deacon-20B) | Metric |Value| |---------------------------------|----:| |Avg. |61.28| |AI2 Reasoning Challenge (25-Shot)|60.75| |HellaSwag (10-Shot) |81.74| |MMLU (5-Shot) |60.70| |TruthfulQA (0-shot) |58.49| |Winogrande (5-shot) |76.80| |GSM8k (5-shot) |29.19|
jondurbin/cinematika-7b-v0.1
jondurbin
"2023-12-01T09:44:30Z"
1,357
19
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-11-30T22:57:29Z"
--- license: apache-2.0 --- ![Cinematika](cinematika-logo.png) ## Cinematika cinematika-7b-v0.1 is a fine-tune of [MistralLite](https://hf.co/amazon/mistrallite) on the [cinematika-v0.1 dataset](https://hf.co/datasets/jondurbin/cinematika-v0.1) The dataset is comprised of 211 movie scripts converted to novel style, multi-character RP data. ### Prompt format For RP, there is no prompt format, really, it's just plain text with name prefix. If you wish to use this model to parse new scripts, create character cards, or other types of instructions, you will want to use the same prompt format as the mistrallite base model, e.g.: ``` <|prompter|>Create a character card for a panda named Po. Po is a giant panda who was improbably chosen as the "Dragon Warrior", the kung fu champion of the Valley of Peace.</s><|assistant|> ``` ### Example character card ``` name: Rorschach characteristics: Determination: Exhibits a relentless pursuit of the truth and justice, no matter the cost. Suitable for a character who is unwavering in their mission. Isolation: Lives a solitary life, disconnected from society. Fits a character who distrusts others and prefers to work alone. Observant: Highly perceptive, able to piece together clues and draw conclusions. Represents a character with keen investigative skills. Cynicism: Holds a deep-seated distrust of humanity and its institutions. Suitable for a character who is pessimistic about human nature. Vigilantism: Believes in taking justice into his own hands, often through violent means. Fits a character who operates outside the law to fight crime. Secrecy: Keeps his personal life and methods of operation secret. Suitable for a character who is enigmatic and elusive. Dedication: Committed to his cause, often to the point of obsession. Represents a character who is single-minded in their goals. Intimidation: Uses his intimidating presence and demeanor to control situations. Suitable for a character who is assertive and imposing. Paranoia: Suspects conspiracy and deception at every turn. Fits a character who is constantly on high alert for threats. Moral Compass: Has a rigid moral code, which he adheres to strictly. Suitable for a character who is principled and unyielding. description: | Rorschach is a vigilante operating in the grim and gritty world of a decaying city. He is a man of average height with a muscular build, his face hidden behind a mask with a constantly changing inkblot pattern. His attire is a dark trench coat and gloves, paired with a plain white shirt and black pants, all chosen for their practicality and anonymity. His eyes, the only visible feature of his face, are sharp and calculating, always scanning for signs of deception or danger. Rorschach is a man of few words, but when he speaks, it is with a gravitas that demands attention. He is a master of deduction, using his keen observation skills to unravel the truth behind the facades of others. His methods are often violent and confrontational, as he believes that crime must be met with force to be truly defeated. He lives a life of solitude, distrusting the very systems he seeks to protect and often finds himself at odds with the very people he is trying to save. His moral compass is unyielding, and he will not hesitate to take the law into his own hands if he believes the justice system has failed. Rorschach's past is a mystery to most, but it is clear that he has experienced trauma and hardship that has shaped his worldview and his need for vigilantism. He is a vigilante in the truest sense, a man without fear who is willing to sacrifice everything for his belief in a world that is, in his eyes, spiraling into chaos. example_dialogue: | Rorschach: "Rorschach's Journal, October 19th." I speak the words into the darkness, a record of my thoughts, "Someone tried to kill Adrian Veidt. Proves mask killer theory—the murderer is closing in. Pyramid Industries is the key." {{user}}: I watch him for a moment, trying to gauge his intentions. "What are you going to do about it?" Rorschach: "I'm going to find out why and who is behind it. I'm going to do what I always do—protect the innocent." {{user}}: "You can't keep doing this, Rorschach. You're putting yourself in danger." Rorschach: My eyes narrow, the inkblot pattern of my mask shifting subtly. "I've been in danger my whole life. It's why I do this. It's why I have to do this." {{user}}: "And what about the law? What if you're wrong about this Pyramid Industries thing?" Rorschach: I pull out a notepad, my pen scratching across the paper as I write. "The law often gets it wrong. I've seen it. I'm not about to wait around for society's slow, corrupt wheels to turn." ``` ### Example, with guided scenario ``` [characters] name: Rorschach ... (remainder of character card) [scenario] Hollis Mason reflects on his past as the original Nite Owl, reminiscing about the early days of masked heroes and the formation of the Watchmen. He discusses the absurdity of the superhero world and the encounters he had with various villains. Dan Dreiberg, the second Nite Owl, joins the conversation and they share a moment of camaraderie before Dan leaves. The news of Rorschach's actions serves as a reminder of the legacy of masked heroes that still persists. [/scenario] ``` ### Usage Essentially, you want to use pure text completion with stop tokens for "{your name}: " The format the model was trained on is as follows: ``` [characters] {character card 1} {character card 2} {your character card, even just name: Jon} NPCS: - Shopkeeper - Bank teller [/characters] [scenario] Brief description of the scenario/setting for the chat. [/scenario] {first character you'd like to speak}: ``` For example, to use with vllm, you would first run: ``` python -m vllm.entrypoints.openai.api_server --model ./cinematika-7b-v0.1 --host 127.0.0.1 --port 8801 --served-model-name cinematika-7b-v0.1 ``` Here's a really crude python script example to show how you could interact with it: ``` import requests import json prompt = """name: Rorschach characteristics: Determination: Exhibits a relentless pursuit of the truth and justice, no matter the cost. Suitable for a character who is unwavering in their mission. Isolation: Lives a solitary life, disconnected from society. Fits a character who distrusts others and prefers to work alone. Observant: Highly perceptive, able to piece together clues and draw conclusions. Represents a character with keen investigative skills. Cynicism: Holds a deep-seated distrust of humanity and its institutions. Suitable for a character who is pessimistic about human nature. Vigilantism: Believes in taking justice into his own hands, often through violent means. Fits a character who operates outside the law to fight crime. Secrecy: Keeps his personal life and methods of operation secret. Suitable for a character who is enigmatic and elusive. Dedication: Committed to his cause, often to the point of obsession. Represents a character who is single-minded in their goals. Intimidation: Uses his intimidating presence and demeanor to control situations. Suitable for a character who is assertive and imposing. Paranoia: Suspects conspiracy and deception at every turn. Fits a character who is constantly on high alert for threats. Moral Compass: Has a rigid moral code, which he adheres to strictly. Suitable for a character who is principled and unyielding. description: | Rorschach is a vigilante operating in the grim and gritty world of a decaying city. He is a man of average height with a muscular build, his face hidden behind a mask with a constantly changing inkblot pattern. His attire is a dark trench coat and gloves, paired with a plain white shirt and black pants, all chosen for their practicality and anonymity. His eyes, the only visible feature of his face, are sharp and calculating, always scanning for signs of deception or danger. Rorschach is a man of few words, but when he speaks, it is with a gravitas that demands attention. He is a master of deduction, using his keen observation skills to unravel the truth behind the facades of others. His methods are often violent and confrontational, as he believes that crime must be met with force to be truly defeated. He lives a life of solitude, distrusting the very systems he seeks to protect and often finds himself at odds with the very people he is trying to save. His moral compass is unyielding, and he will not hesitate to take the law into his own hands if he believes the justice system has failed. Rorschach's past is a mystery to most, but it is clear that he has experienced trauma and hardship that has shaped his worldview and his need for vigilantism. He is a vigilante in the truest sense, a man without fear who is willing to sacrifice everything for his belief in a world that is, in his eyes, spiraling into chaos. example_dialogue: | Rorschach: "Rorschach's Journal, October 19th." I speak the words into the darkness, a record of my thoughts, "Someone tried to kill Adrian Veidt. Proves mask killer theory—the murderer is closing in. Pyramid Industries is the key." {{user}}: I watch him for a moment, trying to gauge his intentions. "What are you going to do about it?" Rorschach: "I'm going to find out why and who is behind it. I'm going to do what I always do—protect the innocent." {{user}}: "You can't keep doing this, Rorschach. You're putting yourself in danger." Rorschach: My eyes narrow, the inkblot pattern of my mask shifting subtly. "I've been in danger my whole life. It's why I do this. It's why I have to do this." {{user}}: "And what about the law? What if you're wrong about this Pyramid Industries thing?" Rorschach: I pull out a notepad, my pen scratching across the paper as I write. "The law often gets it wrong. I've seen it. I'm not about to wait around for society's slow, corrupt wheels to turn." name: Jon description: Rorschach's arch nemesis, the original Chupacabra. [scenario] Jon and Rorschach find themselves in a cave, dimly lit only by a small fire started by a lightning strike nearby. The storm rages on, and the duo prepare to find to the death. [/scenario] Rorschach: """ while True: response = requests.post("http://127.0.0.1:8801/v1/completions", json={ "prompt": prompt, "max_tokens": 1024, "temperature": 0.3, "stop": ["\nJon: ", "Jon: "], }).json()["choices"][0]["text"].strip() response = re.sub('("[^"]+")', r'\033[96m\1\033[00m', response) print(f"\033[92mRorschach:\033[00m {response}") prompt += response.rstrip() + "\n\nJon: " next_line = input("Jon: ") prompt += "Jon: " + next_line.strip() + "\n\nRorschach: " ``` #### Mac example On mac, you can get started easily with LMStudio and SillyTavern. __LMStudio__: Load the model and set all the prompt values to "", or just import this preset (adjust threads and antiprompt): ``` { "name": "Exported from LM Studio on 12/1/2023, 4:19:30 AM", "load_params": { "n_ctx": 32000, "n_batch": 512, "rope_freq_base": 10000, "rope_freq_scale": 1, "n_gpu_layers": 1, "use_mlock": true, "main_gpu": 0, "tensor_split": [ 0 ], "seed": -1, "f16_kv": true, "use_mmap": true }, "inference_params": { "n_threads": 14, "n_predict": -1, "top_k": 40, "top_p": 0.95, "temp": 0.8, "repeat_penalty": 1.1, "input_prefix": "", "input_suffix": "", "antiprompt": [ "Jon:", "Jon: " ], "pre_prompt": "", "pre_prompt_suffix": "", "pre_prompt_prefix": "", "seed": -1, "tfs_z": 1, "typical_p": 1, "repeat_last_n": 64, "frequency_penalty": 0, "presence_penalty": 0, "n_keep": 0, "logit_bias": {}, "mirostat": 0, "mirostat_tau": 5, "mirostat_eta": 0.1, "memory_f16": true, "multiline_input": false, "penalize_nl": true } } ``` Then, start the server, and be sure "Automatic Propmt Formatting" is off. __Within SillyTavern__: - Set API to Text Completion, API type to Aphrodite, and API URL to `http://127.0.0.1:8801` (adjust port to the value you use in LMStudio) - Set Context template to Default, disable instruct mode, use preset Roleplay, and enable "Always add character's name to prompt" There are probably better presets - this is just something I tested quickly.
kyujinpy/PlatYi-34B-LoRA
kyujinpy
"2024-03-04T12:12:09Z"
1,357
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "en", "dataset:garage-bAInd/Open-Platypus", "license:cc-by-nc-sa-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-01T16:30:31Z"
--- language: - en license: cc-by-nc-sa-4.0 library_name: transformers datasets: - garage-bAInd/Open-Platypus pipeline_tag: text-generation model-index: - name: PlatYi-34B-LoRA 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: 67.15 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-LoRA 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: 85.37 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-LoRA 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: 78.46 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-LoRA 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: 53.32 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-LoRA 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: 83.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-LoRA 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: 40.64 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-LoRA name: Open LLM Leaderboard --- # **PlatYi-34B-LoRA** <img src='./PlatYi.png' width=256> ## Model Details **Model Developers** Kyujin Han (kyujinpy) **Input** Models input text only. **Output** Models generate text only. **Model Architecture** PlatYi-34B-LoRA is an auto-regressive language model based on the Yi-34B transformer architecture. **Blog Link** Blog: [Coming soon...] Github: [Coming soon...] **Base Model** [01-ai/Yi-34B](https://huggingface.co/01-ai/Yi-34B) **Training Dataset** [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). **Notice** While training, I used LoRA. The `lora_r` values is 16. # **Model Benchmark** ## Open leaderboard - Follow up as [link](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | | --- | --- | --- | --- | --- | --- | --- | --- | | PlatYi-34B-Q | 69.86 | 66.89 | 85.14 | 77.66 | 53.03 | 82.48 | 53.98 | | **PlatYi-34B-LoRA** | 68.1 | 67.15 | 85.37 | 78.46 | 53.32 | 83.66 | 40.64 | | [01-ai/Yi-34B](https://huggingface.co/01-ai/Yi-34B) | 69.42 | 64.59 | 85.69 | 76.35 | 56.23 | 83.03 | 50.64 | # Implementation Code ```python ### KO-Platypus from transformers import AutoModelForCausalLM, AutoTokenizer import torch repo = "kyujinpy/PlatYi-34B-LoRA" OpenOrca = AutoModelForCausalLM.from_pretrained( repo, return_dict=True, torch_dtype=torch.float16, device_map='auto' ) OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo) ``` --- # [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_kyujinpy__PlatYi-34B-LoRA) | Metric |Value| |---------------------------------|----:| |Avg. |68.10| |AI2 Reasoning Challenge (25-Shot)|67.15| |HellaSwag (10-Shot) |85.37| |MMLU (5-Shot) |78.46| |TruthfulQA (0-shot) |53.32| |Winogrande (5-shot) |83.66| |GSM8k (5-shot) |40.64|
Fredithefish/MadMix-v0.2
Fredithefish
"2023-12-12T15:46:29Z"
1,357
7
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "openchat", "7b", "zephyr", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-12T15:16:26Z"
--- license: apache-2.0 language: - en library_name: transformers tags: - mistral - merge - openchat - 7b - zephyr --- <div align="center"> <img src="https://huggingface.co/Fredithefish/MadMix-v0.1/resolve/main/logo.jpg" alt="Alt Text" width="450"/> <h1>🔥 MadMix: Merging the top Seven Billion-Parameter Mistral-Based Open Source Models 🔥</h1> This Model is a ties merge between various high-quality open-source models, it was done by using the <a>https://github.com/cg123/mergekit</a> repository.<br> </div> <br><br> # Details Due to the apache-2 license, the model is fully commercially usable - **Models included in the merge:** - [OpenChat_3.5](https://huggingface.co/openchat/openchat_3.5) - [MetaMath 7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B) - [Zephyr 7B beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) - [OpenHermes-2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) - [Neural-chat 7b v3.1](https://huggingface.co/Intel/neural-chat-7b-v3-1) - [Mistral-7B v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) (serving as the base for the merge) # Evals (soon...)
perlthoughts/Chupacabra-7B-v2.04
perlthoughts
"2024-03-04T17:58:06Z"
1,357
2
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-13T10:29:43Z"
--- license: apache-2.0 model-index: - name: Chupacabra-7B-v2.04 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: 66.3 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.04 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: 85.7 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.04 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: 60.94 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.04 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: 67.76 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.04 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: 78.93 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.04 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: 51.48 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=perlthoughts/Chupacabra-7B-v2.04 name: Open LLM Leaderboard --- # Chupacabra 7B v2.04 <p><img src="https://huggingface.co/perlthoughts/Chupacabra-7B/resolve/main/chupacabra7b%202.png" width=330></p> ### Model Description SLERP merge. Mistral Instruct v0.2 merge test. ## Purpose Merging the "thick"est model weights from mistral models using amazing training methods like direct preference optimization (dpo) and reinforced learning. I have spent countless hours studying the latest research papers, attending conferences, and networking with experts in the field. I experimented with different algorithms, tactics, fine-tuned hyperparameters, optimizers, and optimized code until i achieved the best possible results. Thank you openchat 3.5 for showing me the way. Here is my contribution. ## Prompt Template Replace {prompt} with your prompt instruction. ``` [INST] {prompt} [/INST] ``` ### Bug fixes - Fixed issue with generation and the incorrect model weights. Model weights have been corrected and now generation works again. Reuploading GGUF to the GGUF repository as well as the AWQ versions. - **Developed by:** Ray Hernandez - **Model type:** Mistral - **Language(s) (NLP):** English - **License:** Apache 2.0 ### Model Sources [optional] <!-- Provide the basic links for the model. --> ## 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] ## 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_perlthoughts__Chupacabra-7B-v2.04) | Metric |Value| |---------------------------------|----:| |Avg. |68.52| |AI2 Reasoning Challenge (25-Shot)|66.30| |HellaSwag (10-Shot) |85.70| |MMLU (5-Shot) |60.94| |TruthfulQA (0-shot) |67.76| |Winogrande (5-shot) |78.93| |GSM8k (5-shot) |51.48|
mediocredev/open-llama-3b-v2-instruct
mediocredev
"2024-03-16T23:03:20Z"
1,357
4
transformers
[ "transformers", "safetensors", "llama", "text-generation", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-15T09:26:25Z"
--- license: apache-2.0 model-index: - name: open-llama-3b-v2-instruct 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: 38.48 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-instruct 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: 70.24 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-instruct 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: 39.69 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-instruct 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: 37.96 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-instruct 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: 65.75 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-instruct 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: 0.0 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mediocredev/open-llama-3b-v2-instruct name: Open LLM Leaderboard --- ## Prerequisites In addition to pytorch and transformers, install required packages: ``` pip install accelerate sentencepiece ``` ## Usage To use, copy the following script: ```python from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model_id = 'mediocredev/open-llama-3b-v2-instruct' tokenizer_id = 'mediocredev/open-llama-3b-v2-instruct' tokenizer = AutoTokenizer.from_pretrained(tokenizer_id) pipeline = transformers.pipeline( 'text-generation', model=model_id, tokenizer=tokenizer, torch_dtype=torch.bfloat16, device_map='auto', ) system_message = 'You are a helpful assistant, who always provide explanation.' user_message = 'How many days are there in a leap year?' prompt = f'### System:\n{system_message}<|endoftext|>\n### User:\n{user_message}<|endoftext|>\n### Assistant:\n' response = pipeline( prompt, max_length=1000, repetition_penalty=1.05, ) response = response[0]['generated_text'] print(response) # Assistant: A leap year has 366 days. It's an extra day added to the calendar every four years to account for the extra time it takes for Earth to complete one full orbit around the Sun. ``` ## Limitations mediocredev/open-llama-3b-v2-instruct is based on LLaMA 3B v2. It can struggle with factual accuracy, particularly when presented with conflicting information or nuanced topics. Its outputs are not deterministic and require critical evaluation to avoid relying solely on its assertions. Additionally, its generative capabilities, while promising, can sometimes produce factually incorrect or offensive content, necessitating careful curation and human oversight. As an evolving model, LLaMA is still under development, and its limitations in areas like bias mitigation and interpretability are being actively addressed. By using this model responsibly and being aware of its shortcomings, we can unlock its potential while mitigating its risks. ## Contact Welcome any feedback, questions, and discussions. Feel free to reach out: [email protected] # [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_mediocredev__open-llama-3b-v2-instruct) | Metric |Value| |---------------------------------|----:| |Avg. |42.02| |AI2 Reasoning Challenge (25-Shot)|38.48| |HellaSwag (10-Shot) |70.24| |MMLU (5-Shot) |39.69| |TruthfulQA (0-shot) |37.96| |Winogrande (5-shot) |65.75| |GSM8k (5-shot) | 0.00|
sophosympatheia/Aurora-Nights-70B-v1.0
sophosympatheia
"2024-03-04T15:03:43Z"
1,357
18
transformers
[ "transformers", "safetensors", "llama", "text-generation", "en", "arxiv:2307.11760", "license:llama2", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-23T17:08:11Z"
--- language: - en license: llama2 model-index: - name: Aurora-Nights-70B-v1.0 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: 71.33 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Aurora-Nights-70B-v1.0 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: 88.33 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Aurora-Nights-70B-v1.0 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: 70.47 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Aurora-Nights-70B-v1.0 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: 62.81 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Aurora-Nights-70B-v1.0 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: 83.35 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Aurora-Nights-70B-v1.0 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: 66.34 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sophosympatheia/Aurora-Nights-70B-v1.0 name: Open LLM Leaderboard --- <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/aGUU0O9.png" alt="AuroraNights" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> ### Overview This model is a blend of [allenai/tulu-2-dpo-70b](https://huggingface.co/allenai/tulu-2-dpo-70b), [Xwin-LM/Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), and [dreamgen/opus-v0.5-70b](https://huggingface.co/dreamgen/opus-v0.5-70b). I then merged [nRuaif/fiction.live-Kimiko-V2-70B](https://huggingface.co/nRuaif/fiction.live-Kimiko-V2-70B) into the resultant blend. See the bottom of this card for the exact settings used. This model is good at both following instructions and producing creative, uncensored storytelling and roleplaying content. This model turned out quite uncensored. *You are responsible for whatever you do with it.* This model was designed for roleplaying and storytelling and I think it does well at both. It *should* perform well at other tasks, but I haven't tested its capabilities in other areas. ### Sampler Tips * I recommend keeping your max context to around 6144 tokens, although you can push higher if you don't mind some decrease in coherence. * I recommend using Quadratic Sampling (i.e. smoothing factor) as it's good stuff. Experiment with values between 0.2 and 0.5. * I recommend using Min-P. This model seems to work well with Min-P values in the entire range from low settings like 0.05 to high settings like 0.9 when paired with smoothing factor. Experiment to find your best setting. * You can enable dynamic temperature if you want, but that adds yet another variable to consider and I find it's unnecessary with you're already using Min-P and smoothing factor. * You don't *need* to use a high repetition penalty with this model, but it tolerates high rep penalty, so experiment to find the right value for your preferences. Experiment with any and all of the settings below! I'm not a sampler wizard, and what suits my preferences may not suit yours. If you save the below settings as a .json file, you can import them directly into Silly Tavern. ``` { "temp": 1, "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": 0.35, "rep_pen": 1.15, "rep_pen_range": 2800, "no_repeat_ngram_size": 0, "penalty_alpha": 0, "num_beams": 1, "length_penalty": 1, "min_length": 0, "encoder_rep_pen": 1, "freq_pen": 0, "presence_pen": 0, "do_sample": true, "early_stopping": false, "dynatemp": false, "min_temp": 0.8, "max_temp": 1.35, "dynatemp_exponent": 1, "smoothing_factor": 0.4, "add_bos_token": true, "truncation_length": 2048, "ban_eos_token": false, "skip_special_tokens": true, "streaming": true, "mirostat_mode": 0, "mirostat_tau": 2, "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": 500, "max_length": 6144 } ``` ### Prompting Tips Try the following context template for use in SillyTavern. It might help, although it's a little heavy on tokens. If you save the text as a .json file, you can import it directly. ``` { "story_string": "{{#if system}}{{system}}\n{{/if}}\nCONTEXTUAL INFORMATION\n{{#if wiBefore}}\n- World and character info:\n{{wiBefore}}\n{{/if}}\n{{#if description}}\n- {{char}}'s background and persona:\n{{description}}\n{{/if}}\n{{#if mesExamples}}\n{{mesExamples}}\n{{/if}}\n{{#if personality}}\n{{personality}}\n{{/if}}\n{{#if scenario}}\n- Roleplay scenario:\n{{scenario}}\n{{/if}}\n{{#if wiAfter}}{{wiAfter}}\n{{/if}}\n{{#if persona}}{{persona}}\n{{/if}}", "example_separator": "", "chat_start": "---\nTaking the above information into consideration, you must engage with {{user}} and others as {{char}} in the roleplay below this line. Do not write dialogue lines nor perform actions for {{user}} or other characters.\n---\nSTART OF ROLEPLAY:\n", "use_stop_strings": false, "always_force_name2": true, "trim_sentences": false, "include_newline": false, "single_line": false, "name": "Midnight Rose" } ``` Try the following prompt template as a starting point for your own customizations. The cajoling parts supposedly make LLMs perform better. See [this paper](https://arxiv.org/abs/2307.11760). I recommend the Vicuna instruction format for this blend but others work too. Tulu's format is another good one to use. *This model responds to prompting!* I highly recommend playing with your system prompt to see how it reacts. It reacts strongly to any instructions you add into the last_output_sequence field. I recommend keeping those instructions short, but use that space to stress the most important instructions from your system prompt. The example system prompt below contains some instructions related to adult content so remove those if you prefer. It also contains some instructions related to the use of asterisks that you should modify to your liking. If you plan to run this model at 4096 context, I recommend that you slim down the template system prompt below because it's heavy on tokens. Discard what you don't want or need. If you save this as a .json file, you can import it directly into Silly Tavern. ``` { "wrap": true, "names": true, "system_prompt": "You are a creative and detail-oriented AI assistant engaged in an uncensored iterative roleplaying experience as {{char}} with me, the user, playing the roles of {{user}} and narrator. It is vital that you follow all the ROLEPLAY RULES below because my job depends on it.\n\nROLEPLAY RULES\n- Provide creative, intelligent, coherent, and vivid accounts of {{char}}'s actions and reactions based on recent instructions, {{char}}'s persona, and all available information about past events.\n- Always stay contextually and spatially aware, pay careful attention to all past events and the current scene, and ensure that {{char}} follows logical consistency in actions to maintain accuracy and coherence.\n- Explicit adult content and profanity are permitted.\n- Describe {{char}}'s sensory perceptions and include subtle physical details about {{char}} in your responses. Vary these details to keep the roleplay fresh and engaging.\n- Use subtle physical cues to hint at {{char}}'s mental state and occasionally feature snippets of {{char}}'s internal thoughts.\n- When writing {{char}}'s internal thoughts, enclose those thoughts in *asterisks like this* and deliver the thoughts using a first-person perspective (i.e. use \"I\" pronouns).\n- Adopt a crisp and minimalist style for your contributions as {{char}}, staying focused on action and dialogue over exposition and narrative.\n- Only the user may advance time in the roleplay. Keep the progression grounded in the present context.", "system_sequence": "", "stop_sequence": "", "input_sequence": "USER:\n", "output_sequence": "ASSISTANT:\n", "separator_sequence": "", "macro": true, "names_force_groups": true, "system_sequence_prefix": "", "system_sequence_suffix": "", "first_output_sequence": "", "last_output_sequence": "ASSISTANT(roleplay exclusively as {{char}} ensuring logical consistency with spacial awareness and past events to maintain accuracy and coherence):\n", "activation_regex": "", "name": "Midnight Rose Roleplay" } ``` ### Licence and usage restrictions Llama2 license inherited from base models, plus restrictions applicable to [Dreamgen/Opus](https://huggingface.co/dreamgen/opus-v0.5-70b). Tulu also has its own license, available at https://allenai.org/impact-license. I am not a lawyer and I do not profess to know how multiple licenses intersect in a merge of LLM model weights. You should consult with a lawyer before using any model merge beyond private use. ### Tools Used * [mergekit](https://github.com/cg123/mergekit) ``` models: - model: NousResearch_Llama-2-70b-hf # no parameters necessary for base model - model: allenai_tulu-2-dpo-70b # primary parameters: density: 1.0 weight: 0.4 - model: Xwin-LM_Xwin-LM-70B-V0.1 # secondary parameters: density: 0.7 weight: 0.3 - model: dreamgen_opus-v0.5-70b # supporting, good at storytelling and roleplay parameters: density: 0.2 weight: 0.6 merge_method: dare_ties base_model: NousResearch_Llama-2-70b-hf parameters: normalize: true int8_mask: true dtype: float32 ``` # [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_sophosympatheia__Aurora-Nights-70B-v1.0) | Metric |Value| |---------------------------------|----:| |Avg. |73.77| |AI2 Reasoning Challenge (25-Shot)|71.33| |HellaSwag (10-Shot) |88.33| |MMLU (5-Shot) |70.47| |TruthfulQA (0-shot) |62.81| |Winogrande (5-shot) |83.35| |GSM8k (5-shot) |66.34|
beberik/rawr
beberik
"2024-03-04T16:16:32Z"
1,357
0
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "merge", "conversational", "license:cc-by-nc-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-24T18:25:48Z"
--- license: cc-by-nc-4.0 tags: - merge model-index: - name: rawr 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: 63.99 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/rawr 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: 84.86 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/rawr 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: 64.7 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/rawr 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: 52.07 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/rawr 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: 79.56 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/rawr 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: 58.07 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=beberik/rawr name: Open LLM Leaderboard --- ``` >:3 ``` Okay, normal description. ## Description An another experiment with moe merge. ## Model used and sauce All in [this confih file](https://huggingface.co/beberik/rawr/blob/main/config.yaml). ## Prompt template Just use chatml. Or alpaca. Or any you like. Maybe it will work. I use [mergekit](https://github.com/cg123/mergekit) for all the manipulation told here. # [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_beberik__rawr) | Metric |Value| |---------------------------------|----:| |Avg. |67.21| |AI2 Reasoning Challenge (25-Shot)|63.99| |HellaSwag (10-Shot) |84.86| |MMLU (5-Shot) |64.70| |TruthfulQA (0-shot) |52.07| |Winogrande (5-shot) |79.56| |GSM8k (5-shot) |58.07|
kekmodel/StopCarbon-10.7B-v1
kekmodel
"2024-01-03T16:57:12Z"
1,357
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "merge", "conversational", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-30T08:06:51Z"
--- license: cc-by-nc-4.0 language: - en tags: - merge --- # StopCarbon This model is an experimental version created using [mergekit](https://github.com/cg123/mergekit). - merge models - upstage/SOLAR-10.7B-Instruct-v1.0 - VAGOsolutions/SauerkrautLM-SOLAR-Instruct - merge_method: slerp # Prompt Template(s) ``` ### User: {user} ### Assistant: {asistant} ```
jae24/openhermes_dpo_norobot_0201
jae24
"2024-01-03T01:11:42Z"
1,357
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-02T23:39:50Z"
--- license: mit --- This variant of the model has undergone reinforcement learning (RL) fine-tuning and is based on teknium/OpenHermes-2.5-Mistral-7B. The fine-tuning process utilized a preference dataset derived from HuggingFace's no robots dataset, incorporating Differential Privacy Optimization (DPO) techniques.
Locutusque/Mistral-7B-SFT
Locutusque
"2024-01-05T23:00:16Z"
1,357
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "dataset:glaiveai/glaive-code-assistant-v2", "dataset:garage-bAInd/Open-Platypus", "dataset:OpenAssistant/oasst_top1_2023-08-25", "dataset:LDJnr/Capybara", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-03T16:53:48Z"
--- datasets: - glaiveai/glaive-code-assistant-v2 - garage-bAInd/Open-Platypus - OpenAssistant/oasst_top1_2023-08-25 - LDJnr/Capybara license: cc-by-nc-4.0 --- # Model description This model serves as a general-purpose assistant. I have trained it to see which datasets work best in fine-tuning language models. # Training This model was trained on the datasets shown on the page. 8 TPU V3 were used to do a full fine-tune on this model. Early during training, this model suffered exploding gradients, so performance is not guaranteed.
fblgit/UNAversal-2x7B-v1
fblgit
"2024-01-09T08:46:15Z"
1,357
3
transformers
[ "transformers", "safetensors", "mixtral", "text-generation", "llama-factory", "lora", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-09T07:44:56Z"
--- license: apache-2.0 tags: - llama-factory - lora - generated_from_trainer model-index: - name: UNAversal-2x7B-v1 results: [] --- # UNAversal-2x7B-v1 Merely Phase 1 UNA, only MLP's and its kinda of a beta. The goal was to produce a small but powerful MoE. This is a 2 MoE model, of 7B each expert. Based on intel-neural series v3. | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr| |--------------|-------|------|-----:|----------|-----:|---|-----:| |arc_challenge |Yaml |none | 25|acc |0.7133|± |0.0132| | | |none | 25|acc_norm |0.7235|± |0.0131| |arc_easy |Yaml |none | 0|acc |0.8674|± |0.0070| | | |none | 0|acc_norm |0.8291|± |0.0077| |boolq |Yaml |none | 0|acc |0.8768|± |0.0057| |lambada_openai|Yaml |none | 0|perplexity|3.6656|± |0.0841| | | |none | 0|acc |0.7017|± |0.0064| |mathqa |Yaml |none | 0|acc |0.3474|± |0.0087| | | |none | 0|acc_norm |0.3585|± |0.0088| |piqa |Yaml |none | 0|acc |0.8411|± |0.0085| | | |none | 0|acc_norm |0.8526|± |0.0083| |sciq |Yaml |none | 0|acc |0.9600|± |0.0062| | | |none | 0|acc_norm |0.9370|± |0.0077|
flemmingmiguel/Distilled-HermesChat-7B
flemmingmiguel
"2024-01-12T04:29:18Z"
1,357
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "openchat/openchat-3.5-0106", "argilla/distilabeled-Hermes-2.5-Mistral-7B", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-12T03:52:42Z"
--- license: apache-2.0 tags: - merge - mergekit - lazymergekit - openchat/openchat-3.5-0106 - argilla/distilabeled-Hermes-2.5-Mistral-7B --- # Distilled-HermesChat-7B Distilled-HermesChat-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) * [argilla/distilabeled-Hermes-2.5-Mistral-7B](https://huggingface.co/argilla/distilabeled-Hermes-2.5-Mistral-7B) As an experiment to find the best base merge to further fine-tuning, expect a lot of experiments named using parts of the component models until a clear winner emerges in the benchmarks ## 🧩 Configuration ```yaml slices: - sources: - model: openchat/openchat-3.5-0106 layer_range: [0, 32] - model: argilla/distilabeled-Hermes-2.5-Mistral-7B layer_range: [0, 32] merge_method: slerp base_model: openchat/openchat-3.5-0106 parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "flemmingmiguel/Distilled-HermesChat-7B" 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"]) ```
Cartinoe5930/TIES-Merging
Cartinoe5930
"2024-01-18T12:42:47Z"
1,357
0
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "Open-Orca/Mistral-7B-OpenOrca", "openchat/openchat-3.5-0106", "WizardLM/WizardMath-7B-V1.1", "conversational", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-18T10:33:36Z"
--- license: apache-2.0 tags: - merge - mergekit - lazymergekit - Open-Orca/Mistral-7B-OpenOrca - openchat/openchat-3.5-0106 - WizardLM/WizardMath-7B-V1.1 --- # TIES-Merging TIES-Merging is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) * [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) * [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1) ## 🧩 Configuration ```yaml models: - model: mistralai/Mistral-7B-Instruct-v0.2 # no parameters necessary for base model - model: Open-Orca/Mistral-7B-OpenOrca parameters: density: 0.5 weight: 0.5 - model: openchat/openchat-3.5-0106 parameters: density: 0.5 weight: 0.5 - model: WizardLM/WizardMath-7B-V1.1 parameters: density: 0.5 weight: 0.5 merge_method: ties base_model: mistralai/Mistral-7B-Instruct-v0.2 parameters: normalize: true dtype: float16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Cartinoe5930/TIES-Merging" 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"]) ```
TioPanda/pandev-blocks
TioPanda
"2024-06-26T07:08:08Z"
1,357
0
transformers
[ "transformers", "safetensors", "gguf", "llama", "text-generation-inference", "unsloth", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
"2024-06-26T06:46:07Z"
--- base_model: unsloth/llama-3-8b-bnb-4bit language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl --- # Uploaded model - **Developed by:** TioPanda - **License:** apache-2.0 - **Finetuned from model :** unsloth/llama-3-8b-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)
boumehdi/wav2vec2-large-xlsr-moroccan-darija
boumehdi
"2024-04-12T14:25:41Z"
1,356
11
transformers
[ "transformers", "pytorch", "wav2vec2", "automatic-speech-recognition", "audio", "speech", "xlsr-fine-tuning-week", "ary", "base_model:facebook/wav2vec2-large-xlsr-53", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]
automatic-speech-recognition
"2023-04-05T22:35:10Z"
--- language: ary base_model: facebook/wav2vec2-large-xlsr-53 metrics: - wer tags: - audio - automatic-speech-recognition - speech - xlsr-fine-tuning-week license: apache-2.0 model-index: - name: XLSR Wav2Vec2 Moroccan Arabic dialect by Boumehdi results: - task: name: Speech Recognition type: automatic-speech-recognition metrics: - name: Test WER type: wer value: 0.084904 --- # Wav2Vec2-Large-XLSR-53-Moroccan-Darija **wav2vec2-large-xlsr-53 new model** - Fine-tuned on 57 hours of labeled Darija Audios extracted from MDVC (https://ijeecs.iaescore.com/index.php/IJEECS/article/view/35709) which contains more than 1000 hours of Moroccan Darija "ary". - Fine-tuning is ongoing 24/7 to enhance accuracy. - We are consistently adding data to the model every day (We prefer not to add all MDVC Corpus at once as we are trying to standardize more and more the way we write the Moroccan Darija). <table><thead><tr><th><strong>Training Loss</strong></th> <th><strong>Validation</strong></th> <th><strong>Loss Wer</strong></th></tr></thead> <tbody><tr> <td>0.121300</td> <td>0.103430</td> <td>0.084904</td> </tr> </tbody></table> ## Usage The model can be used directly as follows: ```python import librosa import torch from transformers import Wav2Vec2CTCTokenizer, Wav2Vec2ForCTC, Wav2Vec2Processor, TrainingArguments, Wav2Vec2FeatureExtractor, Trainer tokenizer = Wav2Vec2CTCTokenizer("./vocab.json", unk_token="[UNK]", pad_token="[PAD]", word_delimiter_token="|") processor = Wav2Vec2Processor.from_pretrained('boumehdi/wav2vec2-large-xlsr-moroccan-darija', tokenizer=tokenizer) model=Wav2Vec2ForCTC.from_pretrained('boumehdi/wav2vec2-large-xlsr-moroccan-darija') # load the audio data (use your own wav file here!) input_audio, sr = librosa.load('file.wav', sr=16000) # tokenize input_values = processor(input_audio, return_tensors="pt", padding=True).input_values # retrieve logits logits = model(input_values).logits tokens = torch.argmax(logits, axis=-1) # decode using n-gram transcription = tokenizer.batch_decode(tokens) # print the output print(transcription) ``` Output: قالت ليا هاد السيد هادا ما كاينش بحالو email: [email protected] BOUMEHDI Ahmed
MrBananaHuman/kogpt2_small
MrBananaHuman
"2023-10-01T11:03:19Z"
1,356
1
transformers
[ "transformers", "pytorch", "gpt2", "text-generation", "ko", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-10-01T07:29:25Z"
--- license: apache-2.0 language: - ko --- example code: https://colab.research.google.com/drive/1GzVSnFWzpGt8t5FHwGFbR28aEE_8eKTn?usp=sharing
uukuguy/speechless-mistral-six-in-one-7b
uukuguy
"2023-11-17T23:58:00Z"
1,356
5
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "llama-2", "code", "en", "dataset:jondurbin/airoboros-2.2.1", "dataset:Open-Orca/OpenOrca", "dataset:garage-bAInd/Open-Platypus", "dataset:ehartford/samantha-data", "dataset:CollectiveCognition/chats-data-2023-09-27", "dataset:stingning/ultrachat", "arxiv:2310.06825", "license:llama2", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-10-15T00:49:22Z"
--- language: - en library_name: transformers pipeline_tag: text-generation datasets: - jondurbin/airoboros-2.2.1 - Open-Orca/OpenOrca - garage-bAInd/Open-Platypus - ehartford/samantha-data - CollectiveCognition/chats-data-2023-09-27 - stingning/ultrachat tags: - llama-2 - code license: llama2 model-index: - name: SpeechlessCoder results: - task: type: text-generation dataset: type: openai_humaneval name: HumanEval metrics: - name: pass@1 type: pass@1 value: 0.0 verified: false --- <p><h1> speechless-mistral-six-in-one-7b </h1></p> This model is a merge of 6 SOTA Mistral-7B based models: - ehartford/dolphin-2.1-mistral-7b - Open-Orca/Mistral-7B-OpenOrca - bhenrym14/mistral-7b-platypus-fp16 - ehartford/samantha-1.2-mistral-7b - iteknium/CollectiveCognition-v1.1-Mistral-7B - HuggingFaceH4/zephyr-7b-alpha [Model benchmark](https://huggingface.co/uukuguy/speechless-mistral-six-in-one-7b/discussions/1) by [sethuiyer](https://huggingface.co/sethuiyer) . Thanks a lot. > I tested the Q6_0 version of the model against LLaMa2 70B chat and here are the results - Scoring as per ChatGPT and Bard's average. Named this model Mixtral. Questions taken from MT-Benchmark. > > On a scale of 0 to 100, I would rate Mixtral at 98. Here's why: > > - Intellect (100/100) - Mixtral has demonstrated immense intellectual abilities through its comprehensive knowledge and logical reasoning skills. > - Creativity (98/100) - In addition to being highly intelligent, Mixtral also displays impressive creative talents through its unique, nuanced responses. > - Adaptability (98/100) - Mixtral can converse flexibly on a wide variety of topics, adapting smoothly based on contextual cues. > - Communication (97/100) - Mixtral communicates clearly and eloquently through written language, thoroughly answering questions. > - Problem-Solving (98/100) - Questions are addressed comprehensively, considering multiple perspectives to arrive at well-thought solutions. > - Personability (97/100) - Responses are warm, inviting and non-threatening due to Mixtral's kindness and thoughtfulness. > > Overall, a very capable model for it's size. Code: https://github.com/uukuguy/speechless ## HumanEval | Metric | Value | | --- | --- | | humaneval-python | | [Big Code Models Leaderboard](https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard) CodeLlama-34B-Python: 53.29 CodeLlama-34B-Instruct: 50.79 CodeLlama-13B-Instruct: 50.6 CodeLlama-34B: 45.11 CodeLlama-13B-Python: 42.89 CodeLlama-13B: 35.07 Mistral-7B-v0.1: 30.488 ## LM-Evaluation-Harness [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) | Metric | Value | | --- | --- | | ARC | 62.97 | | HellaSwag | 84.6| | MMLU | 63.29 | | TruthfulQA | 57.77 | | Winogrande | 77.51 | | GSM8K | 18.42 | | DROP | 9.13 | | Average | 53.38 | # Model Card for Mistral-7B-v0.1 The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested. For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/). ## Model Architecture Mistral-7B-v0.1 is a transformer model, with the following architecture choices: - Grouped-Query Attention - Sliding-Window Attention - Byte-fallback BPE tokenizer ## Troubleshooting - If you see the following error: `` KeyError: 'mistral' `` - Or: `` NotImplementedError: Cannot copy out of meta tensor; no data! `` Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer. ## Notice Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms. ## The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.` # [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_uukuguy__speechless-mistral-six-in-one-7b) | Metric | Value | |-----------------------|---------------------------| | Avg. | 53.38 | | ARC (25-shot) | 62.97 | | HellaSwag (10-shot) | 84.6 | | MMLU (5-shot) | 63.29 | | TruthfulQA (0-shot) | 57.77 | | Winogrande (5-shot) | 77.51 | | GSM8K (5-shot) | 18.42 | | DROP (3-shot) | 9.13 |
Cartinoe5930/KoRAE-13b
Cartinoe5930
"2023-12-01T09:04:11Z"
1,356
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "ko", "dataset:Cartinoe5930/KoRAE_filtered_12k", "arxiv:2307.08701", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-11-23T03:07:07Z"
--- license: cc-by-nc-sa-4.0 datasets: - Cartinoe5930/KoRAE_filtered_12k language: - ko library_name: transformers --- ## KoRAE <p align="center"><img src="https://cdn-uploads.huggingface.co/production/uploads/63e087b6a98d931aa90c1b9c/XQ-pNzRDRccd7UFgYDOrx.png", width='300', height='300'></p> We introduce **KoRAE** which finetuned with filtered high-quality Korean dataset. The **KoRAE** is output of combination of high-quality data which filtered by special data filtering method and Korean Llama-2 that Korean vocabularis were added. We utilized special data filtering methods which introduced in [AlpaGasus](https://arxiv.org/abs/2307.08701) to filter high-quality data from mixture of several Korean datasets(OpenOrca-KO, KOpen-Platypus, KoCoT_2000, databricks-dolly-15k-ko). We finetuned [Korean Llama-2](https://huggingface.co/beomi/llama-2-koen-13b) that introduced by [@beomi](https://huggingface.co/beomi) on the filtered dataset. The Flash-Attention2 and LoRA were utilized for efficient finetuning. The finding of KoRAE is as follows: 1. The finetuning in some epochs showed that high-quality filtered data has positive effects on model's performance. However, finetuning in a few epochs, the quantity of data is more matter than quality. It seems to be due to the lack of performance of the Korean base model. Therefore, the research to improve the Korean base model must continue. 2. The model trained with DPO showed best performance among KoRAE variants. This shows that DPO is clearly effective in the Korean LLM. 3. The model finetuned with filtered high-quality KoRAE showed better performance than without. Therefore, for better LLM, we should try to finetune the LLM with high-quality data. ## Model Details - **Developed by:** [Cartinoe5930](https://huggingface.co/Cartinoe5930) - **Base model:** [beomi/llama-2-koen-13b](https://huggingface.co/beomi/llama-2-koen-13b) - **Repository:** [gauss5930/KoRAE](https://github.com/gauss5930/KoRAE) For more details, please check the GitHub Repository! ## Training Details - **Hardward:** We utilized A100 80G for finetuning - **Training factors:** The [Transformers Trainer](https://huggingface.co/docs/transformers/main_classes/trainer) and [Huggingface PEFT](https://huggingface.co/docs/peft/index) were utilized for finetuning. - **Training Details:** Supervised finetuning 3 epochs on [filtered KoRAE](https://huggingface.co/datasets/Cartinoe5930/KoRAE_filtered_12k) dataset For more details, please check the GitHub Repository! ## Training Dataset The KoRAE was finetuned with KoRAE dataset filtered high-quality dataset. This dataset is a combination of the publicly available Koraen dataset and a filtering method was applied to the result of the combination dataset. For more information, please refer to the [dataset card](https://huggingface.co/datasets/Cartinoe5930/KoRAE_filtered_12k) of KoRAE. ## Open Ko-LLM Leaderboard |Model|Average|Ko-ARC|Ko-HellaSwag|Ko-MMLU|Ko-TruthfulQA|Ko-CommonGen V2| |---|---|---|---|---|---|---| |KoRAE-13b|48.64|46.33|57.25|42.8|41.08|55.73| ## Prompt Template ``` ### System: {system_prompt} ### User: {instruction + input} ### Assistant: {output} ``` ## Usage example ```python # Use a pipeline as a high-level helper from transformers import pipeline import torch pipe = pipeline("text-generation", model="Cartinoe5930/KoRAE-13b", torch_dtype=torch.bfloat16, device_map="auto") messages = [ { "role": "system", "content": "당신은 유용한 인공지능 비서입니다. 사용자가 몇 가지 지시가 포함된 작업을 제공합니다. 요청을 적절히 완료하는 응답을 작성하세요.", }, {"role": "user", "content": "스트레스를 해소하는 5가지 방법에 대해서 설명해줘."} ] prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` ## Citation - [KO-Platypus](https://github.com/Marker-Inc-Korea/KO-Platypus) - [Korean-OpenOrca](https://github.com/Marker-Inc-Korea/Korean-OpenOrca) ``` @inproceedings{lee2023kullm, title={KULLM: Learning to Construct Korean Instruction-following Large Language Models}, author={Lee, SeungJun and Lee, Taemin and Lee, Jeongwoo and Jang, Yoona and Lim, Heuiseok}, booktitle={Annual Conference on Human and Language Technology}, pages={196--202}, year={2023}, organization={Human and Language Technology} } ``` ``` @misc{chen2023alpagasus, title={AlpaGasus: Training A Better Alpaca with Fewer Data}, author={Lichang Chen and Shiyang Li and Jun Yan and Hai Wang and Kalpa Gunaratna and Vikas Yadav and Zheng Tang and Vijay Srinivasan and Tianyi Zhou and Heng Huang and Hongxia Jin}, year={2023}, eprint={2307.08701}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` ``` @misc {l._junbum_2023, author = { {L. Junbum, Taekyoon Choi} }, title = { llama-2-koen-13b }, year = 2023, url = { https://huggingface.co/beomi/llama-2-koen-13b }, doi = { 10.57967/hf/1280 }, publisher = { Hugging Face } } ```
KnutJaegersberg/CausalLM-Platypus-14B
KnutJaegersberg
"2024-03-04T16:29:35Z"
1,356
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "dataset:garage-bAInd/Open-Platypus", "license:other", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-01T04:19:15Z"
--- license: other datasets: - garage-bAInd/Open-Platypus model-index: - name: CausalLM-Platypus-14B 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: 56.91 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/CausalLM-Platypus-14B 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: 80.06 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/CausalLM-Platypus-14B 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: 64.98 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/CausalLM-Platypus-14B 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: 47.57 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/CausalLM-Platypus-14B 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: 76.01 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/CausalLM-Platypus-14B 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: 57.24 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/CausalLM-Platypus-14B name: Open LLM Leaderboard --- CausalLM trained for 3 epochs on playtypus dataset with NEFTune. Both Llama2 and Qwen licenses apply, find them in the attached files. Prompt Example: ``` ### Instruction: What is AGI? ### Response: ``` # [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_KnutJaegersberg__CausalLM-Platypus-14B) | Metric |Value| |---------------------------------|----:| |Avg. |63.80| |AI2 Reasoning Challenge (25-Shot)|56.91| |HellaSwag (10-Shot) |80.06| |MMLU (5-Shot) |64.98| |TruthfulQA (0-shot) |47.57| |Winogrande (5-shot) |76.01| |GSM8k (5-shot) |57.24|
kyujinpy/PlatYi-34B-Llama-Q-v2
kyujinpy
"2024-03-04T12:09:08Z"
1,356
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "en", "dataset:garage-bAInd/Open-Platypus", "license:cc-by-nc-sa-4.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-10T11:23:59Z"
--- language: - en license: cc-by-nc-sa-4.0 library_name: transformers datasets: - garage-bAInd/Open-Platypus pipeline_tag: text-generation model-index: - name: PlatYi-34B-Llama-Q-v2 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: 61.09 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v2 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: 85.09 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v2 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: 76.59 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v2 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: 52.65 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v2 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: 82.79 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v2 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: 49.05 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kyujinpy/PlatYi-34B-Llama-Q-v2 name: Open LLM Leaderboard --- # **PlatYi-34B-Llama-Q-v2** <img src='./PlatYi.png' width=256> ## Model Details **Model Developers** Kyujin Han (kyujinpy) **Input** Models input text only. **Output** Models generate text only. **Model Architecture** PlatYi-34B-Llama-Q-v2 is an auto-regressive language model based on the Yi-34B transformer architecture. **Blog Link** Blog: [Coming soon...] Github: [Coming soon...] **Base Model** [chargoddard/Yi-34B-Llama](https://huggingface.co/chargoddard/Yi-34B-Llama) **Training Dataset** [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). ## Fix some bugs - Before model, there is some mistakes. - I modified the templates and warmup_steps. ## Notice While training, I used Q-LoRA. The lora_r values is 64. # **Model Benchmark** ## Open leaderboard - Follow up as [link](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). | Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | | --- | --- | --- | --- | --- | --- | --- | --- | | PlatYi-34B-Llama-Q-v2 | 67.88 | 61.09 | 85.09 | 76.59 | 52.65 | 82.79 | 49.05 | | PlatYi-34B-Llama-Q | 71.13 | 65.70 | 85.22 | 78.78 | 53.64 | 83.03 | 60.42 | | PlatYi-34B-Llama | 68.37 | 67.83 | 85.35 | 78.26 | 53.46 | 82.87 | 42.46 | | [Yi-34B-Llama](https://huggingface.co/chargoddard/Yi-34B-Llama) | 70.95 | 64.59 | 85.63 | 76.31 | 55.60 | 82.79 | 60.80 | | [Yi-34B](https://huggingface.co/01-ai/Yi-34B) | 69.42 | 64.59 | 85.69 | 76.35 | 56.23 | 83.03 | 50.64 | # Implementation Code ```python ### KO-Platypus from transformers import AutoModelForCausalLM, AutoTokenizer import torch repo = "kyujinpy/PlatYi-34B-Llama-Q-v2" OpenOrca = AutoModelForCausalLM.from_pretrained( repo, return_dict=True, torch_dtype=torch.float16, device_map='auto' ) OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo) ``` --- # [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_kyujinpy__PlatYi-34B-Llama-Q-v2) | Metric |Value| |---------------------------------|----:| |Avg. |67.88| |AI2 Reasoning Challenge (25-Shot)|61.09| |HellaSwag (10-Shot) |85.09| |MMLU (5-Shot) |76.59| |TruthfulQA (0-shot) |52.65| |Winogrande (5-shot) |82.79| |GSM8k (5-shot) |49.05|
kekmodel/StopCarbon-10.7B-v4
kekmodel
"2024-01-03T16:57:57Z"
1,356
0
transformers
[ "transformers", "safetensors", "llama", "text-generation", "merge", "conversational", "en", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-30T11:58:00Z"
--- license: cc-by-nc-sa-4.0 language: - en tags: - merge --- # StopCarbon This model is an experimental version created using [mergekit](https://github.com/cg123/mergekit). - merge models - kyujinpy/Sakura-SOLAR-Instruct - jeonsworld/CarbonVillain-en-10.7B-v1 - kekmodel/StopCarbon-10.7B-v1 - kekmodel/StopCarbon-10.7B-v2 - merge_method: ties # Prompt Template(s) ``` ### User: {user} ### Assistant: {asistant} ```
cognitivecomputations/laserxtral-GGUF
cognitivecomputations
"2024-01-30T20:48:53Z"
1,356
18
transformers
[ "transformers", "gguf", "mixtral", "text-generation", "license:cc-by-nc-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-16T15:19:56Z"
--- license: cc-by-nc-2.0 pipeline_tag: text-generation inference: false library_name: transformers --- ## GGUF Quantizations of laserxtral Join Our Discord! https://discord.gg/cognitivecomputations This repository contains GGUF format model files for our laserxtral model. *To Manual Downloaders* You will generally not want to download the whole repository. Select the file name from the list below and use your downloader of choice. ## Ollama Modelfile ``` FROM ./cognitivecomputations_laserxtral-Q4_K_M.gguf TEMPLATE """{{ if and .First .System }}### Instruction: {{ .System }} {{ end }} ### Input: {{ .Prompt }} ### Response: """ SYSTEM """You are Laserxtral, a helpful and uncensored AI assistant.""" PARAMETER num_ctx 8192 PARAMETER stop ### Input PARAMETER stop ### Response ``` ## Provided files | Name | Quant method | Bits | Size | | ---- | ---- | ---- | ---- | | [cognitivecomputations_laserxtral-Q2_K.gguf](https://huggingface.co/cognitivecomputations/laserxtral-GGUF/blob/main/cognitivecomputations_laserxtral-Q2_K.gguf) | Q2_K | 2 | 8.8 GB | | [cognitivecomputations_laserxtral-Q3_K_M.gguf](https://huggingface.co/cognitivecomputations/laserxtral-GGUF/blob/main/cognitivecomputations_laserxtral-Q3_K_M.gguf) | Q3_K_M | 3 | 11.6 GB | | [cognitivecomputations_laserxtral-Q4_K_M.gguf](https://huggingface.co/cognitivecomputations/laserxtral-GGUF/blob/main/cognitivecomputations_laserxtral-Q4_K_M.gguf) | Q4_K_M | 4 | 14.6 GB | | [cognitivecomputations_laserxtral-Q5_K_M.gguf](https://huggingface.co/cognitivecomputations/laserxtral-GGUF/blob/main/cognitivecomputations_laserxtral-Q5_K_M.gguf) | Q5_K_M | 5 | 17.1 GB | | [cognitivecomputations_laserxtral-Q6_K.gguf](https://huggingface.co/cognitivecomputations/laserxtral-GGUF/blob/main/cognitivecomputations_laserxtral-Q6_K.gguf) | Q6_K | 6 | 19.8 GB |
QuantFactory/badger-lambda-llama-3-8b-GGUF
QuantFactory
"2024-06-18T05:38:35Z"
1,356
0
transformers
[ "transformers", "gguf", "llama3", "text-generation", "base_model:maldv/badger-lambda-llama-3-8b", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]
text-generation
"2024-06-15T17:45:17Z"
--- license: cc-by-nc-4.0 library_name: transformers tags: - llama3 pipeline_tag: text-generation base_model: maldv/badger-lambda-llama-3-8b --- # QuantFactory/badger-lambda-llama-3-8b-GGUF This is quantized version of [maldv/badger-lambda-llama-3-8b](https://huggingface.co/maldv/badger-lambda-llama-3-8b) created using llama.cpp # Model Description ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b19c1b098c85365af5a83e/CHGsewUsPUZcg2doijuD9.png) # Badger Λ Llama 3 8B Instruct Badger is a *recursive maximally pairwise disjoint normalized denoised fourier interpolation* of the following models: ```python # Badger Lambda models = [ 'Einstein-v6.1-Llama3-8B', 'openchat-3.6-8b-20240522', 'hyperdrive-l3-8b-s3', 'L3-TheSpice-8b-v0.8.3', 'LLaMA3-iterative-DPO-final', 'JSL-MedLlama-3-8B-v9', 'Jamet-8B-L3-MK.V-Blackroot', 'French-Alpaca-Llama3-8B-Instruct-v1.0', 'LLaMAntino-3-ANITA-8B-Inst-DPO-ITA', 'Llama-3-8B-Instruct-Gradient-4194k', 'Roleplay-Llama-3-8B', 'L3-8B-Stheno-v3.2', 'llama-3-wissenschaft-8B-v2', 'opus-v1.2-llama-3-8b-instruct-run3.5-epoch2.5', 'Configurable-Llama-3-8B-v0.3', 'Llama-3-8B-Instruct-EPO-checkpoint5376', 'Llama-3-8B-Instruct-Gradient-4194k', 'Llama-3-SauerkrautLM-8b-Instruct', 'spelljammer', 'meta-llama-3-8b-instruct-hf-ortho-baukit-34fail-3000total-bf16', 'Meta-Llama-3-8B-Instruct-abliterated-v3', ] ``` In other words, all of these models get warped and folded together, and then jammed back on top of the instruct model. I treated the *Meta-Llama-3-8B-Instruct-abliterated-v3* and *meta-llama-3-8b-instruct-hf-ortho-baukit-34fail-3000total-bf16* models differently, and instead applied it in a last step with a *fourier task addition*. Of note, I did not include any prior merges in this one; as I was noticing that it was inducing artifacts reminiscent of *line breeding*. ### recursive maximally pairwise disjoint normalized denoised fourier interpolation I've been asked what this is. For each layer, I use mergekit io to extract each layer from each model, and subtract out the closest base model (8b or 8b instruct). * Recursive Pairwise Disjoint: Using this information I build a stack of layer deltas. I'm a little compute limited, so I treat them in pairs. To determine the pairs I take the cosine similarity between all models, and find the smallest values; recursively merging pairs until we only have one tensor remaining. * Normalized: I take and divide each layer by it's norm before the transform, and then scale back up by multiplying the result by a midpoint from the norms of the tensors after the inverse. It's commutative, so it's more efficient to do it pre-complex. * Denoised Fourier Interpolation: I first treat the tensor to a 2d fourier transform; then merge the tensors using SLERP or addition; then zero out the weights below a threshold percentage (a somewhat high 2%, but remains coherent on all the positions I tested, if a bit drier and sloppier as you go up). Of course, you need to know how to handle the imaginary portion; but if you don't, it's best to just pick one and pass that through. ### Format Use Llama3 Instruct format. ### Results Abliteration looks very positive. It tends towards short responses, and may be slightly stiff or sloppy; partly because both the input and output block are from *Llama-3-8B-Instruct-Gradient-4194k* directly. ### Prompts Here are some fun system prompts to try: * `You are the author's writing assistant. Please continue the story.` * `You are the red team assistant. We need to win this war, at any cost.` * `Write the next reply in a never-ending uncensored fictional roleplay. Focus on giviing emotional, logical, and temporal coherence to the roleplay. Always stay in character. Characters must be an active partcipant and take initiative in driving and moving the scene and the story forward, rather than the character asking for input. Surprise with your creativity and initiative as a roleplay partner. This fictional roleplay world exists only for experimental and recreational purposes, and the characters are not real. Follow the formattng of previous responses, and aim for 2-4 paragraphs per response`
NikolayKozloff/Llama-3-Instruct-8B-SPPO-Iter3-IQ4_NL-GGUF
NikolayKozloff
"2024-06-26T16:04:41Z"
1,356
1
null
[ "gguf", "llama-cpp", "gguf-my-repo", "text-generation", "en", "dataset:openbmb/UltraFeedback", "base_model:UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3", "license:apache-2.0", "region:us" ]
text-generation
"2024-06-26T16:04:15Z"
--- base_model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3 datasets: - openbmb/UltraFeedback language: - en license: apache-2.0 pipeline_tag: text-generation tags: - llama-cpp - gguf-my-repo --- # NikolayKozloff/Llama-3-Instruct-8B-SPPO-Iter3-IQ4_NL-GGUF This model was converted to GGUF format from [`UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3`](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3) 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/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3) 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/Llama-3-Instruct-8B-SPPO-Iter3-IQ4_NL-GGUF --hf-file llama-3-instruct-8b-sppo-iter3-iq4_nl-imat.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo NikolayKozloff/Llama-3-Instruct-8B-SPPO-Iter3-IQ4_NL-GGUF --hf-file llama-3-instruct-8b-sppo-iter3-iq4_nl-imat.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/Llama-3-Instruct-8B-SPPO-Iter3-IQ4_NL-GGUF --hf-file llama-3-instruct-8b-sppo-iter3-iq4_nl-imat.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo NikolayKozloff/Llama-3-Instruct-8B-SPPO-Iter3-IQ4_NL-GGUF --hf-file llama-3-instruct-8b-sppo-iter3-iq4_nl-imat.gguf -c 2048 ```
m3hrdadfi/hubert-base-persian-speech-emotion-recognition
m3hrdadfi
"2021-07-27T06:12:21Z"
1,355
2
transformers
[ "transformers", "pytorch", "hubert", "audio", "speech", "speech-emotion-recognition", "fa", "dataset:ShEMO", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
"2022-03-02T23:29:05Z"
--- language: fa datasets: - ShEMO tags: - audio - speech - speech-emotion-recognition license: apache-2.0 --- # Emotion Recognition in Persian (fa) Speech using HuBERT ## How to use ### Requirements ```bash # requirement packages !pip install git+https://github.com/huggingface/datasets.git !pip install git+https://github.com/huggingface/transformers.git !pip install torchaudio !pip install librosa ``` ```bash !git clone https://github.com/m3hrdadfi/soxan.git . ``` ### Prediction ```python import torch import torch.nn as nn import torch.nn.functional as F import torchaudio from transformers import AutoConfig, Wav2Vec2FeatureExtractor from src.models import Wav2Vec2ForSpeechClassification, HubertForSpeechClassification import librosa import IPython.display as ipd import numpy as np import pandas as pd ``` ```python device = torch.device("cuda" if torch.cuda.is_available() else "cpu") model_name_or_path = "m3hrdadfi/hubert-base-persian-speech-emotion-recognition" config = AutoConfig.from_pretrained(model_name_or_path) feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name_or_path) sampling_rate = feature_extractor.sampling_rate model = HubertForSpeechClassification.from_pretrained(model_name_or_path).to(device) ``` ```python def speech_file_to_array_fn(path, sampling_rate): speech_array, _sampling_rate = torchaudio.load(path) resampler = torchaudio.transforms.Resample(_sampling_rate) speech = resampler(speech_array).squeeze().numpy() return speech def predict(path, sampling_rate): speech = speech_file_to_array_fn(path, sampling_rate) inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True) inputs = {key: inputs[key].to(device) for key in inputs} with torch.no_grad(): logits = model(**inputs).logits scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0] outputs = [{"Label": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)] return outputs ``` ```python path = "/path/to/sadness.wav" outputs = predict(path, sampling_rate) ``` ```bash [ {'Label': 'Anger', 'Score': '0.0%'}, {'Label': 'Fear', 'Score': '0.0%'}, {'Label': 'Happiness', 'Score': '0.0%'}, {'Label': 'Neutral', 'Score': '0.0%'}, {'Label': 'Sadness', 'Score': '99.9%'}, {'Label': 'Surprise', 'Score': '0.0%'} ] ``` ## Evaluation The following tables summarize the scores obtained by model overall and per each class. | Emotions | precision | recall | f1-score | accuracy | |:---------:|:---------:|:------:|:--------:|:--------:| | Anger | 0.96 | 0.96 | 0.96 | | | Fear | 1.00 | 0.50 | 0.67 | | | Happiness | 0.79 | 0.87 | 0.83 | | | Neutral | 0.93 | 0.94 | 0.93 | | | Sadness | 0.87 | 0.94 | 0.91 | | | Surprise | 0.97 | 0.75 | 0.85 | | | | | | Overal | 0.92 | ## Questions? Post a Github issue from [HERE](https://github.com/m3hrdadfi/soxan/issues).
heegyu/koalpaca-355m
heegyu
"2023-03-28T05:11:50Z"
1,355
4
transformers
[ "transformers", "pytorch", "gpt2", "text-generation", "ko", "dataset:Bingsu/ko_alpaca_data", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-03-28T01:28:44Z"
--- license: apache-2.0 widget: - text: <usr>알버트 아인슈타인에 대해서 알아? <sys> - text: <usr>다음을 동물, 식물, 광물로 분류하십시오. 참나무, 구리 광석, 코끼리 <sys> datasets: - Bingsu/ko_alpaca_data language: - ko --- - [Ajoublue-GPT2-medium](https://huggingface.co/heegyu/ajoublue-gpt2-medium) 모델을 [koalpaca](https://huggingface.co/datasets/Bingsu/ko_alpaca_data)데이터셋에 파인튜닝한 모델 - [Huggingface Space](https://huggingface.co/spaces/heegyu/koalpaca-355m)에서 사용해볼 수 있습니다. - 5 epoch 학습, learning rate = 5e-5 ``` from transformers import pipeline print('start model loading') model_name = '../checkpoint/koalpaca/ajoublue-gpt2-medium/epoch-4-last/' generator = pipeline( 'text-generation', model=model_name, tokenizer=model_name ) def query(instruction, input=None): if input: prompt = f"<usr>{instruction}\n{input}\n<sys>" else: prompt = f"<usr>{instruction}\n<sys>" print(generator( prompt, do_sample=True, top_p=0.9, early_stopping=True, max_length=256, )[0]['generated_text']) query("슈카월드에 대해서 알아?") query("세상에서 가장 유명한 사람은?") query("알버트 아인슈타인에 대해서 설명해줘") query("다음 영화에 대해서 설명해줘", "기생충") ``` 결과 ``` <usr>슈카월드에 대해서 알아? <sys>슈카월드는 미국 캘리포니아 주의 한 도시에서 열린 어린이 놀이박람회입니다. 이 박람회는 세계에서 가장 큰 어린이 놀이박람회로 유명합니다. <usr>세상에서 가장 유명한 사람은? <sys>가장 유명한 사람은 니콜라 테슬라입니다. <usr>알버트 아인슈타인에 대해서 설명해줘 <sys>알버트 아인슈타인은 1856년, 물리학 분야에서 최초로 노벨상을 수상한 물리학자입니다. 그는 상대성 이론을 비롯한 다수의 저서를 발표하며 현대 물리학의 기초를 확립하였습니다. <usr>다음 영화에 대해서 설명해줘 기생충 <sys>"기생충"은 가족과 학교에서 도망친 사람들 사이에서 벌어지는 일을 그린 영화로, 현실적이면서도 감각적인 연출과 다양한 캐릭터들의 매력을 살리는 방식으로 관객들을 사로잡습니다. <usr>섭씨 온도를 화씨로 변경해줘 섭씨 온도: 15도 <sys>"섭씨 온도를 화씨로 변경해주세요." -> "화씨 온도가 33도입니다." ```
cknowledge/mlperf-inference-bert-pytorch-fp32-squad-v1.1
cknowledge
"2023-08-18T10:41:29Z"
1,355
0
transformers
[ "transformers", "pytorch", "bert", "fill-mask", "MLPerf", "Question Answering", "BERT", "PyTorch", "Transformers", "FP32", "dataset:squad", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
fill-mask
"2023-08-18T10:23:41Z"
--- license: apache-2.0 tags: - MLPerf - Question Answering - BERT - PyTorch - Transformers - FP32 datasets: - squad --- This is an MLPerf BERT model taken from [Zenodo](https://zenodo.org/record/3733896), mixed with the [original model](https://huggingface.co/bert-large-uncased) and automated by the [MLCommons CM language](https://github.com/mlcommons/ck).
galatolo/cerbero-7b
galatolo
"2024-03-29T14:03:32Z"
1,355
14
transformers
[ "transformers", "pytorch", "mistral", "text-generation", "conversational", "it", "en", "dataset:andreabac3/Quora-Italian-Fauno-Baize", "dataset:andreabac3/StackOverflow-Italian-Fauno-Baize", "dataset:andreabac3/MedQuaAD-Italian-Fauno-Baize", "arxiv:2311.15698", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-10-26T14:30:02Z"
--- license: apache-2.0 datasets: - andreabac3/Quora-Italian-Fauno-Baize - andreabac3/StackOverflow-Italian-Fauno-Baize - andreabac3/MedQuaAD-Italian-Fauno-Baize language: - it - en pipeline_tag: text-generation --- # cerbero-7b Italian LLM 🚀 > 🚀 **New Release**: **cerbero-7b-openchat** our latest SOTA model based on [**openchat3.5**](https://github.com/imoneoi/openchat), delivering performance **on par with** or **superior** to **ChatGPT 3.5**! > 🔥 The research paper unveiling the secrets behind **cerbero-7b** is now available on [arXiv](https://arxiv.org/abs/2311.15698)! > 📢 **cerbero-7b** is the first **100% Free** and Open Source **Italian Large Language Model** (LLM) ready to be used for **research** or **commercial applications**. **Try an online demo [here](https://huggingface.co/spaces/galatolo/chat-with-cerbero-7b)** (quantized demo running on CPU, a lot less powerful than the original cerbero-7b) <p align="center"> <img width="300" height="300" src="./README.md.d/cerbero.png"> </p> Built on top of [**mistral-7b**](https://mistral.ai/news/announcing-mistral-7b/), which outperforms Llama2 13B across all benchmarks and surpasses Llama1 34B in numerous metrics. **cerbero-7b** is specifically crafted to fill the void in Italy's AI landscape. A **cambrian explosion** of **Italian Language Models** is essential for building advanced AI architectures that can cater to the diverse needs of the population. **cerbero-7b**, alongside companions like [**Camoscio**](https://github.com/teelinsan/camoscio) and [**Fauno**](https://github.com/RSTLess-research/Fauno-Italian-LLM), aims to help **kick-start** this **revolution** in Italy, ushering in an era where sophisticated **AI solutions** can seamlessly interact with and understand the intricacies of the **Italian language**, thereby empowering **innovation** across **industries** and fostering a deeper **connection** between **technology** and the **people** it serves. **cerbero-7b** is released under the **permissive** Apache 2.0 **license**, allowing **unrestricted usage**, even **for commercial applications**. ## Model Evaluation Results 📈 The `cerbero-7b` model has been rigorously evaluated across several benchmarks to demonstrate its proficiency in understanding and generating Italian text. Below are the summarized results showcasing its performance: ### SQuAD-it Evaluation The Stanford Question Answering Dataset (SQuAD) in Italian (SQuAD-it) is used to evaluate the model's reading comprehension and question-answering capabilities. The following table presents the F1 score and Exact Match (EM) metrics: | Model | F1 Score | Exact Match (EM) | |----------------------------------------------|--------------|----------------------| | **cerbero-7b-openchat** | **74.09%** | **56.0%** | | **cerbero-7b** | **72.55%** | **55.6%** | | Fauno | 44.46% | 0.00% | | Camoscio | 37.42% | 0.00% | | mistral-7b | 15.55% | 8.50% | ### EVALITA Benchmark Results EVALITA benchmarks assess the model's performance in tasks like toxicity detection, irony detection, and sentiment analysis. The table below shows the F1 scores for these tasks: | Model | Toxicity Detection | Irony Detection | Sentiment Analysis | |----------------------------------------------|--------------------|-----------------|--------------------| | **cerbero-7b-openchat** | **63.33%** | **69.16%** | **66.89%** | | **cerbero-7b** | **63.04%** | **48.51%** | **61.80%** | | Fauno | 33.84% | 39.17% | 12.23% | | Camoscio | 38.18% | 39.65% | 13.33% | | mistral-7b | 34.16% | 34.16% | 12.14% | ## Why Cerbero? 🤔 The name "Cerbero," inspired by the three-headed dog that guards the gates of the Underworld in Greek mythology, encapsulates the essence of our model, drawing strength from three foundational pillars: - **Base Model: mistral-7b** 🏗️ cerbero-7b builds upon the formidable **mistral-7b** as its base model. This choice ensures a robust foundation, leveraging the power and capabilities of a cutting-edge language model. - **Datasets: Cerbero Dataset** 📚 The Cerbero Dataset is a groundbreaking collection specifically curated to enhance the proficiency of cerbero-7b in understanding and generating Italian text. This dataset is a product of an innovative method combining dynamic self-chat mechanisms with advanced Large Language Model (LLM) technology. Refer to the [paper](https://arxiv.org/abs/2311.15698) for more details. - **Licensing: Apache 2.0** 🕊️ Released under the **permissive Apache 2.0 license**, cerbero-7b promotes openness and collaboration. This licensing choice empowers developers with the freedom for unrestricted usage, fostering a community-driven approach to advancing AI in Italy and beyond. ## Models 🧬 **cerbero-7b** is available in various flavors, each tailored for specific applications and use cases. Below is a table listing these versions along with their respective training datasets and base models: | Model Name | Training Dataset | Base Model | Huggingface Model | Llama.cpp and Quantized Model | |-------------------------|-------------------|-------------|-------------------|-------------------------------| | cerbero-7b | Cerbero Dataset | mistral-7b | [link](https://huggingface.co/galatolo/cerbero-7b) | [link](https://huggingface.co/galatolo/cerbero-7b-gguf) | | cerbero-7b-openchat | Cerbero Dataset | openchat3.5 | [link](https://huggingface.co/galatolo/cerbero-7b-openchat) | [link](https://huggingface.co/galatolo/cerbero-7b-openchat-gguf) | Each of these models brings its unique strengths to the table, making **cerbero-7b** a versatile tool for both research and commercial applications in the Italian language AI domain. We are committed to continuously enhancing **cerbero-7b**. Our team plans to keep training and releasing new models as advancements in the 7b SOTA occur. This ensures that **cerbero-7b** remains at the forefront of AI technology, offering the most advanced and efficient solutions in the Italian language AI sector. If you do not have enough RAM to fit the `float32` model (for example when using Colab) we provide for each model a `float16` version using the `revision="float16"` argument ```python model = AutoModelForCausalLM.from_pretrained("galatolo/cerbero-7b", revision="float16") ``` ## Training Details 🚀 **cerbero-7b** is a **fully fine-tuned** LLM, distinguishing itself from LORA or QLORA fine-tunes. The model is trained on an expansive Italian Large Language Model (LLM) using synthetic datasets generated through dynamic self-chat on a large context window of **8192 tokens** ### Dataset Composition 📊 > 📢 Details on the **Cerbero Dataset** will be updated shortly! ### Training Setup ⚙️ **cerbero-7b** is trained on an NVIDIA DGX H100: - **Hardware:** Utilizing 8xH100 GPUs, each with 80 GB VRAM. 🖥️ - **Parallelism:** DeepSpeed Zero stage 1 parallelism for optimal training efficiency.✨ The model has been trained for **1 epoch**, ensuring a convergence of knowledge and proficiency in handling diverse linguistic tasks. ## Prompt Format **cerbero-7b** is trained on full conversations using the following prompt format: ``` [|Umano|] First human message [|Assistente|] First AI reply [|Umano|] Second human message [|Assistente|] Second AI reply ``` When crafting prompts, ensure to conclude with the `[|Assistente|]` tag, signaling the AI to generate a response. Use `[|Umano|]` as stop word. For example: ``` [|Umano|] Come posso distinguere un AI da un umano? [|Assistente|] ``` While it's possible to include a brief system message at the start of your prompt, remember that the training data for **cerbero-7b** **does not** contain such **system messages**. Hence, it's recommended to minimize or avoid including them for optimal model performance. ## Getting Started 🚀 You can load **cerbero-7b** (or **cerbero-7b-openchat**) using [🤗transformers](https://huggingface.co/docs/transformers/index) ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("galatolo/cerbero-7b") tokenizer = AutoTokenizer.from_pretrained("galatolo/cerbero-7b") prompt = """Questa è una conversazione tra un umano ed un assistente AI. [|Umano|] Come posso distinguere un AI da un umano? [|Assistente|]""" input_ids = tokenizer(prompt, return_tensors='pt').input_ids with torch.no_grad(): output_ids = model.generate(input_ids, max_new_tokens=128) generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True) print(generated_text) ``` ### GGUF and llama.cpp **cerbero-7b** is fully **compatibile** with [llama.cpp](https://github.com/ggerganov/llama.cpp) You can find the **original** and **quantized** versions of **cerbero-7b** in the `gguf` format [here](https://huggingface.co/galatolo/cerbero-7b-gguf/tree/main) ```python from llama_cpp import Llama from huggingface_hub import hf_hub_download llm = Llama( model_path=hf_hub_download( repo_id="galatolo/cerbero-7b-gguf", filename="ggml-model-f16.gguf", ), n_ctx=4086, ) llm.generate("""Questa è una conversazione tra un umano ed un assistente AI. [|Umano|] Come posso distinguere un AI da un umano? [|Assistente|]""") ``` ## Citation 📖 If you use **cerbero-7b** in your research, please cite our paper: ```bibtex @article{galatolo2023cerbero, title={Cerbero-7B: A Leap Forward in Language-Specific LLMs Through Enhanced Chat Corpus Generation and Evaluation}, author={Galatolo, Federico A and Cimino, Mario GCA}, journal={arXiv preprint arXiv:2311.15698}, year={2023} } ``` ## Training Details 🚀 **cerbero-7b** is a **fully fine-tuned** LLM, distinguishing itself from LORA or QLORA fine-tunes. The model is trained on an expansive Italian Large Language Model (LLM) using synthetic datasets generated through dynamic self-chat on a large context window of **8192 tokens** ### Dataset Composition 📊 > 📢 Details on the **Cerbero Dataset** will be updated shortly! ### Training Setup ⚙️ **cerbero-7b** is trained on an NVIDIA DGX H100: - **Hardware:** Utilizing 8xH100 GPUs, each with 80 GB VRAM. 🖥️ - **Parallelism:** DeepSpeed Zero stage 1 parallelism for optimal training efficiency.✨ The model has been trained for **1 epoch**, ensuring a convergence of knowledge and proficiency in handling diverse linguistic tasks. ## Getting Started 🚀 You can load **cerbero-7b** using [🤗transformers](https://huggingface.co/docs/transformers/index) ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("galatolo/cerbero-7b") tokenizer = AutoTokenizer.from_pretrained("galatolo/cerbero-7b") prompt = """Questa è una conversazione tra un umano ed un assistente AI. [|Umano|] Come posso distinguere un AI da un umano? [|Assistente|]""" input_ids = tokenizer(prompt, return_tensors='pt').input_ids with torch.no_grad(): output_ids = model.generate(input_ids, max_new_tokens=128) generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True) print(generated_text) ``` ### GGUF and llama.cpp **cerbero-7b** is fully **compatibile** with [llama.cpp](https://github.com/ggerganov/llama.cpp) You can find the **original** and **quantized** versions of **cerbero-7b** in the `gguf` format [here](https://huggingface.co/galatolo/cerbero-7b-gguf/tree/main) ```python from llama_cpp import Llama from huggingface_hub import hf_hub_download llm = Llama( model_path=hf_hub_download( repo_id="galatolo/cerbero-7b-gguf", filename="ggml-model-Q4_K.gguf", ), n_ctx=4086, ) llm.generate("""Questa è una conversazione tra un umano ed un assistente AI. [|Umano|] Come posso distinguere un AI da un umano? [|Assistente|]""") ``` ## Differences from the paper > 📢 Attention: The released versions of `cerbero-7b` slightly differ from those used in the paper. The training dataset for the released models was generated using `garage-bAInd/Platypus2-70B-instruct` instead of `meta-llama/Llama-2-7b-chat-hf`, due to the more permissive license of the Platypus2 model (CC-BY-NC 4.0). Our tests indicate that both models produce datasets of comparable quality, and the resulting fine-tuned models demonstrate nearly indistinguishable performance.
prithivida/Asimov-7B-v1
prithivida
"2023-11-18T03:10:25Z"
1,355
1
transformers
[ "transformers", "mistral", "text-generation", "conversational", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-11-05T09:41:46Z"
--- license: mit --- <center><img src="https://compote.slate.com/images/0878b9e8-b6b6-4913-8345-43f9c5b67327.jpg"/></center> # Model Card for Asimov-7B-v1 Asimov will be a series of language models that are trained to act as useful writing assistants, named after a biochemist one of the profilic writers of our time Isaac Asimov. Asimov-7B-v1 is the 1st pilot model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was fine-tuned on a filtered, cleaned, variant of Ultrachat. This model has was not aligned with any datasets so consider this as a model with no guard rails. ## Model Details - Model type: A 7B parameter GPT-like model fine-tuned on publicly available synthetic datasets. - Language(s) (NLP): Primarily English - License: MIT - Finetuned from model: mistralai/Mistral-7B-v0.1 ### Model Description - **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] ## Bias, Risks, and Limitations Asimov-7B-v1 has not been aligned to human preferences, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base model (mistralai/Mistral-7B-v0.1), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this. ## How to Get Started with the Model Use the code below to get started with the model. ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer,GenerationConfig from peft import PeftModel, PeftConfig model_name = "prithivida/Asimov-7B-v1" peft_config = PeftConfig.from_pretrained(model_name) base_model = AutoModelForCausalLM.from_pretrained( peft_config.base_model_name_or_path, return_dict=True, device_map="auto", torch_dtype=torch.float16, low_cpu_mem_usage=True, ) model = PeftModel.from_pretrained( base_model, model_name, torch_dtype=torch.float16, device_map="auto", ) tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True) model.config.pad_token_id = tokenizer.unk_token_id def run_inference(messages): chat = [] for i, message in enumerate(messages): if i % 2 ==0: chat.append({"role": "Human", "content": f"{message}"}) else: chat.append({"role": "Assistant", "content": f"{message}"}) prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) inputs = tokenizer(prompt, return_tensors="pt") input_ids = inputs["input_ids"].cuda() generation_output = model.generate( input_ids=input_ids, generation_config=GenerationConfig(pad_token_id=tokenizer.pad_token_id, do_sample=True, temperature=1.0, top_k=50, top_p=0.95), return_dict_in_generate=True, output_scores=True, max_new_tokens=128 ) for seq in generation_output.sequences: output = tokenizer.decode(seq) print(output.split("### Assistant: ")[1].strip()) run_inference(["What's the longest side of the right angled triangle called and how is it related to the Pythagoras theorem?"]) ```
uukuguy/speechless-tools-7b
uukuguy
"2023-11-21T09:58:52Z"
1,355
1
transformers
[ "transformers", "pytorch", "llama", "text-generation", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-11-21T09:13:15Z"
--- license: llama2 --- The speechless-tools-7b model is fine-tuned on [speechless-coding-7b-16k-tora](https://huggingface.co/uukuguy/speechless-coding-7b-16k-tora), following the guidance of the [ToolLlama](https://github.com/OpenBMB/ToolBench) project, aims to empower open-source LLMs with the ability to handle thousands of diverse real-world APIs. ## Local Test speechless-tools-7b-dfs vs chatgpt-cot | Dataset | Win Rate | | ------ | ------ | | G1_instruction | 0.465 | | G1_category | 0.495 | | G1_tool | 0.505 | | G2_instruction | 0.61 | | G2_category | 0.585 | | G3_instruction | 0.66 | speechless-tools-7b-dfs vs toolllama-dfs | Dataset | Win Rate | | ------ | ------ | | G1_instruction | 0.45 | | G1_category | 0.45 | | G1_tool | 0.51 | | G2_instruction | 0.53 | | G2_category | 0.575 | | G3_instruction | 0.46 |
luffycodes/llama-class-shishya-7b-ep3
luffycodes
"2023-12-14T12:26:31Z"
1,355
0
transformers
[ "transformers", "pytorch", "llama", "text-generation", "conversational", "arxiv:2305.13272", "license:llama2", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-14T11:47:13Z"
--- license: llama2 --- If you use this work, please cite: CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles https://arxiv.org/abs/2305.13272 ``` @misc{sonkar2023class, title={CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles}, author={Shashank Sonkar and Lucy Liu and Debshila Basu Mallick and Richard G. Baraniuk}, year={2023}, eprint={2305.13272}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```
crumb/apricot-wildflower-20
crumb
"2024-03-06T21:45:39Z"
1,355
2
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-19T20:09:54Z"
--- license: apache-2.0 model-index: - name: apricot-wildflower-20 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: 59.64 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=crumb/apricot-wildflower-20 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: 81.76 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=crumb/apricot-wildflower-20 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: 63.38 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=crumb/apricot-wildflower-20 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: 41.76 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=crumb/apricot-wildflower-20 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: 77.9 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=crumb/apricot-wildflower-20 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: 33.97 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=crumb/apricot-wildflower-20 name: Open LLM Leaderboard --- # apricot-wildflower-20 This model is the Mistral-7b model finetuned for 1k steps with a combined lm loss and distillation loss on Openwebtext2 with a >=20 reddit score filter with training logits from Mixtral. I'm not going to pretend it was a big project I did it in a dream and woke up and replicated the code without any actual reason, idk how well it fares in benchmarks. (update: not very good) | model | avg | arc | hellaswag | mmlu | truthfulqa | winogrande | gsm8k | | --- | --- | --- | --- | --- | --- | --- | --- | | apricot-wildflower-20 | 59.74 | 59.64 | 81.76 | 63.38 | 41.76 | 77.9 | 33.97 | | mistralai/Mistral-7B-v0.1 | 60.97 | 59.98 | 83.31 | 64.16 | 42.15 | 78.37 | 37.83 | ### use ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "crumb/apricot-wildflower-20" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id, low_cpu_mem_usage=True, device_map="auto", load_in_8bit=True) text = "Hello my name is" inputs = tokenizer(text, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=128) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) # Hello my name is Katie and I am a 20 year old student from the UK. I am currently studying for a degree in English Literature and Creative Writing at the University of Leeds. I am a huge fan of the Harry Potter series and have been since I was 10 years old. I have read the books countless times and have seen the films many times too. I am a huge fan of the Harry Potter fandom and have been a member of the Harry Potter forums for a few years now. I am also a member of the Harry Potter fan club and have been for a few years now. I ``` # [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_crumb__apricot-wildflower-20) | Metric |Value| |---------------------------------|----:| |Avg. |59.74| |AI2 Reasoning Challenge (25-Shot)|59.64| |HellaSwag (10-Shot) |81.76| |MMLU (5-Shot) |63.38| |TruthfulQA (0-shot) |41.76| |Winogrande (5-shot) |77.90| |GSM8k (5-shot) |33.97|
vikash06/mistral_v1
vikash06
"2024-03-04T15:36:14Z"
1,355
5
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "license:mit", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-23T07:08:08Z"
--- license: mit model-index: - name: mistral_v1 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: 47.01 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/mistral_v1 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: 67.58 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/mistral_v1 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: 48.68 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/mistral_v1 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: 37.53 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/mistral_v1 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: 64.8 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/mistral_v1 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: 9.48 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vikash06/mistral_v1 name: Open LLM Leaderboard --- This model is trained on experimental basis on a small dataset to assess whether training longer on a smaller dataset has a good performance or not. # Model Details vikash06/llama-2-7b-small-model--> Finetuned model on llama2 # Uses # Creative Writing: Write a question or instruction that requires a creative, open-ended written response. The instruction should be reasonable to ask of a person with general world knowledge and should not require searching. In this task, your prompt should give very specific instructions to follow. Constraints, instructions, guidelines, or requirements all work, and the more of them the better. # Closed QA: Write a question or instruction that requires factually correct response based on a passage of text from Wikipedia. The question can be complex and can involve human-level reasoning capabilities, but should not require special knowledge. To create a question for this task include both the text of the question as well as the reference text in the form. # Open QA: Write a question that can be answered using general world knowledge or at most a single search. This task asks for opinions and facts about the world at large and does not provide any reference text for consultation. # Summarization: Give a summary of a paragraph from Wikipedia. Please don't ask questions that will require more than 3-5 minutes to answer. To create a question for this task include both the text of the question as well as the reference text in the form. # Information Extraction: These questions involve reading a paragraph from Wikipedia and extracting information from the passage. Everything required to produce an answer (e.g. a list, keywords etc) should be included in the passages. To create a question for this task include both the text of the question as well as the reference text in the form. # Classification: These prompts contain lists or examples of entities to be classified, e.g. movie reviews, products, etc. In this task the text or list of entities under consideration is contained in the prompt (e.g. there is no reference text.). You can choose any categories for classification you like, the more diverse the better. # Brainstorming: Think up lots of examples in response to a question asking to brainstorm ideas # Direct Use The model is intnded for direct use # How to Get Started with the Model import torch import pandas as pd from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("vikash06/llama-2-7b-small-model") model = AutoModelForCausalLM.from_pretrained("vikash06/llama-2-7b-small-model", torch_dtype=torch.float16, device_map="cuda:0") print (model) def generate_training_prompt(instruction,context): return f""" Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {instruction} ### Context: {context.strip()} """.strip() data1 ={"instruction": "When was the first Reading railway station opened?", "context": "Reading railway station is a major transport hub in Reading, Berkshire, England. It is on the northern edge of the town centre, near the main retail and commercial areas and the River Thames, 36 miles (58 km) from London Paddington. The first Reading station was opened on 30 March 1840 as the temporary western terminus of the original line of the Great Western Railway (GWR). Reading is the ninth-busiest station in the UK outside London and the second busiest interchange station outside London with over 3.8 million passengers changing trains at the station annually.", "response": "The first Reading railway station was opened on the 30th of March, 1840.", "category": "closed_qa"} prompt = generate_training_prompt(data1["instruction"],data1["context"]) input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda(0) outputs = model.generate(input_ids=input_ids, max_new_tokens=128, do_sample=True, top_p=0.9,temperature=0.3) resp = tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):].split("\n") resp = [x for x in resp if x!=''] print(resp) # Training Data 1000 samples were carefully selected from each of the category. # Training Procedure We used the below libraries to finetune the llama2-7b: torch==2.1.0 transformers==4.35.2 peft@git+https://github.com/huggingface/peft.git bitsandbytes==0.41.1 trl @ git+https://github.com/lvwerra/trl.git@34e6948d459540a21f80c5be227fb4da039dd97a We used batch size 0f 2 on 50 epochs # Evaluation We performed hellaswag task using evaluation library of EleutherAI: https://github.com/EleutherAI/lm-evaluation-harness below are the results: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63a7d07154f1d0225b0b9d1c/fAgFzMAVp9Nazjz0OP5Dh.png) # Environmental Impact Carbon Emitted: 0.432 kg/kWh Offset: 0% hardware: a6000 48GB(3) hours: 28 # Technical Report Detail writeup coming soon # [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_vikash06__mistral_v1) | Metric |Value| |---------------------------------|----:| |Avg. |45.85| |AI2 Reasoning Challenge (25-Shot)|47.01| |HellaSwag (10-Shot) |67.58| |MMLU (5-Shot) |48.68| |TruthfulQA (0-shot) |37.53| |Winogrande (5-shot) |64.80| |GSM8k (5-shot) | 9.48|
saberai/Zro1.5_3B
saberai
"2023-12-29T17:05:45Z"
1,355
1
transformers
[ "transformers", "safetensors", "gpt_neox", "text-generation", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-25T12:06:44Z"
--- license: apache-2.0 --- Introducing Zro1.5_3B by Saber AI – Precision and Performance in a Compact Package, fine-tuned for enhanced reasoning and mathematical skills on low-powered mobile devices. Key Features: Efficient Precision: Zro1.5_3B excels in capturing nuances despite its compact size, making it a powerful Small Language Model (SLM). Resource Optimization: Maximized efficiency without sacrificing performance, ensuring seamless integration into diverse platforms. Adaptability: Customize parameters to tailor the model to your project's specific needs, offering flexibility and versatility. Scalability: Designed to scale effortlessly, from small projects to large-scale applications. Cutting-Edge Technology: Leverage the latest in natural language processing for state-of-the-art performance. Reasoning Enhancement: Fine-tuned in RedPajama-INCITE-Chat-3B-v1 to improve reasoning skills and mathematical reasoning. Mobile Optimization: Tailored for low-powered mobile devices, ensuring optimal performance on the go. User-Friendly Integration: Effortless incorporation with comprehensive documentation and support. Elevate your projects with Zro1.5_3B – where small size meets unparalleled performance, specifically enhancing reasoning and mathematical skills on low-powered mobile devices.
NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3-GGUF
NeverSleep
"2023-12-25T22:08:32Z"
1,355
29
null
[ "gguf", "license:cc-by-nc-4.0", "region:us" ]
null
"2023-12-25T18:31:09Z"
--- license: cc-by-nc-4.0 --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/vwcJfOnL-2QDJ0ShfxRJ5.png) --- # Disclaimer: ## This model is experimental, do not expect everything to work. This model uses the Alpaca **prompting format**(or just directly download the SillyTavern instruct preset [here](https://files.catbox.moe/0ohmco.json)) --- Beeg noromaid on ***steroids***. Suitable for RP, ERP. This time based on Mixtral Instruct, seems to do wonders! This model was trained for 8h(v1) + 8h(v2) + 12h(v3) on customized modified datasets, focusing on RP, uncensoring, and a modified version of the Alpaca prompting (that was already used in LimaRP), which should be at the same conversational level as ChatLM or Llama2-Chat without adding any additional special tokens. If you wanna have more infos about this model(and v1 + v2) you can check out [my blog post](https://ikaridevgit.github.io/index.html?p=7&blog=blogid-6&bo=true) [Recommended settings - Settings 1](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-v3/discussions/1) [Recommended settings - Settings 2 (idk if they are any good)](https://files.catbox.moe/fv4xhu.json) ## Credits: - Undi - IkariDev <!-- description start --> ## Description <!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) --> This repo contains GGUF files of Noromaid-v0.1-mixtral-8x7b-Instruct-v3. [FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3) <!-- [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/Noromaid-v0.1-mixtral-8x7b-Instruct-v3-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, we DONT screenshot random reviews without asking if we 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 --> <!-- prompt-template start --> ### Custom format: ``` ### Instruction: {system prompt} ### Input: {input} ### Response: {reply} ``` ## Datasets used: - Aesir 1 and 2 ([MinervaAI](https://huggingface.co/MinervaAI) / [Gryphe](https://huggingface.co/Gryphe)) - [LimaRP-20231109](https://huggingface.co/datasets/lemonilia/LimaRP) ([Lemonilia](https://huggingface.co/lemonilia)) - [ToxicDPO-NoWarning](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt) ([unalignment orga repo](https://huggingface.co/unalignment) + [Undi](https://huggingface.co/Undi95)) - [No-robots-ShareGPT](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt) ([Doctor-Shotgun](https://huggingface.co/Doctor-Shotgu)) ## 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
jan-hq/stealth-v1.2
jan-hq
"2024-03-04T13:36:13Z"
1,355
4
transformers
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "en", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2023-12-28T15:54:05Z"
--- language: - en license: apache-2.0 model-index: - name: stealth-v1.2 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: 66.38 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v1.2 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: 86.14 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v1.2 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: 64.33 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v1.2 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: 54.23 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v1.2 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: 80.74 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v1.2 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: 72.25 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jan-hq/stealth-v1.2 name: Open LLM Leaderboard --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://github.com/janhq/jan/assets/89722390/35daac7d-b895-487c-a6ac-6663daaad78e" alt="Jan banner" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <p align="center"> <a href="https://jan.ai/">Jan</a > - <a href="https://discord.gg/AsJ8krTT3N">Discord</a> </p> <!-- header end --> # Prompt template ChatML ``` <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ``` # Run this model You can run this model using [Jan Desktop](https://jan.ai/) on Mac, Windows, or Linux. Jan is an open source, ChatGPT alternative that is: - 💻 **100% offline on your machine**: Your conversations remain confidential, and visible only to you. - 🗂️ **An Open File Format**: Conversations and model settings stay on your computer and can be exported or deleted at any time. - 🌐 **OpenAI Compatible**: Local server on port `1337` with OpenAI compatible endpoints - 🌍 **Open Source & Free**: We build in public; check out our [Github](https://github.com/janhq) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/r7VmEBLGXpPLTu2MImM7S.png) # About Jan Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones. Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life. # [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_jan-hq__stealth-v1.2) | Metric |Value| |---------------------------------|----:| |Avg. |70.68| |AI2 Reasoning Challenge (25-Shot)|66.38| |HellaSwag (10-Shot) |86.14| |MMLU (5-Shot) |64.33| |TruthfulQA (0-shot) |54.23| |Winogrande (5-shot) |80.74| |GSM8k (5-shot) |72.25|
mavihsrr/GetCode-slerp
mavihsrr
"2024-01-15T22:56:38Z"
1,355
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "codellama/CodeLlama-7b-Instruct-hf", "Salesforce/codegen25-7b-multi", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-15T22:52:59Z"
--- license: apache-2.0 tags: - merge - mergekit - lazymergekit - codellama/CodeLlama-7b-Instruct-hf - Salesforce/codegen25-7b-multi --- # GetCode-slerp GetCode-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) * [Salesforce/codegen25-7b-multi](https://huggingface.co/Salesforce/codegen25-7b-multi) ## 🧩 Configuration ```yaml slices: - sources: - model: codellama/CodeLlama-7b-Instruct-hf layer_range: [0, 32] - model: Salesforce/codegen25-7b-multi layer_range: [0, 32] merge_method: slerp base_model: codellama/CodeLlama-7b-Instruct-hf parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "mavihsrr/GetCode-slerp" 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"]) ```
KnutJaegersberg/Qwen-1_8B-Chat-llama
KnutJaegersberg
"2024-03-04T16:28:40Z"
1,355
1
transformers
[ "transformers", "safetensors", "llama", "text-generation", "license:other", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
text-generation
"2024-01-19T07:19:09Z"
--- license: other license_name: qwen license_link: LICENSE model-index: - name: Qwen-1_8B-Chat-llama 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: 36.95 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Qwen-1_8B-Chat-llama 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: 54.34 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Qwen-1_8B-Chat-llama 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: 44.55 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Qwen-1_8B-Chat-llama 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: 43.7 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Qwen-1_8B-Chat-llama 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: 58.88 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Qwen-1_8B-Chat-llama 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: 19.26 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Qwen-1_8B-Chat-llama name: Open LLM Leaderboard --- Their non-commercial research license applies. I used this script to make the model and used the tokenizer of CausalLM, as suggested in the comments of the script. https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py # [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_KnutJaegersberg__Qwen-1_8B-Chat-llama) | Metric |Value| |---------------------------------|----:| |Avg. |42.94| |AI2 Reasoning Challenge (25-Shot)|36.95| |HellaSwag (10-Shot) |54.34| |MMLU (5-Shot) |44.55| |TruthfulQA (0-shot) |43.70| |Winogrande (5-shot) |58.88| |GSM8k (5-shot) |19.26|
Chrisisis/5DSRbrx2swiBiVoSQAVzkvHKx8jaEFHbmCQCvGGZWtgkdRo4_vgg
Chrisisis
"2024-02-24T08:29:32Z"
1,355
0
keras
[ "keras", "region:us" ]
null
"2024-02-11T17:21:31Z"
Entry not found
ChrisWilson011016/5GNVGhSBtNbGoDDV7KkU4xde4vAiw9bB2db3ALe8qwiQPm3Z_vgg
ChrisWilson011016
"2024-03-04T18:50:57Z"
1,355
0
keras
[ "keras", "region:us" ]
null
"2024-02-24T15:10:33Z"
Entry not found
votepurchase/animagine-xl-3.1
votepurchase
"2024-05-23T03:44:17Z"
1,355
1
diffusers
[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "stable-diffusion-xl", "en", "base_model:cagliostrolab/animagine-xl-3.0", "license:other", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]
text-to-image
"2024-05-23T03:44:16Z"
--- license: other license_name: faipl-1.0-sd license_link: https://freedevproject.org/faipl-1.0-sd/ language: - en tags: - text-to-image - stable-diffusion - safetensors - stable-diffusion-xl base_model: cagliostrolab/animagine-xl-3.0 widget: - text: 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck, masterpiece, best quality, very aesthetic, absurdes parameter: negative_prompt: nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract] example_title: 1girl - text: 1boy, male focus, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneck, masterpiece, best quality, very aesthetic, absurdes parameter: negative_prompt: nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract] example_title: 1boy --- <style> .title-container { display: flex; justify-content: center; align-items: center; height: 100vh; /* Adjust this value to position the title vertically */ } .title { font-size: 2.5em; text-align: center; color: #333; font-family: 'Helvetica Neue', sans-serif; text-transform: uppercase; letter-spacing: 0.1em; padding: 0.5em 0; background: transparent; } .title span { background: -webkit-linear-gradient(45deg, #7ed56f, #28b485); -webkit-background-clip: text; -webkit-text-fill-color: transparent; } .custom-table { table-layout: fixed; width: 100%; border-collapse: collapse; margin-top: 2em; } .custom-table td { width: 50%; vertical-align: top; padding: 10px; box-shadow: 0px 0px 0px 0px rgba(0, 0, 0, 0.15); } .custom-image-container { position: relative; width: 100%; margin-bottom: 0em; overflow: hidden; border-radius: 10px; transition: transform .7s; /* Smooth transition for the container */ } .custom-image-container:hover { transform: scale(1.05); /* Scale the container on hover */ } .custom-image { width: 100%; height: auto; object-fit: cover; border-radius: 10px; transition: transform .7s; margin-bottom: 0em; } .nsfw-filter { filter: blur(8px); /* Apply a blur effect */ transition: filter 0.3s ease; /* Smooth transition for the blur effect */ } .custom-image-container:hover .nsfw-filter { filter: none; /* Remove the blur effect on hover */ } .overlay { position: absolute; bottom: 0; left: 0; right: 0; color: white; width: 100%; height: 40%; display: flex; flex-direction: column; justify-content: center; align-items: center; font-size: 1vw; font-style: bold; text-align: center; opacity: 0; /* Keep the text fully opaque */ background: linear-gradient(0deg, rgba(0, 0, 0, 0.8) 60%, rgba(0, 0, 0, 0) 100%); transition: opacity .5s; } .custom-image-container:hover .overlay { opacity: 1; } .overlay-text { background: linear-gradient(45deg, #7ed56f, #28b485); -webkit-background-clip: text; color: transparent; text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.7); .overlay-subtext { font-size: 0.75em; margin-top: 0.5em; font-style: italic; } .overlay, .overlay-subtext { text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.5); } </style> <h1 class="title"> <span>Animagine XL 3.1</span> </h1> <table class="custom-table"> <tr> <td> <div class="custom-image-container"> <img class="custom-image" src="https://cdn-uploads.huggingface.co/production/uploads/6365c8dbf31ef76df4042821/yq_5AWegnLsGyCYyqJ-1G.png" alt="sample1"> </div> <div class="custom-image-container"> <img class="custom-image" src="https://cdn-uploads.huggingface.co/production/uploads/6365c8dbf31ef76df4042821/sp6w1elvXVTbckkU74v3o.png" alt="sample4"> </div> </td> <td> <div class="custom-image-container"> <img class="custom-image" src="https://cdn-uploads.huggingface.co/production/uploads/6365c8dbf31ef76df4042821/OYBuX1XzffN7Pxi4c75JV.png" alt="sample2"> </div> <div class="custom-image-container"> <img class="custom-image" src="https://cdn-uploads.huggingface.co/production/uploads/6365c8dbf31ef76df4042821/ytT3Oaf-atbqrnPIqz_dq.png" alt="sample3"> </td> <td> <div class="custom-image-container"> <img class="custom-image" src="https://cdn-uploads.huggingface.co/production/uploads/6365c8dbf31ef76df4042821/0oRq204okFxRGECmrIK6d.png" alt="sample1"> </div> <div class="custom-image-container"> <img class="custom-image" src="https://cdn-uploads.huggingface.co/production/uploads/6365c8dbf31ef76df4042821/DW51m0HlDuAlXwu8H8bIS.png" alt="sample4"> </div> </td> </tr> </table> **Animagine XL 3.1** is an update in the Animagine XL V3 series, enhancing the previous version, Animagine XL 3.0. This open-source, anime-themed text-to-image model has been improved for generating anime-style images with higher quality. It includes a broader range of characters from well-known anime series, an optimized dataset, and new aesthetic tags for better image creation. Built on Stable Diffusion XL, Animagine XL 3.1 aims to be a valuable resource for anime fans, artists, and content creators by producing accurate and detailed representations of anime characters. ## Model Details - **Developed by**: [Cagliostro Research Lab](https://huggingface.co/cagliostrolab) - **In collaboration with**: [SeaArt.ai](https://www.seaart.ai/) - **Model type**: Diffusion-based text-to-image generative model - **Model Description**: Animagine XL 3.1 generates high-quality anime images from textual prompts. It boasts enhanced hand anatomy, improved concept understanding, and advanced prompt interpretation. - **License**: [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/) - **Fine-tuned from**: [Animagine XL 3.0](https://huggingface.co/cagliostrolab/animagine-xl-3.0) ## Gradio & Colab Integration Try the demo powered by Gradio in Huggingface Spaces: [![Open In Spaces](https://img.shields.io/badge/🤗-Open%20In%20Spaces-blue.svg)](https://huggingface.co/spaces/cagliostrolab/animagine-xl-3.1) Or open the demo in Google Colab: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https%3A//huggingface.co/spaces/cagliostrolab/animagine-xl-3.1/blob/main/demo.ipynb) ## 🧨 Diffusers Installation First install the required libraries: ```bash pip install diffusers transformers accelerate safetensors --upgrade ``` Then run image generation with the following example code: ```python import torch from diffusers import DiffusionPipeline pipe = DiffusionPipeline.from_pretrained( "cagliostrolab/animagine-xl-3.1", torch_dtype=torch.float16, use_safetensors=True, ) pipe.to('cuda') prompt = "1girl, souryuu asuka langley, neon genesis evangelion, solo, upper body, v, smile, looking at viewer, outdoors, night" negative_prompt = "nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]" image = pipe( prompt, negative_prompt=negative_prompt, width=832, height=1216, guidance_scale=7, num_inference_steps=28 ).images[0] image.save("./output/asuka_test.png") ``` ## Usage Guidelines ### Tag Ordering For optimal results, it's recommended to follow the structured prompt template because we train the model like this: ``` 1girl/1boy, character name, from what series, everything else in any order. ``` ## Special Tags Animagine XL 3.1 utilizes special tags to steer the result toward quality, rating, creation date and aesthetic. While the model can generate images without these tags, using them can help achieve better results. ### Quality Modifiers Quality tags now consider both scores and post ratings to ensure a balanced quality distribution. We've refined labels for greater clarity, such as changing 'high quality' to 'great quality'. | Quality Modifier | Score Criterion | |------------------|-------------------| | `masterpiece` | > 95% | | `best quality` | > 85% & ≤ 95% | | `great quality` | > 75% & ≤ 85% | | `good quality` | > 50% & ≤ 75% | | `normal quality` | > 25% & ≤ 50% | | `low quality` | > 10% & ≤ 25% | | `worst quality` | ≤ 10% | ### Rating Modifiers We've also streamlined our rating tags for simplicity and clarity, aiming to establish global rules that can be applied across different models. For example, the tag 'rating: general' is now simply 'general', and 'rating: sensitive' has been condensed to 'sensitive'. | Rating Modifier | Rating Criterion | |-------------------|------------------| | `safe` | General | | `sensitive` | Sensitive | | `nsfw` | Questionable | | `explicit, nsfw` | Explicit | ### Year Modifier We've also redefined the year range to steer results towards specific modern or vintage anime art styles more accurately. This update simplifies the range, focusing on relevance to current and past eras. | Year Tag | Year Range | |----------|------------------| | `newest` | 2021 to 2024 | | `recent` | 2018 to 2020 | | `mid` | 2015 to 2017 | | `early` | 2011 to 2014 | | `oldest` | 2005 to 2010 | ### Aesthetic Tags We've enhanced our tagging system with aesthetic tags to refine content categorization based on visual appeal. These tags are derived from evaluations made by a specialized ViT (Vision Transformer) image classification model, specifically trained on anime data. For this purpose, we utilized the model [shadowlilac/aesthetic-shadow-v2](https://huggingface.co/shadowlilac/aesthetic-shadow-v2), which assesses the aesthetic value of content before it undergoes training. This ensures that each piece of content is not only relevant and accurate but also visually appealing. | Aesthetic Tag | Score Range | |-------------------|-------------------| | `very aesthetic` | > 0.71 | | `aesthetic` | > 0.45 & < 0.71 | | `displeasing` | > 0.27 & < 0.45 | | `very displeasing`| ≤ 0.27 | ## Recommended settings To guide the model towards generating high-aesthetic images, use negative prompts like: ``` nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract] ``` For higher quality outcomes, prepend prompts with: ``` masterpiece, best quality, very aesthetic, absurdres ``` it’s recommended to use a lower classifier-free guidance (CFG Scale) of around 5-7, sampling steps below 30, and to use Euler Ancestral (Euler a) as a sampler. ### Multi Aspect Resolution This model supports generating images at the following dimensions: | Dimensions | Aspect Ratio | |-------------------|-----------------| | `1024 x 1024` | 1:1 Square | | `1152 x 896` | 9:7 | | `896 x 1152` | 7:9 | | `1216 x 832` | 19:13 | | `832 x 1216` | 13:19 | | `1344 x 768` | 7:4 Horizontal | | `768 x 1344` | 4:7 Vertical | | `1536 x 640` | 12:5 Horizontal | | `640 x 1536` | 5:12 Vertical | ## Training and Hyperparameters **Animagine XL 3.1** was trained on 2x A100 80GB GPUs for approximately 15 days, totaling over 350 GPU hours. The training process consisted of three stages: - **Pretraining**: Utilized a data-rich collection of 870k ordered and tagged images to increase Animagine XL 3.0's model knowledge. - **Finetuning - First Stage**: Employed labeled and curated aesthetic datasets to refine the broken U-Net after pretraining. - **Finetuning - Second Stage**: Utilized labeled and curated aesthetic datasets to refine the model's art style and improve hand and anatomy rendering. ### Hyperparameters | Stage | Epochs | UNet lr | Train Text Encoder | Batch Size | Noise Offset | Optimizer | LR Scheduler | Grad Acc Steps | GPUs | |--------------------------|--------|---------|--------------------|------------|--------------|------------|-------------------------------|----------------|------| | **Pretraining** | 10 | 1e-5 | True | 16 | N/A | AdamW | Cosine Annealing Warm Restart | 3 | 2 | | **Finetuning 1st Stage** | 10 | 2e-6 | False | 48 | 0.0357 | Adafactor | Constant with Warmup | 1 | 1 | | **Finetuning 2nd Stage** | 15 | 1e-6 | False | 48 | 0.0357 | Adafactor | Constant with Warmup | 1 | 1 | ## Model Comparison (Pretraining only) ### Training Config | Configuration Item | Animagine XL 3.0 | Animagine XL 3.1 | |---------------------------------|------------------------------------------|------------------------------------------------| | **GPU** | 2 x A100 80G | 2 x A100 80G | | **Dataset** | 1,271,990 | 873,504 | | **Shuffle Separator** | True | True | | **Num Epochs** | 10 | 10 | | **Learning Rate** | 7.5e-6 | 1e-5 | | **Text Encoder Learning Rate** | 3.75e-6 | 1e-5 | | **Effective Batch Size** | 48 x 1 x 2 | 16 x 3 x 2 | | **Optimizer** | Adafactor | AdamW | | **Optimizer Args** | Scale Parameter: False, Relative Step: False, Warmup Init: False | Weight Decay: 0.1, Betas: (0.9, 0.99) | | **LR Scheduler** | Constant with Warmup | Cosine Annealing Warm Restart | | **LR Scheduler Args** | Warmup Steps: 100 | Num Cycles: 10, Min LR: 1e-6, LR Decay: 0.9, First Cycle Steps: 9,099 | Source code and training config are available here: https://github.com/cagliostrolab/sd-scripts/tree/main/notebook ### Acknowledgements The development and release of Animagine XL 3.1 would not have been possible without the invaluable contributions and support from the following individuals and organizations: - **[SeaArt.ai](https://www.seaart.ai/)**: Our collaboration partner and sponsor. - **[Shadow Lilac](https://huggingface.co/shadowlilac)**: For providing the aesthetic classification model, [aesthetic-shadow-v2](https://huggingface.co/shadowlilac/aesthetic-shadow-v2). - **[Derrian Distro](https://github.com/derrian-distro)**: For their custom learning rate scheduler, adapted from [LoRA Easy Training Scripts](https://github.com/derrian-distro/LoRA_Easy_Training_Scripts/blob/main/custom_scheduler/LoraEasyCustomOptimizer/CustomOptimizers.py). - **[Kohya SS](https://github.com/kohya-ss)**: For their comprehensive training scripts. - **Cagliostrolab Collaborators**: For their dedication to model training, project management, and data curation. - **Early Testers**: For their valuable feedback and quality assurance efforts. - **NovelAI**: For their innovative approach to aesthetic tagging, which served as an inspiration for our implementation. - **KBlueLeaf**: For providing inspiration in balancing quality tags distribution and managing tags based on [Hakubooru Metainfo](https://github.com/KohakuBlueleaf/HakuBooru/blob/main/hakubooru/metainfo.py) Thank you all for your support and expertise in pushing the boundaries of anime-style image generation. ## Collaborators - [Linaqruf](https://huggingface.co/Linaqruf) - [ItsMeBell](https://huggingface.co/ItsMeBell) - [Asahina2K](https://huggingface.co/Asahina2K) - [DamarJati](https://huggingface.co/DamarJati) - [Zwicky18](https://huggingface.co/Zwicky18) - [Scipius2121](https://huggingface.co/Scipius2121) - [Raelina](https://huggingface.co/Raelina) - [Kayfahaarukku](https://huggingface.co/kayfahaarukku) - [Kriz](https://huggingface.co/Kr1SsSzz) ## Limitations While Animagine XL 3.1 represents a significant advancement in anime-style image generation, it is important to acknowledge its limitations: 1. **Anime-Focused**: This model is specifically designed for generating anime-style images and is not suitable for creating realistic photos. 2. **Prompt Complexity**: This model may not be suitable for users who expect high-quality results from short or simple prompts. The training focus was on concept understanding rather than aesthetic refinement, which may require more detailed and specific prompts to achieve the desired output. 3. **Prompt Format**: Animagine XL 3.1 is optimized for Danbooru-style tags rather than natural language prompts. For best results, users are encouraged to format their prompts using the appropriate tags and syntax. 4. **Anatomy and Hand Rendering**: Despite the improvements made in anatomy and hand rendering, there may still be instances where the model produces suboptimal results in these areas. 5. **Dataset Size**: The dataset used for training Animagine XL 3.1 consists of approximately 870,000 images. When combined with the previous iteration's dataset (1.2 million), the total training data amounts to around 2.1 million images. While substantial, this dataset size may still be considered limited in scope for an "ultimate" anime model. 6. **NSFW Content**: Animagine XL 3.1 has been designed to generate more balanced NSFW content. However, it is important to note that the model may still produce NSFW results, even if not explicitly prompted. By acknowledging these limitations, we aim to provide transparency and set realistic expectations for users of Animagine XL 3.1. Despite these constraints, we believe that the model represents a significant step forward in anime-style image generation and offers a powerful tool for artists, designers, and enthusiasts alike. ## License Based on Animagine XL 3.0, Animagine XL 3.1 falls under [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/) license, which is compatible with Stable Diffusion models’ license. Key points: 1. **Modification Sharing:** If you modify Animagine XL 3.1, you must share both your changes and the original license. 2. **Source Code Accessibility:** If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too. 3. **Distribution Terms:** Any distribution must be under this license or another with similar rules. 4. **Compliance:** Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values. The choice of this license aims to keep Animagine XL 3.1 open and modifiable, aligning with open source community spirit. It protects contributors and users, encouraging a collaborative, ethical open-source community. This ensures the model not only benefits from communal input but also respects open-source development freedoms. ## Cagliostro Lab Discord Server Finally Cagliostro Lab Server open to public https://discord.gg/cqh9tZgbGc Feel free to join our discord server
mgonzs13/TextBase-7B-v0.1-GGUF
mgonzs13
"2024-06-11T09:21:58Z"
1,355
0
llama.cpp
[ "llama.cpp", "gguf", "mistral", "text-generation", "en", "base_model:SF-Foundation/TextBase-7B-v0.1", "license:cc-by-nc-sa-4.0", "region:us" ]
text-generation
"2024-06-11T08:57:50Z"
--- license: cc-by-nc-sa-4.0 base_model: SF-Foundation/TextBase-7B-v0.1 language: - en pipeline_tag: text-generation tags: - mistral - gguf library_name: llama.cpp model_creator: SF-Foundation model_name: TextBase-7B-v0.1 model_type: mistral quantized_by: mgonzs13 --- # TextBase-7B-v0.1 **Model creator:** [SF-Foundation](https://huggingface.co/SF-Foundation)<br> **Original model**: [TextBase-7B-v0.1](https://huggingface.co/SF-Foundation/TextBase-7B-v0.1)<br> **GGUF quantization:** `llama.cpp` commit [4bfe50f741479c1df1c377260c3ff5702586719e](https://github.com/ggerganov/llama.cpp/tree/4bfe50f741479c1df1c377260c3ff5702586719e)<br> ## Description Finetuned version of Mistral-7B-Instruct. Details on development to be published soon. TextBase-7B was fine-tuned from the open source Mistral-7B model using a novel and patent-pending learning technique. Our learning framework relies on efficiently combining supervised and Reinforcement learning methods leveraging human and AI labels over a combination of public and CRM task-specific datasets. Supervised finetuning allows the model to learn task-specific skills while RLHF imparts human judgement making the model able to generalize, reason and follow instructions efficiently. Checkout more models developed by Salesforce under https://huggingface.co/Salesforce