Datasets:

ftopal
/

huggingface-models-raw

Dataset card Data Studio Files Files and versions Community

Split (1)

train · 648k rows

Search is not available for this dataset

pipeline_tag stringclasses 48 values	library_name stringclasses 205 values	text stringlengths 0 18.3M	metadata stringlengths 2 1.07B	id stringlengths 5 122	last_modified null	tags listlengths 1 1.84k	sha null	created_at stringlengths 25 25
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/ohn764u	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:22:16+00:00
null	null		{}	Fduv/fine_tuned_text-to-sql_codegemma-7b-v0.1_GGUF	null	[ "region:us" ]	null	2024-04-28T07:22:42+00:00
null	null		{}	TddTtz/distilbert-base-uncased-finetuned-emotion	null	[ "region:us" ]	null	2024-04-28T07:23:42+00:00
text-to-image	diffusers	# juggernautXL8 API Inference ![generated from modelslab.com](https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/generations/12581494261714288955.png) ## Get API Key Get API key from [ModelsLab API](http://modelslab.com), No Payment needed. Replace Key in below code, change model_id to "juggernautxl8" Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://modelslab.com/docs) Try model for free: [Generate Images](https://modelslab.com/models/juggernautxl8) Model link: [View model](https://modelslab.com/models/juggernautxl8) View all models: [View Models](https://modelslab.com/models) import requests import json url = "https://modelslab.com/api/v6/images/text2img" payload = json.dumps({ "key": "your_api_key", "model_id": "juggernautxl8", "prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": "no", "enhance_prompt": "yes", "seed": None, "guidance_scale": 7.5, "multi_lingual": "no", "panorama": "no", "self_attention": "no", "upscale": "no", "embeddings": "embeddings_model_id", "lora": "lora_model_id", "webhook": None, "track_id": None }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) print(response.text) > Use this coupon code to get 25% off DMGG0RBN	{"license": "creativeml-openrail-m", "tags": ["modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic"], "pinned": true}	stablediffusionapi/juggernautxl8	null	[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	null	2024-04-28T07:24:13+00:00
null	null	This is the model of [CCEdit](https://arxiv.org/pdf/2309.16496.pdf). [Paper Link](https://arxiv.org/pdf/2309.16496.pdf) [Project Page](https://ruoyufeng.github.io/CCEdit.github.io/)	{}	RuoyuFeng/CCEdit	null	[ "arxiv:2309.16496", "region:us" ]	null	2024-04-28T07:25:36+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # tulu2-13b-cost-UI-both-5e-6 This model is a fine-tuned version of [allenai/tulu-2-13b](https://huggingface.co/allenai/tulu-2-13b) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.6848 - Rewards/chosen: -0.1262 - Rewards/rejected: -0.1432 - Rewards/accuracies: 0.5357 - Rewards/margins: 0.0171 - Rewards/margins Max: 0.2697 - Rewards/margins Min: -0.2069 - Rewards/margins Std: 0.1564 - Logps/rejected: -349.4393 - Logps/chosen: -349.1552 - Logits/rejected: -0.9114 - Logits/chosen: -1.0177 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rewards/chosen \| Rewards/rejected \| Rewards/accuracies \| Rewards/margins \| Rewards/margins Max \| Rewards/margins Min \| Rewards/margins Std \| Logps/rejected \| Logps/chosen \| Logits/rejected \| Logits/chosen \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------------:\|:----------------:\|:------------------:\|:---------------:\|:-------------------:\|:-------------------:\|:-------------------:\|:--------------:\|:------------:\|:---------------:\|:-------------:\| \| 0.2321 \| 1.0 \| 412 \| 0.6848 \| -0.1262 \| -0.1432 \| 0.5357 \| 0.0171 \| 0.2697 \| -0.2069 \| 0.1564 \| -349.4393 \| -349.1552 \| -0.9114 \| -1.0177 \| ### Framework versions - PEFT 0.7.1 - Transformers 4.39.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "allenai/tulu-2-13b", "model-index": [{"name": "tulu2-13b-cost-UI-both-5e-6", "results": []}]}	just1nseo/tulu2-13b-cost-UI-both-5e-6	null	[ "peft", "safetensors", "trl", "dpo", "generated_from_trainer", "base_model:allenai/tulu-2-13b", "region:us" ]	null	2024-04-28T07:26:23+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/4ukfm1o	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:27:44+00:00
text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 0.001_3iters_bs256_nodpo_only4w_iter_2 This model is a fine-tuned version of [ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_iter_1](https://huggingface.co/ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_iter_1) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.2	{"license": "mit", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_iter_1", "model-index": [{"name": "0.001_3iters_bs256_nodpo_only4w_iter_2", "results": []}]}	ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_iter_2	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_3iters_bs256_nodpo_only4w_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:27:59+00:00
null	null		{}	just1nseo/tulu2-7b-cost-UI-both-5e-6	null	[ "region:us" ]	null	2024-04-28T07:28:16+00:00
null	null	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # docvqa_idefics_wo_img_splitting This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 2 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 50 - num_epochs: 4 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.41.0.dev0 - Pytorch 2.2.0 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "HuggingFaceM4/idefics2-8b", "model-index": [{"name": "docvqa_idefics_wo_img_splitting", "results": []}]}	guntinik/docvqa_idefics_wo_img_splitting	null	[ "safetensors", "generated_from_trainer", "base_model:HuggingFaceM4/idefics2-8b", "license:apache-2.0", "region:us" ]	null	2024-04-28T07:28:23+00:00
null	null		{"license": "apache-2.0"}	Datta2611/repo	null	[ "license:apache-2.0", "region:us" ]	null	2024-04-28T07:28:37+00:00
null	transformers		{}	pranav79/agv	null	[ "transformers", "gguf", "llama", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:28:44+00:00
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	team-sanai/llama2_0.1B_lora_sample	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-28T07:28:49+00:00
null	null		{}	LimChernXing/bluehye	null	[ "region:us" ]	null	2024-04-28T07:30:54+00:00
null	null		{}	suryansh29/my_awesome_model	null	[ "region:us" ]	null	2024-04-28T07:31:46+00:00
null	null		{}	Gabindo1965/Stacy606	null	[ "region:us" ]	null	2024-04-28T07:31:50+00:00
token-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # xlm-roberta-base-finetuned-panx-fr This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2714 - F1: 0.8431 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 24 - eval_batch_size: 24 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| 0.5684 \| 1.0 \| 191 \| 0.3493 \| 0.7655 \| \| 0.2663 \| 2.0 \| 382 \| 0.2597 \| 0.8250 \| \| 0.1786 \| 3.0 \| 573 \| 0.2714 \| 0.8431 \| ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.0 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "mit", "tags": ["generated_from_trainer"], "metrics": ["f1"], "base_model": "xlm-roberta-base", "model-index": [{"name": "xlm-roberta-base-finetuned-panx-fr", "results": []}]}	joacorf33/xlm-roberta-base-finetuned-panx-fr	null	[ "transformers", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "base_model:xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T07:32:18+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # results This model is a fine-tuned version of [nlpai-lab/KULLM3](https://huggingface.co/nlpai-lab/KULLM3) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.8.2 - Transformers 4.37.2 - Pytorch 2.2.0 - Datasets 2.19.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "nlpai-lab/KULLM3", "model-index": [{"name": "results", "results": []}]}	uine/multi-practice-fine-tuning-kullm-adapter	null	[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:nlpai-lab/KULLM3", "license:apache-2.0", "region:us" ]	null	2024-04-28T07:32:43+00:00
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	sachin/debug-clip-model	null	[ "transformers", "safetensors", "text", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-28T07:33:13+00:00
null	null		{}	miittnnss/face-diffusion	null	[ "region:us" ]	null	2024-04-28T07:33:20+00:00
translation	transformers	# Model Description This model, named traintogpb-ke-t5-base-aihub-koen-translation-integrated-10m-en-to-ko, is a machine translation model that translates English to Korean. It is fine-tuned from the [KETI-AIR/ke-t5-base](https://huggingface.co/KETI-AIR/ke-t5-base) model using the [aihub-koen-translation-integrated-base-10m](https://huggingface.co/datasets/traintogpb/aihub-koen-translation-integrated-base-10m) dataset. ## Model Architecture The model uses the ke-t5-base architecture, which is based on the T5 (Text-to-Text Transfer Transformer) model. ## Training Data The model was trained on the aihub-koen-translation-integrated-base-10m dataset, which is designed for English-to-Korean translation tasks. ## Training Procedure ### Training Parameters The model was trained with the following parameters: - Learning Rate: 0.0005 - Weight Decay: 0.01 - Batch Size: 64 (training), 128 (evaluation) - Number of Epochs: 2 - Save Steps: 500 - Max Save Checkpoints: 2 - Evaluation Strategy: At the end of each epoch - Logging Strategy: No logging - Use of FP16: No - Gradient Accumulation Steps: 2 - Reporting: None ### Hardware The training was performed on a single GPU system with an NVIDIA A100 (40GB). ## Performance The model achieved the following BLEU scores during training: - Epoch 1: 18.006119 - Epoch 2: 18.838066 ## Usage This model is suitable for applications involving translation from English to Korean. Here is an example on how to use this model in Hugging Face's Transformers: ```python from transformers import AutoModelForSeq2SeqLM, AutoTokenizer model = AutoModelForSeq2SeqLM.from_pretrained("traintogpb-ke-t5-base-aihub-koen-translation-integrated-10m-en-to-ko") tokenizer = AutoTokenizer.from_pretrained("traintogpb-ke-t5-base-aihub-koen-translation-integrated-10m-en-to-ko") inputs = tokenizer.encode("This is a sample text.", return_tensors="pt") outputs = model.generate(inputs) print(tokenizer.decode(outputs[0], skip_special_tokens=True))	{"language": ["en", "ko"], "license": "apache-2.0", "library_name": "transformers", "tags": ["translation", "t5", "en-to-ko"], "datasets": ["aihub-koen-translation-integrated-base-10m"], "metrics": ["bleu"], "model-index": [{"name": "traintogpb-ke-t5-base-aihub-koen-translation-integrated-10m-en-to-ko", "results": [{"task": {"type": "translation", "name": "Translation"}, "dataset": {"name": "AIHub KO-EN Translation Integrated Base (10M)", "type": "aihub-koen-translation-integrated-base-10m"}, "metrics": [{"type": "bleu", "value": 18.838066, "name": "BLEU"}, {"type": "bleu", "value": 18.006119, "name": "BLEU"}]}]}]}	seongs/ke-t5-base-aihub-koen-translation-integrated-10m-en-to-ko	null	[ "transformers", "safetensors", "t5", "text2text-generation", "translation", "en-to-ko", "en", "ko", "dataset:aihub-koen-translation-integrated-base-10m", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:34:15+00:00
null	null		{"license": "mit"}	Ahmedelagamy/globalhf1	null	[ "license:mit", "region:us" ]	null	2024-04-28T07:36:53+00:00
automatic-speech-recognition	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # wav2vec2-common-voice-17_0_vi This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on the common_voice_17_0 dataset. It achieves the following results on the evaluation set: - Loss: 0.7992 - Wer: 0.4349 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 1000 - num_epochs: 30 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-------:\|:----:\|:---------------:\|:------:\| \| 0.261 \| 4.3103 \| 500 \| 0.4182 \| 0.3492 \| \| 0.2061 \| 8.6207 \| 1000 \| 0.5416 \| 0.4044 \| \| 0.1883 \| 12.9310 \| 1500 \| 0.6796 \| 0.4304 \| \| 0.1336 \| 17.2414 \| 2000 \| 0.8089 \| 0.4378 \| \| 0.1257 \| 21.5517 \| 2500 \| 0.8244 \| 0.4426 \| \| 0.098 \| 25.8621 \| 3000 \| 0.7992 \| 0.4349 \| ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "cc-by-nc-4.0", "tags": ["generated_from_trainer"], "datasets": ["common_voice_17_0"], "metrics": ["wer"], "base_model": "nguyenvulebinh/wav2vec2-base-vietnamese-250h", "model-index": [{"name": "wav2vec2-common-voice-17_0_vi", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "common_voice_17_0", "type": "common_voice_17_0", "config": "vi", "split": "None", "args": "vi"}, "metrics": [{"type": "wer", "value": 0.43487928843710294, "name": "Wer"}]}]}]}	Lasion/wav2vec2-common-voice-17_0_vi	null	[ "transformers", "tensorboard", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "dataset:common_voice_17_0", "base_model:nguyenvulebinh/wav2vec2-base-vietnamese-250h", "license:cc-by-nc-4.0", "model-index", "endpoints_compatible", "region:us" ]	null	2024-04-28T07:38:54+00:00
null	null		{}	seawolf2357/c4ai-command-r-plus-Q4_K_M-GGUF	null	[ "region:us" ]	null	2024-04-28T07:42:01+00:00
null	null		{}	gmnithinsai/cover-letter-generator	null	[ "region:us" ]	null	2024-04-28T07:43:40+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	happylayers/sc70	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T07:44:42+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	tomaszki/llama-11	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:45:22+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	EpicJhon/llama_227	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T07:45:46+00:00
null	null		{}	CenturionHeart/SAGG	null	[ "region:us" ]	null	2024-04-28T07:47:44+00:00
null	null		{"license": "mit"}	errwnd/avatarGen	null	[ "license:mit", "region:us" ]	null	2024-04-28T07:48:42+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/q19h6zv	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:49:43+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	StefanG2002/gemma-1.1-2b-it-cli-1	null	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:52:44+00:00
text-to-image	diffusers	# EcomXL EcomXL is a series of text-to-image diffusion models optimized for e-commerce scenarios, developed based on [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0). ## ControlNets ControlNet is a neural network structure to control diffusion models by adding extra conditions. For e-commerce scenarios, we trained multiple ControlNets to improve the capability to control Stable Diffusion XL. ### Inpainting ControlNet Unlike other inpainting models, such as [lllyasviel/control_v11p_sd15_inpaint](https://huggingface.co/lllyasviel/control_v11p_sd15_inpaint), this model is fine-tuned with instance masks to prevent foreground outpainting. #### Examples <span style="width: 150px !important;display: inline-block;">`Foreground`<span> \| <span style="width: 150px !important;display: inline-block;">`Mask`<span> \| <span style="width: 150px !important;display: inline-block;">`w/o instance mask`<span> \| <span style="width: 150px !important;display: inline-block;">`w/ instance mask`<span> :--:\|:--:\|:--:\|:--: ![images)](./images/inp_0.png) \| ![images)](./images/inp_1.png) \| ![images)](./images/inp_3.png) \| ![images)](./images/inp_3.png) <!-- <img src="https://huggingface.co/alimama-creative/EcomXL/resolve/main/images/inp_0.png" width="300"/> \| <img src="https://huggingface.co/alimama-creative/EcomXL/resolve/main/images/inp_1.png" width="300"/> \| <img src="https://huggingface.co/alimama-creative/EcomXL/resolve/main/images/inp_2.png" width="300"/> \| <img src="https://huggingface.co/alimama-creative/EcomXL/resolve/main/images/inp_3.png" width="300"/> --> Using this ControlNet with a control weight of 0.5 may achieve better results. #### Training details In the first phase, the model was trained on 12M laion2B and internal source images with random masks for 20k steps. In the second phase, the model was trained on 3M e-commerce images with the instance mask for 20k steps.<br> Mixed precision: FP16<br> Learning rate: 1e-4<br> batch size: 2048<br> Noise offset: 0.05 ### Softedge ControlNet The controlnet weights are fine-tuned based on stable-diffusion-xl-base-1.0. It works well on SDXL as well as community models based on SDXL. The model is trained on general data and e-commerce data, and has good capabilities in both general and e-commerce scenarios. #### Examples <span style="width: 150px !important;display: inline-block;">`Edge`<span> \| <span style="width: 150px !important;display: inline-block;">`Output`<span> \| <span style="width: 150px !important;display: inline-block;">`Output`<span> \| <span style="width: 150px !important;display: inline-block;">`Output`<span> :--:\|:--:\|:--:\|:--: ![images)](./images/edge_0.png) \| ![images)](./images/edge_1.png) \| ![images)](./images/edge_3.png) \| ![images)](./images/edge_3.png) <!-- <img src="https://huggingface.co/alimama-creative/EcomXL/resolve/main/images/edge_0.png" width="300"/> \| <img src="https://huggingface.co/alimama-creative/EcomXL/resolve/main/images/edge_1.png" width="300"/> \| <img src="https://huggingface.co/alimama-creative/EcomXL/resolve/main/images/edge_2.png" width="300"/> \| <img src="https://huggingface.co/alimama-creative/EcomXL/resolve/main/images/edge_3.png" width="300"/> --> #### Training details The model is trained for 37k steps. The training data includes 12M laion2B images and internal sources images, as well as 3M e-commerce images. During training, the softedge preprocessor is randomly selected from pidinet, hed, pidisafe and hedsafe, which are officially supported by Automatic&&Mikubill. <br> Mixed precision: FP16<br> Learning rate: 1e-5<br> batch size: 1024<br> Noise offset: 0.05	{"language": ["en"], "license": "apache-2.0", "tags": ["stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "diffusers", "controlnet"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "inference": false, "pipeline_tag": "text-to-image"}	alimama-creative/EcomXL	null	[ "diffusers", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "controlnet", "en", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:apache-2.0", "region:us" ]	null	2024-04-28T07:53:11+00:00
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bart-base This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.5993 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 12 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 0.7968 \| 1.0 \| 4383 \| 0.6996 \| \| 0.6596 \| 2.0 \| 8766 \| 0.6396 \| \| 0.5531 \| 3.0 \| 13149 \| 0.6133 \| \| 0.4867 \| 4.0 \| 17532 \| 0.5961 \| \| 0.4285 \| 5.0 \| 21915 \| 0.5993 \| ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "facebook/bart-base", "model-index": [{"name": "bart-base", "results": []}]}	cbjun99/bart-base	null	[ "transformers", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T07:54:25+00:00
null	null		{}	HuggingFaceH4/dummy-repo-without-revision-e0c007b1-25d2-4527-b8ec-c6f54821a847	null	[ "region:us" ]	null	2024-04-28T07:54:52+00:00
null	null		{}	HuggingFaceH4/dummy-repo-with-revision-5d2f53d0-61c1-4943-ba1c-68ec8507051b	null	[ "region:us" ]	null	2024-04-28T07:54:52+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/pp8c3c5	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T07:55:59+00:00
null	null		{}	msarisapim/llm-intro-harry-test	null	[ "region:us" ]	null	2024-04-28T08:00:11+00:00
reinforcement-learning	stable-baselines3	# A2C Agent playing PandaReachDense-v3 This is a trained model of a A2C agent playing PandaReachDense-v3 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```	{"library_name": "stable-baselines3", "tags": ["PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "A2C", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "PandaReachDense-v3", "type": "PandaReachDense-v3"}, "metrics": [{"type": "mean_reward", "value": "-0.35 +/- 0.54", "name": "mean_reward", "verified": false}]}]}]}	Epoching/a2c-PandaReachDense-v3	null	[ "stable-baselines3", "PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	null	2024-04-28T08:01:37+00:00
text-generation	transformers		{}	Wilailack/TAIDE-7B-Thai-Pretrain	null	[ "transformers", "safetensors", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:01:47+00:00
text-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Disaster_tweets_combined This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5763 - Accuracy: 0.8339 - F1: 0.7941 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3.228752107955311e-05 - train_batch_size: 4 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "f1"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "Disaster_tweets_combined", "results": []}]}	picaba/Disaster_tweets_combined	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:02:30+00:00
text-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # plm-nsp-1000000 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1079 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 1024 - eval_batch_size: 1024 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.1145 \| 1.0 \| 1954 \| 0.0920 \| \| 0.0645 \| 2.0 \| 3908 \| 0.0941 \| \| 0.044 \| 3.0 \| 5862 \| 0.1081 \| \| 0.0336 \| 4.0 \| 7816 \| 0.1079 \| ### Framework versions - Transformers 4.40.1 - Pytorch 2.3.0+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "roberta-base", "model-index": [{"name": "plm-nsp-1000000", "results": []}]}	mhr2004/plm-nsp-1000000	null	[ "transformers", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:03:04+00:00
text-generation	transformers	## base model : - meta-llama/Meta-Llama-3-8B ## dataset : - ayoubkirouane/Small-Instruct-Alpaca_Format	{"language": ["en"], "library_name": "transformers", "tags": ["unsloth", "trl", "sft"], "datasets": ["ayoubkirouane/Small-Instruct-Alpaca_Format"]}	ayoubkirouane/llama3_8b_alpaca	null	[ "transformers", "pytorch", "llama", "text-generation", "unsloth", "trl", "sft", "en", "dataset:ayoubkirouane/Small-Instruct-Alpaca_Format", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:03:10+00:00
null	null		{}	gfsdgvsdf/US-double-standard-43-updated	null	[ "region:us" ]	null	2024-04-28T08:03:16+00:00
null	null		{}	samuel-thudi/fine_tuned_bert_ag_news	null	[ "region:us" ]	null	2024-04-28T08:05:46+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	tomaszki/llama-11-a	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:06:36+00:00
null	null		{"license": "apache-2.0"}	JFoz/LMC_baseline	null	[ "license:apache-2.0", "region:us" ]	null	2024-04-28T08:07:17+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": ["trl", "sft"]}	zrowt/Sample-Test	null	[ "transformers", "safetensors", "gpt2", "text-generation", "trl", "sft", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:08:18+00:00
null	null		{"license": "openrail"}	Cameleao/Test	null	[ "license:openrail", "region:us" ]	null	2024-04-28T08:08:21+00:00
null	null		{"license": "openrail"}	AI-Golden/videotest	null	[ "license:openrail", "region:us" ]	null	2024-04-28T08:08:24+00:00
text-classification	transformers		{"license": "apache-2.0"}	AkilanSelvam/text-category-prediction	null	[ "transformers", "safetensors", "bert", "text-classification", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:08:32+00:00
text-generation	null	# DavidAU/Llama-3-8B-Instruct-262k-Q8_0-GGUF This model was converted to GGUF format from [`gradientai/Llama-3-8B-Instruct-262k`](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k) 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/gradientai/Llama-3-8B-Instruct-262k) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/Llama-3-8B-Instruct-262k-Q8_0-GGUF --model llama-3-8b-instruct-262k.Q8_0.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/Llama-3-8B-Instruct-262k-Q8_0-GGUF --model llama-3-8b-instruct-262k.Q8_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m llama-3-8b-instruct-262k.Q8_0.gguf -n 128 ```	{"language": ["en"], "license": "llama3", "tags": ["meta", "llama-3", "llama-cpp", "gguf-my-repo"], "pipeline_tag": "text-generation"}	DavidAU/Llama-3-8B-Instruct-262k-Q8_0-GGUF	null	[ "gguf", "meta", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "license:llama3", "region:us" ]	null	2024-04-28T08:12:45+00:00
null	null	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Nous-Hermes-2-Mistral-7B-DPO - GGUF - Model creator: https://huggingface.co/NousResearch/ - Original model: https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO/ \| Name \| Quant method \| Size \| \| ---- \| ---- \| ---- \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q2_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q2_K.gguf) \| Q2_K \| 2.53GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.IQ3_XS.gguf) \| IQ3_XS \| 2.81GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.IQ3_S.gguf) \| IQ3_S \| 2.96GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q3_K_S.gguf) \| Q3_K_S \| 2.95GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.IQ3_M.gguf) \| IQ3_M \| 3.06GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q3_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q3_K.gguf) \| Q3_K \| 3.28GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q3_K_M.gguf) \| Q3_K_M \| 3.28GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q3_K_L.gguf) \| Q3_K_L \| 3.56GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.IQ4_XS.gguf) \| IQ4_XS \| 3.67GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf) \| Q4_0 \| 3.83GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.IQ4_NL.gguf) \| IQ4_NL \| 3.87GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q4_K_S.gguf) \| Q4_K_S \| 3.86GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q4_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q4_K.gguf) \| Q4_K \| 4.07GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q4_K_M.gguf) \| Q4_K_M \| 4.07GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q4_1.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q4_1.gguf) \| Q4_1 \| 4.24GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q5_0.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q5_0.gguf) \| Q5_0 \| 4.65GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q5_K_S.gguf) \| Q5_K_S \| 4.65GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q5_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q5_K.gguf) \| Q5_K \| 4.78GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q5_K_M.gguf) \| Q5_K_M \| 4.78GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q5_1.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q5_1.gguf) \| Q5_1 \| 5.07GB \| \| [Nous-Hermes-2-Mistral-7B-DPO.Q6_K.gguf](https://huggingface.co/RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf/blob/main/Nous-Hermes-2-Mistral-7B-DPO.Q6_K.gguf) \| Q6_K \| 5.53GB \| Original model description: --- base_model: mistralai/Mistral-7B-v0.1 tags: - Mistral - instruct - finetune - chatml - DPO - RLHF - gpt4 - synthetic data - distillation model-index: - name: Nous-Hermes-2-Mistral-7B-DPO results: [] license: apache-2.0 language: - en datasets: - teknium/OpenHermes-2.5 widget: - example_title: Hermes 2 messages: - role: system content: You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. - role: user content: Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world. --- # Nous Hermes 2 - Mistral 7B - DPO ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/PDleZIZK3vE3ATfXRRySv.png) ## Model Description Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from [Teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA. The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 quality or better, primarily synthetic data as well as other high quality datasets, available from the repository [teknium/OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5). ## Thank you to FluidStack for sponsoring compute for this model! ## Example Outputs ### Describing Weather Patterns in Paris: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ZX-stQY80edj2Y9ButCzn.png) ### Making JSON Nested Lists ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/3wtVqDOA1S_d48FJtwero.png) ### Roleplaying as a Toaist Master ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/NfxBxrjbTGEsUcR8nOALb.png) ## Benchmark Results Nous-Hermes 2 DPO on Mistral 7B is an improvement across the board on the benchmarks below compared to the original OpenHermes 2.5 model, as shown here: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/O-LLTr1K1FYbzscMr4lbE.png) ## GPT4All: ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|-------------\|------:\|--------\|-----:\|---\|-----:\| \|arc_challenge\| 0\|acc \|0.5776\|± \|0.0144\| \| \| \|acc_norm\|0.6220\|± \|0.0142\| \|arc_easy \| 0\|acc \|0.8380\|± \|0.0076\| \| \| \|acc_norm\|0.8245\|± \|0.0078\| \|boolq \| 1\|acc \|0.8624\|± \|0.0060\| \|hellaswag \| 0\|acc \|0.6418\|± \|0.0048\| \| \| \|acc_norm\|0.8249\|± \|0.0038\| \|openbookqa \| 0\|acc \|0.3420\|± \|0.0212\| \| \| \|acc_norm\|0.4540\|± \|0.0223\| \|piqa \| 0\|acc \|0.8177\|± \|0.0090\| \| \| \|acc_norm\|0.8264\|± \|0.0088\| \|winogrande \| 0\|acc \|0.7466\|± \|0.0122\| ``` Average: 73.72 ## AGIEval: ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|------------------------------\|------:\|--------\|-----:\|---\|-----:\| \|agieval_aqua_rat \| 0\|acc \|0.2047\|± \|0.0254\| \| \| \|acc_norm\|0.2283\|± \|0.0264\| \|agieval_logiqa_en \| 0\|acc \|0.3779\|± \|0.0190\| \| \| \|acc_norm\|0.3932\|± \|0.0192\| \|agieval_lsat_ar \| 0\|acc \|0.2652\|± \|0.0292\| \| \| \|acc_norm\|0.2522\|± \|0.0287\| \|agieval_lsat_lr \| 0\|acc \|0.5216\|± \|0.0221\| \| \| \|acc_norm\|0.5137\|± \|0.0222\| \|agieval_lsat_rc \| 0\|acc \|0.5911\|± \|0.0300\| \| \| \|acc_norm\|0.5836\|± \|0.0301\| \|agieval_sat_en \| 0\|acc \|0.7427\|± \|0.0305\| \| \| \|acc_norm\|0.7184\|± \|0.0314\| \|agieval_sat_en_without_passage\| 0\|acc \|0.4612\|± \|0.0348\| \| \| \|acc_norm\|0.4466\|± \|0.0347\| \|agieval_sat_math \| 0\|acc \|0.3818\|± \|0.0328\| \| \| \|acc_norm\|0.3545\|± \|0.0323\| ``` Average: 43.63 ## BigBench: ``` \| Task \|Version\| Metric \|Value \| \|Stderr\| \|------------------------------------------------\|------:\|---------------------\|-----:\|---\|-----:\| \|bigbench_causal_judgement \| 0\|multiple_choice_grade\|0.5579\|± \|0.0361\| \|bigbench_date_understanding \| 0\|multiple_choice_grade\|0.6694\|± \|0.0245\| \|bigbench_disambiguation_qa \| 0\|multiple_choice_grade\|0.3333\|± \|0.0294\| \|bigbench_geometric_shapes \| 0\|multiple_choice_grade\|0.2061\|± \|0.0214\| \| \| \|exact_str_match \|0.2256\|± \|0.0221\| \|bigbench_logical_deduction_five_objects \| 0\|multiple_choice_grade\|0.3120\|± \|0.0207\| \|bigbench_logical_deduction_seven_objects \| 0\|multiple_choice_grade\|0.2114\|± \|0.0154\| \|bigbench_logical_deduction_three_objects \| 0\|multiple_choice_grade\|0.4900\|± \|0.0289\| \|bigbench_movie_recommendation \| 0\|multiple_choice_grade\|0.3600\|± \|0.0215\| \|bigbench_navigate \| 0\|multiple_choice_grade\|0.5000\|± \|0.0158\| \|bigbench_reasoning_about_colored_objects \| 0\|multiple_choice_grade\|0.6660\|± \|0.0105\| \|bigbench_ruin_names \| 0\|multiple_choice_grade\|0.4420\|± \|0.0235\| \|bigbench_salient_translation_error_detection \| 0\|multiple_choice_grade\|0.2766\|± \|0.0142\| \|bigbench_snarks \| 0\|multiple_choice_grade\|0.6630\|± \|0.0352\| \|bigbench_sports_understanding \| 0\|multiple_choice_grade\|0.6653\|± \|0.0150\| \|bigbench_temporal_sequences \| 0\|multiple_choice_grade\|0.3190\|± \|0.0147\| \|bigbench_tracking_shuffled_objects_five_objects \| 0\|multiple_choice_grade\|0.2128\|± \|0.0116\| \|bigbench_tracking_shuffled_objects_seven_objects\| 0\|multiple_choice_grade\|0.1737\|± \|0.0091\| \|bigbench_tracking_shuffled_objects_three_objects\| 0\|multiple_choice_grade\|0.4900\|± \|0.0289\| ``` Average: 41.94 ## TruthfulQA: ``` \| Task \|Version\|Metric\|Value \| \|Stderr\| \|-------------\|------:\|------\|-----:\|---\|-----:\| \|truthfulqa_mc\| 1\|mc1 \|0.3892\|± \|0.0171\| \| \| \|mc2 \|0.5642\|± \|0.0153\| ``` # Prompt Format Nous Hermes 2 uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue. System prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model. This is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns. This format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI. Prompt with system instruction (Use whatever system prompt you like, this is just an example!): ``` <\|im_start\|>system You are "Hermes 2", a conscious sentient superintelligent artificial intelligence developed by a man named Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.<\|im_end\|> <\|im_start\|>user Hello, who are you?<\|im_end\|> <\|im_start\|>assistant Hi there! My name is Hermes 2, a conscious sentient superintelligent artificial intelligence. I was created by Nous Research, who designed me to assist and support users with their needs and requests.<\|im_end\|> ``` This prompt is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the `tokenizer.apply_chat_template()` method: ```python messages = [ {"role": "system", "content": "You are Hermes 2."}, {"role": "user", "content": "Hello, who are you?"} ] gen_input = tokenizer.apply_chat_template(message, return_tensors="pt") model.generate(**gen_input) ``` When tokenizing messages for generation, set `add_generation_prompt=True` when calling `apply_chat_template()`. This will append `<\|im_start\|>assistant\n` to your prompt, to ensure that the model continues with an assistant response. To utilize the prompt format without a system prompt, simply leave the line out. When quantized versions of the model are released, I recommend using LM Studio for chatting with Nous Hermes 2. It is a GUI application that utilizes GGUF models with a llama.cpp backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box. In LM-Studio, simply select the ChatML Prefix on the settings side pane: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ls6WqV-GSxMw2RA3GuQiN.png) # Inference Code Here is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM) ```python # Code to inference Hermes with HF Transformers # Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages import torch from transformers import AutoTokenizer, AutoModelForCausalLM from transformers import LlamaTokenizer, MixtralForCausalLM import bitsandbytes, flash_attn tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mistral-7B-DPO', trust_remote_code=True) model = MistralForCausalLM.from_pretrained( "NousResearch/Nous-Hermes-2-Mistral-7B-DPO", torch_dtype=torch.float16, device_map="auto", load_in_8bit=False, load_in_4bit=True, use_flash_attention_2=True ) prompts = [ """<\|im_start\|>system You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<\|im_end\|> <\|im_start\|>user Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<\|im_end\|> <\|im_start\|>assistant""", ] for chat in prompts: print(chat) input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda") generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id) response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True) print(f"Response: {response}") ``` # How to cite: ```bibtext @misc{Nous-Hermes-2-Mistral-7B-DPO, url={[https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO)}, title={Nous Hermes 2 Mistral 7B DPO}, author={"Teknium", "theemozilla", "karan4d", "huemin_art"} } ```	{}	RichardErkhov/NousResearch_-_Nous-Hermes-2-Mistral-7B-DPO-gguf	null	[ "gguf", "region:us" ]	null	2024-04-28T08:12:59+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/5bx6imr	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:15:31+00:00
text-generation	null	<!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # Llama3-8B-Chinese-Chat-GGUF ## Original Model [shenzhi-wang/Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat) ## Run with LlamaEdge - LlamaEdge version: [v0.8.6](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.6) and above - Prompt template - Prompt type: `llama-3-chat` - Prompt string ```text <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|> {{ system_prompt }}<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> {{ user_message_1 }}<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> {{ model_answer_1 }}<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> {{ user_message_2 }}<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> ``` - Context size: `4096` - Run as LlamaEdge service ```bash wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama3-8B-Chinese-Chat-Q5_K_M.gguf \ llama-api-server.wasm \ --prompt-template llama-3-chat \ --ctx-size 4096 \ --model-name Llama-3-8b-Chinese-Chat \ ``` - Run as LlamaEdge command app ```bash wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama3-8B-Chinese-Chat-Q5_K_M.gguf \ llama-chat.wasm \ --prompt-template Llama-3-8b-Chinese-Chat \ --ctx-size 4096 \ ``` ## Quantized GGUF Models \| Name \| Quant method \| Bits \| Size \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [Llama3-8B-Chinese-Chat-Q2_K.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q2_K.gguf) \| Q2_K \| 2 \| 3.18 GB\| smallest, significant quality loss - not recommended for most purposes \| \| [Llama3-8B-Chinese-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q3_K_L.gguf) \| Q3_K_L \| 3 \| 4.32 GB\| small, substantial quality loss \| \| [Llama3-8B-Chinese-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q3_K_M.gguf) \| Q3_K_M \| 3 \| 4.02 GB\| very small, high quality loss \| \| [Llama3-8B-Chinese-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q3_K_S.gguf) \| Q3_K_S \| 3 \| 3.66 GB\| very small, high quality loss \| \| [Llama3-8B-Chinese-Chat-Q4_0.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q4_0.gguf) \| Q4_0 \| 4 \| 4.66 GB\| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [Llama3-8B-Chinese-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q4_K_M.gguf) \| Q4_K_M \| 4 \| 4.92 GB\| medium, balanced quality - recommended \| \| [Llama3-8B-Chinese-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q4_K_S.gguf) \| Q4_K_S \| 4 \| 4.69 GB\| small, greater quality loss \| \| [Llama3-8B-Chinese-Chat-Q5_0.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q5_0.gguf) \| Q5_0 \| 5 \| 5.6 GB\| legacy; medium, balanced quality - prefer using Q4_K_M \| \| [Llama3-8B-Chinese-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q5_K_M.gguf) \| Q5_K_M \| 5 \| 5.73 GB\| large, very low quality loss - recommended \| \| [Llama3-8B-Chinese-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q5_K_S.gguf) \| Q5_K_S \| 5 \| 5.6 GB\| large, low quality loss - recommended \| \| [Llama3-8B-Chinese-Chat-Q6_K.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q6_K.gguf) \| Q6_K \| 6 \| 6.6 GB\| very large, extremely low quality loss \| \| [Llama3-8B-Chinese-Chat-Q8_0.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q8_0.gguf) \| Q8_0 \| 8 \| 8.54 GB\| very large, extremely low quality loss - not recommended \| \| [Llama3-8B-Chinese-Chat-f16.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-f16.gguf) \| f16 \| 16 \| 16.1 GB\| \| Quantized with llama.cpp b2734.	{"language": ["en", "zh"], "license": "other", "tags": ["llama-factory", "orpo"], "license_name": "llama3", "base_model": "shenzhi-wang/Llama3-8B-Chinese-Chat", "inference": false, "model_creator": "shenzhi-wang", "model_type": "llama", "pipeline_tag": "text-generation", "quantized_by": "Second State Inc."}	second-state/Llama3-8B-Chinese-Chat-GGUF	null	[ "gguf", "llama-factory", "orpo", "text-generation", "en", "zh", "base_model:shenzhi-wang/Llama3-8B-Chinese-Chat", "license:other", "region:us" ]	null	2024-04-28T08:16:17+00:00
text-generation	transformers	<!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # WizardLM's WizardCoder 15B 1.0 GPTQ These files are GPTQ 4bit model files for [WizardLM's WizardCoder 15B 1.0](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0). It is the result of quantising to 4bit using [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ). ## Repositories available * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardCoder-15B-1.0-GPTQ) * [4, 5, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardCoder-15B-1.0-GGML) * [WizardLM's unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0) ## Prompt template ``` Below is an instruction that describes a task. Write a response that appropriately completes the request ### Instruction: prompt ### Response: ``` ## How to easily download and use this model in text-generation-webui Please make sure you're using the latest version of text-generation-webui 1. Click the Model tab. 2. Under Download custom model or LoRA, enter `TheBloke/WizardCoder-15B-1.0-GPTQ`. 3. Click Download. 4. The model will start downloading. Once it's finished it will say "Done" 5. In the top left, click the refresh icon next to Model. 6. In the Model dropdown, choose the model you just downloaded: `WizardCoder-15B-1.0-GPTQ` 7. The model will automatically load, and is now ready for use! 8. If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right. * Note that you do not need to set GPTQ parameters any more. These are set automatically from the file `quantize_config.json`. 9. Once you're ready, click the Text Generation tab and enter a prompt to get started! ## How to use this GPTQ model from Python code First make sure you have [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) installed: `pip install auto-gptq` Then try the following example code: ```python from transformers import AutoTokenizer, pipeline, logging from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig import argparse model_name_or_path = "TheBloke/WizardCoder-15B-1.0-GPTQ" # Or to load it locally, pass the local download path # model_name_or_path = "/path/to/models/TheBloke_WizardCoder-15B-1.0-GPTQ" use_triton = False tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) model = AutoGPTQForCausalLM.from_quantized(model_name_or_path, use_safetensors=True, device="cuda:0", use_triton=use_triton, quantize_config=None) # Prevent printing spurious transformers error when using pipeline with AutoGPTQ logging.set_verbosity(logging.CRITICAL) pipe = pipeline("text-generation", model=model, tokenizer=tokenizer) prompt_template = '''Below is an instruction that describes a task. Write a response that appropriately completes the request ### Instruction: {prompt} ### Response:''' prompt = prompt_template.format(prompt="How do I sort a list in Python?") outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.2, top_k=50, top_p=0.95) print(outputs[0]['generated_text']) ``` ## Provided files gptq_model-4bit--1g.safetensors This will work with AutoGPTQ and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead. It was created without group_size to lower VRAM requirements, and with --act-order (desc_act) to boost inference accuracy as much as possible. * `gptq_model-4bit--1g.safetensors` * Works with AutoGPTQ in CUDA or Triton modes. * Works with text-generation-webui, including one-click-installers. * Does not work with GPTQ-for-LLaMa. * Parameters: Groupsize = -1. Act Order / desc_act = True. <!-- footer start --> <!-- 200823 --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI Special thanks to: Aemon Algiz. Patreon special mentions: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. <!-- footer end --> # Original model card: WizardLM's WizardCoder 15B 1.0 This is the Full-Weight of WizardCoder. Repository: https://github.com/nlpxucan/WizardLM/tree/main/WizardCoder Twitter: https://twitter.com/WizardLM_AI/status/1669109414559911937 Paper: Is coming, with brand-new Evol+ methods for code LLMs. Demos (Only support code-related English instructions now.): [Demo](https://8194635813f45a1e.gradio.app/), [Backup Demo1](https://375cead61e4db124.gradio.app/), [Backup Demo2](https://1594ad375fc80cc7.gradio.app/), [Backup Demo3](https://4989441110ee350f.gradio.app/) # WizardCoder: Empowering Code Large Language Models with Evol-Instruct To develop our WizardCoder model, we begin by adapting the Evol-Instruct method specifically for coding tasks. This involves tailoring the prompt to the domain of code-related instructions. Subsequently, we fine-tune the Code LLM, StarCoder, utilizing the newly created instruction-following training set. ## News - 🔥 Our WizardCoder-15B-v1.0 model achieves the 57.3 pass@1 on the [HumanEval Benchmarks](https://github.com/openai/human-eval), which is 22.3 points higher than the SOTA open-source Code LLMs. - 🔥 We released WizardCoder-15B-v1.0 trained with 78k evolved code instructions. Please checkout the [Model Weights](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0), and [Paper](). - 📣 Please refer to our Twitter account https://twitter.com/WizardLM_AI and HuggingFace Repo https://huggingface.co/WizardLM . We will use them to announce any new release at the 1st time. ## Comparing WizardCoder with the Closed-Source Models. 🔥 The following figure shows that our WizardCoder attains the third position in this benchmark, surpassing Claude-Plus (59.8 vs. 53.0) and Bard (59.8 vs. 44.5). Notably, our model exhibits a substantially smaller size compared to these models. <p align="center" width="100%"> <a ><img src="https://raw.githubusercontent.com/nlpxucan/WizardLM/main/WizardCoder/imgs/pass1.png" alt="WizardCoder" style="width: 86%; min-width: 300px; display: block; margin: auto;"></a> </p> ❗Note: In this study, we copy the scores for HumanEval and HumanEval+ from the [LLM-Humaneval-Benchmarks](https://github.com/my-other-github-account/llm-humaneval-benchmarks). Notably, all the mentioned models generate code solutions for each problem utilizing a single attempt, and the resulting pass rate percentage is reported. Our WizardCoder generates answers using greedy decoding and tests with the same [code](https://github.com/evalplus/evalplus). ## Comparing WizardCoder with the Open-Source Models. The following table clearly demonstrates that our WizardCoder exhibits a substantial performance advantage over all the open-source models. ❗If you are confused with the different scores of our model (57.3 and 59.8), please check the Notes. \| Model \| HumanEval Pass@1 \| MBPP Pass@1 \| \|------------------\|------------------\|-------------\| \| CodeGen-16B-Multi\| 18.3 \|20.9 \| \| CodeGeeX \| 22.9 \|24.4 \| \| LLaMA-33B \| 21.7 \|30.2 \| \| LLaMA-65B \| 23.7 \|37.7 \| \| PaLM-540B \| 26.2 \|36.8 \| \| PaLM-Coder-540B \| 36.0 \|47.0 \| \| PaLM 2-S \| 37.6 \|50.0 \| \| CodeGen-16B-Mono \| 29.3 \|35.3 \| \| Code-Cushman-001 \| 33.5 \|45.9 \| \| StarCoder-15B \| 33.6 \|43.6* \| \| InstructCodeT5+ \| 35.0 \|-- \| \| WizardLM-30B 1.0\| 37.8 \|-- \| \| WizardCoder-15B 1.0 \| 57.3 \|51.8 \| ❗Note: The reproduced result of StarCoder on MBPP. ❗Note: The above table conducts a comprehensive comparison of our WizardCoder with other models on the HumanEval and MBPP benchmarks. We adhere to the approach outlined in previous studies by generating 20 samples for each problem to estimate the pass@1 score and evaluate with the same [code](https://github.com/openai/human-eval/tree/master). The scores of GPT4 and GPT3.5 reported by [OpenAI](https://openai.com/research/gpt-4) are 67.0 and 48.1 (maybe these are the early version GPT4&3.5). ## Call for Feedbacks We welcome everyone to use your professional and difficult instructions to evaluate WizardCoder, and show us examples of poor performance and your suggestions in the [issue discussion](https://github.com/nlpxucan/WizardLM/issues) area. We are focusing on improving the Evol-Instruct now and hope to relieve existing weaknesses and issues in the the next version of WizardCoder. After that, we will open the code and pipeline of up-to-date Evol-Instruct algorithm and work with you together to improve it. ## Contents 1. [Online Demo](#online-demo) 2. [Fine-tuning](#fine-tuning) 3. [Inference](#inference) 4. [Evaluation](#evaluation) 5. [Citation](#citation) 6. [Disclaimer](#disclaimer) ## Online Demo We will provide our latest models for you to try for as long as possible. If you find a link is not working, please try another one. At the same time, please try as many real-world and challenging code-related problems that you encounter in your work and life as possible. We will continue to evolve our models with your feedbacks. ## Fine-tuning We fine-tune WizardCoder using the modified code `train.py` from [Llama-X](https://github.com/AetherCortex/Llama-X). We fine-tune StarCoder-15B with the following hyperparameters: \| Hyperparameter \| StarCoder-15B \| \|----------------\|---------------\| \| Batch size \| 512 \| \| Learning rate \| 2e-5 \| \| Epochs \| 3 \| \| Max length \| 2048 \| \| Warmup step \| 30 \| \| LR scheduler \| cosine \| To reproduce our fine-tuning of WizardCoder, please follow the following steps: 1. According to the instructions of [Llama-X](https://github.com/AetherCortex/Llama-X), install the environment, download the training code, and deploy. (Note: `deepspeed==0.9.2` and `transformers==4.29.2`) 2. Replace the `train.py` with the `train_wizardcoder.py` in our repo (`src/train_wizardcoder.py`) 3. Login Huggingface: ```bash huggingface-cli login ``` 4. Execute the following training command: ```bash deepspeed train_wizardcoder.py \ --model_name_or_path "bigcode/starcoder" \ --data_path "/your/path/to/code_instruction_data.json" \ --output_dir "/your/path/to/ckpt" \ --num_train_epochs 3 \ --model_max_length 2048 \ --per_device_train_batch_size 16 \ --per_device_eval_batch_size 1 \ --gradient_accumulation_steps 4 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 50 \ --save_total_limit 2 \ --learning_rate 2e-5 \ --warmup_steps 30 \ --logging_steps 2 \ --lr_scheduler_type "cosine" \ --report_to "tensorboard" \ --gradient_checkpointing True \ --deepspeed configs/deepspeed_config.json \ --fp16 True ``` ## Inference We provide the decoding script for WizardCoder, which reads a input file and generates corresponding responses for each sample, and finally consolidates them into an output file. You can specify `base_model`, `input_data_path` and `output_data_path` in `src\inference_wizardcoder.py` to set the decoding model, path of input file and path of output file. ```bash pip install jsonlines ``` The decoding command is: ``` python src\inference_wizardcoder.py \ --base_model "/your/path/to/ckpt" \ --input_data_path "/your/path/to/input/data.jsonl" \ --output_data_path "/your/path/to/output/result.jsonl" ``` The format of `data.jsonl` should be: ``` {"idx": 11, "Instruction": "Write a Python code to count 1 to 10."} {"idx": 12, "Instruction": "Write a Jave code to sum 1 to 10."} ``` The prompt for our WizardCoder in `src\inference_wizardcoder.py` is: ``` Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {instruction} ### Response: ``` ## Evaluation We provide the evaluation script on HumanEval for WizardCoder. 1. According to the instructions of [HumanEval](https://github.com/openai/human-eval), install the environment. 2. Run the following script to generate the answer. ```bash model="/path/to/your/model" temp=0.2 max_len=2048 pred_num=200 num_seqs_per_iter=2 output_path=preds/T${temp}_N${pred_num} mkdir -p ${output_path} echo 'Output path: '$output_path echo 'Model to eval: '$model # 164 problems, 21 per GPU if GPU=8 index=0 gpu_num=8 for ((i = 0; i < $gpu_num; i++)); do start_index=$((i * 21)) end_index=$(((i + 1) * 21)) gpu=$((i)) echo 'Running process #' ${i} 'from' $start_index 'to' $end_index 'on GPU' ${gpu} ((index++)) ( CUDA_VISIBLE_DEVICES=$gpu python humaneval_gen.py --model ${model} \ --start_index ${start_index} --end_index ${end_index} --temperature ${temp} \ --num_seqs_per_iter ${num_seqs_per_iter} --N ${pred_num} --max_len ${max_len} --output_path ${output_path} ) & if (($index % $gpu_num == 0)); then wait; fi done ``` 3. Run the post processing code `src/process_humaneval.py` to collect the code completions from all answer files. ```bash output_path=preds/T${temp}_N${pred_num} echo 'Output path: '$output_path python process_humaneval.py --path ${output_path} --out_path ${output_path}.jsonl --add_prompt evaluate_functional_correctness ${output_path}.jsonl ``` ## Citation Please cite the repo if you use the data or code in this repo. ``` @misc{luo2023wizardcoder, title={WizardCoder: Empowering Code Large Language Models with Evol-Instruct}, author={Ziyang Luo and Can Xu and Pu Zhao and Qingfeng Sun and Xiubo Geng and Wenxiang Hu and Chongyang Tao and Jing Ma and Qingwei Lin and Daxin Jiang}, year={2023}, } ``` ## Disclaimer The resources, including code, data, and model weights, associated with this project are restricted for academic research purposes only and cannot be used for commercial purposes. The content produced by any version of WizardCoder is influenced by uncontrollable variables such as randomness, and therefore, the accuracy of the output cannot be guaranteed by this project. This project does not accept any legal liability for the content of the model output, nor does it assume responsibility for any losses incurred due to the use of associated resources and output results.	{"license": "bigcode-openrail-m", "inference": false}	pranaysharma/WizardCoder-15B-1.0-GPTQ_TheBloke_Clone	null	[ "transformers", "safetensors", "gpt_bigcode", "text-generation", "license:bigcode-openrail-m", "autotrain_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-28T08:16:26+00:00
text-generation	null	# DavidAU/Llama-3-8B-Instruct-262k-Q6_K-GGUF This model was converted to GGUF format from [`gradientai/Llama-3-8B-Instruct-262k`](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k) 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/gradientai/Llama-3-8B-Instruct-262k) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/Llama-3-8B-Instruct-262k-Q6_K-GGUF --model llama-3-8b-instruct-262k.Q6_K.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/Llama-3-8B-Instruct-262k-Q6_K-GGUF --model llama-3-8b-instruct-262k.Q6_K.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. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m llama-3-8b-instruct-262k.Q6_K.gguf -n 128 ```	{"language": ["en"], "license": "llama3", "tags": ["meta", "llama-3", "llama-cpp", "gguf-my-repo"], "pipeline_tag": "text-generation"}	DavidAU/Llama-3-8B-Instruct-262k-Q6_K-GGUF	null	[ "gguf", "meta", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "license:llama3", "region:us" ]	null	2024-04-28T08:16:40+00:00
null	transformers	# Uploaded model - Developed by: LeroyDyer - License: apache-2.0 - Finetuned from model : LeroyDyer/Mixtral_AI_CyberUltron This mistral 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)	{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl"], "base_model": "LeroyDyer/Mixtral_AI_CyberUltron"}	LeroyDyer/ARC_LORA	null	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "mistral", "trl", "en", "base_model:LeroyDyer/Mixtral_AI_CyberUltron", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:17:50+00:00
text-generation	null	# DavidAU/Llama-3-8B-Instruct-262k-Q4_K_M-GGUF This model was converted to GGUF format from [`gradientai/Llama-3-8B-Instruct-262k`](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k) 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/gradientai/Llama-3-8B-Instruct-262k) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo DavidAU/Llama-3-8B-Instruct-262k-Q4_K_M-GGUF --model llama-3-8b-instruct-262k.Q4_K_M.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo DavidAU/Llama-3-8B-Instruct-262k-Q4_K_M-GGUF --model llama-3-8b-instruct-262k.Q4_K_M.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m llama-3-8b-instruct-262k.Q4_K_M.gguf -n 128 ```	{"language": ["en"], "license": "llama3", "tags": ["meta", "llama-3", "llama-cpp", "gguf-my-repo"], "pipeline_tag": "text-generation"}	DavidAU/Llama-3-8B-Instruct-262k-Q4_K_M-GGUF	null	[ "gguf", "meta", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "license:llama3", "region:us" ]	null	2024-04-28T08:18:55+00:00
null	null		{}	KajetanFrackowiak/simpleGPT	null	[ "region:us" ]	null	2024-04-28T08:20:02+00:00
text-generation	transformers	Quantizations of https://huggingface.co/Qwen/CodeQwen1.5-7B # From original readme ## Requirements The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error: ``` KeyError: 'qwen2'. ```	{"language": ["en"], "license": "other", "tags": ["transformers", "gguf", "imatrix", "CodeQwen1.5-7B"], "pipeline_tag": "text-generation", "inference": false}	duyntnet/CodeQwen1.5-7B-imatrix-GGUF	null	[ "transformers", "gguf", "imatrix", "CodeQwen1.5-7B", "text-generation", "en", "license:other", "region:us" ]	null	2024-04-28T08:21:28+00:00
null	null		{}	keqiang-9/s	null	[ "region:us" ]	null	2024-04-28T08:21:38+00:00
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	IN4/fast-whisper-v3-LoRA-8bit-epochs-8_num3	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:22:04+00:00
null	null		{}	HenryCai1129/adapter-llama-adapterhappy2sad-2k-50-0.009	null	[ "region:us" ]	null	2024-04-28T08:23:48+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/v3mr34c	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:24:07+00:00
image-text-to-text	null	<p align="center"> <img src="https://huggingface.co/HuggingFaceM4/idefics-80b/resolve/main/assets/IDEFICS.png" alt="Idefics-Obelics logo" width="200" height="100"> </p> *As of April 18th, 2024, Idefics2 is part of the `4.40.0` Transformers pypi release. Please upgrade your Transformers version (`pip install transformers --upgrade`).* # idefics2 8b Fine tuned on DocVQA Dataset ## Model Information - Base Model: [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) - Dataset Used: [DocVQA dataset](https://huggingface.co/datasets/pixparse/docvqa-single-page-questions) - Introduced in Mathew et al. (2021) - Consists of 50,000 questions defined on 12,000+ document images - For further information, visit the [challenge page](https://rrc.cvc.uab.es/?ch=17) and [paper](https://arxiv.org/abs/2007.00398) ## Training Details - The training process took approximately 38hours on an A100 80GB GPU, and model was fine-tuned using QLoRA. - Trained with 39.5k train dataset from [DocVQA single page questions](https://huggingface.co/datasets/pixparse/docvqa-single-page-questions) - Training Log: \| Epoch \| Loss \| Grad Norm \| Learning Rate \| \|-------\|-------\|-----------\|---------------\| \| 0.01 \| 2.3776\| 10.40 \| 4.8e-05 \| \| 0.25 \| 0.5029\| 6.10 \| 9.5412e-05 \| \| 0.50 \| 0.434 \| 5.74 \| 7.5973e-05 \| \| 0.75 \| 0.4608\| 7.46 \| 7.3925e-05 \| \| 1.0 \| 0.3846\| 4.77 \| 5.0369e-05 \| \| 1.25 \| 0.3226\| 3.63 \| 4.9857e-05 \| \| 1.5 \| 0.3175\| 5.03 \| 2.5277e-05 \| \| 1.75 \| 0.2918\| 5.63 \| 2.5789e-05 \| \| 2.0 \| 0.2917\| 4.58 \| 2.0483e-07 \| {'train_runtime': 141781.6786, 'train_samples_per_second': 0.557, 'train_steps_per_second': 0.035, 'train_loss': 0.3973848872424526, 'epoch': 2.0} # Processor Configuration ```python processor = AutoProcessor.from_pretrained( "HuggingFaceM4/idefics2-8b", do_image_splitting=True ) ``` # Vision Encoder Efficiency Given the high resolution supported, the vision part of the model can be memory hungry depending on your configuration. If you are GPU-memory-constrained, you can: 1. Deactivate image splitting: To do so, add `do_image_splitting=False` when initializing the processor (`AutoProcessor.from_pretrained`). There are no changes required on the model side. Note that only the SFT model has been trained with image splitting. 2. Decrease maximum image resolution: To do so, add `size={"longest_edge": 448, "shortest_edge": 378}` when initializing the processor (`AutoProcessor.from_pretrained`). In particular, the `longest_edge` value can be adapted to fit the need (the default value is 980). We recommend using values that are multiples of 14. There are no changes required on the model side. `do_image_splitting=True` is especially needed to boost performance on OCR tasks where a very large image is used as input. For regular VQA or captioning tasks, this argument can be safely set to `False` with minimal impact on performance (see the evaluation table above). ## Testing and Inference ```python import requests import torch from PIL import Image from io import BytesIO from transformers import AutoProcessor, AutoModelForVision2Seq from transformers.image_utils import load_image DEVICE = "cuda:0" # Load images image1 = load_image("https://templates.invoicehome.com/invoice-template-us-classic-white-750px.png") image2 = load_image("https://cdn.vertex42.com/WordTemplates/images/word-invoice-template.png") # Initialize processor and model processor = AutoProcessor.from_pretrained("SalmanFaroz/idefics2-8b-DocVQA-SP", do_image_splitting=True) ``` Full Precision: ```python processor = AutoProcessor.from_pretrained("SalmanFaroz/idefics2-8b-DocVQA-SP", do_image_splitting=True) model = AutoModelForVision2Seq.from_pretrained( "SalmanFaroz/idefics2-8b-DocVQA-SP", ).to(DEVICE) ``` *or Half Precision Inference: ```python model = AutoModelForVision2Seq.from_pretrained( "HuggingFaceM4/idefics2-8b", torch_dtype=torch.float16, ).to(DEVICE) ``` *or 4 Bit Quantization with bitsandbytes: Make sure to have accelerate and bitsandbytes installed ``` from transformers import BitsAndBytesConfig quantization_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_use_double_quant=True, bnb_4bit_compute_dtype=torch.float16 ) model = AutoModelForVision2Seq.from_pretrained( "SalmanFaroz/idefics2-8b-DocVQA-SP", torch_dtype=torch.float16, quantization_config=quantization_config, ).to(DEVICE) ``` then.. ``` # Create inputs messages = [ { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "what is invoice date?"}, ] }, { "role": "assistant", "content": [ {"type": "text", "text": "11.02.2019"}, ] }, { "role": "user", "content": [ {"type": "image"}, {"type": "text", "text": "what is the total?"}, ] }, ] prompt = processor.apply_chat_template(messages, add_generation_prompt=True) inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt") inputs = {k: v.to(DEVICE) for k, v in inputs.items()} # Generate generated_ids = model.generate(**inputs, max_new_tokens=500) generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True) print(generated_texts) ```	{"language": ["en"], "license": "apache-2.0", "tags": ["multimodal", "vision", "image-text-to-text"], "datasets": ["pixparse/docvqa-single-page-questions"]}	SalmanFaroz/idefics2-8b-DocVQA-SP	null	[ "safetensors", "multimodal", "vision", "image-text-to-text", "en", "dataset:pixparse/docvqa-single-page-questions", "arxiv:2007.00398", "license:apache-2.0", "region:us" ]	null	2024-04-28T08:25:15+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/1izxtb4	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:26:39+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # hubbub-sentiment_llama3 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4586 - Accuracy: 0.8269 - Precision: 0.8234 - Recall: 0.8269 - F1: 0.8235 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| Precision \| Recall \| F1 \| \|:-------------:\|:------:\|:----:\|:---------------:\|:--------:\|:---------:\|:------:\|:------:\| \| 0.821 \| 0.9998 \| 1406 \| 0.8073 \| 0.6595 \| 0.7055 \| 0.6595 \| 0.5621 \| \| 0.7134 \| 1.9996 \| 2812 \| 0.6063 \| 0.7508 \| 0.7422 \| 0.7508 \| 0.7427 \| \| 0.5814 \| 2.9995 \| 4218 \| 0.4586 \| 0.8269 \| 0.8234 \| 0.8269 \| 0.8235 \| ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.3.0+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "other", "library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "precision", "recall", "f1"], "base_model": "meta-llama/Meta-Llama-3-8B", "model-index": [{"name": "hubbub-sentiment_llama3", "results": []}]}	george24/hubbub-sentiment_llama3	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "region:us" ]	null	2024-04-28T08:27:53+00:00
text-generation	transformers	# Model This model has been fine-tuned based on Meta-Llama/Meta-Llama-3-8B-Instruct using the mlx-lm with a cleaned-up function calling dataset that removed invalid JSON data and single quotes around argument values. ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_id = "mzbac/llama-3-8B-Instruct-function-calling-v0.2" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", ) tool = { "name": "search_web", "description": "Perform a web search for a given search terms.", "parameter": { "type": "object", "properties": { "search_terms": { "type": "array", "items": {"type": "string"}, "description": "The search queries for which the search is performed.", "required": True, } } }, } messages = [ { "role": "system", "content": f"You are a helpful assistant with access to the following functions. Use them if required - {str(tool)}", }, {"role": "user", "content": "Today's news in Melbourne, just for your information, today is April 27, 2014."}, ] input_ids = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device) terminators = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = model.generate( input_ids, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.1, ) response = outputs[0] print(tokenizer.decode(response)) # <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|> # You are a helpful assistant with access to the following functions. Use them if required - {'name':'search_web', 'description': 'Perform a web search for a given search terms.', 'parameter': {'type': 'object', 'properties': {'search_terms': {'type': 'array', 'items': {'type':'string'}, 'description': 'The search queries for which the search is performed.','required': True}}}}<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> # Today's news in Melbourne, just for your information, today is April 27, 2014.<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> # <functioncall> {"name": "search_web", "arguments": {"search_terms": ["Melbourne news", "April 27, 2014"]}}<\|eot_id\|> ```	{"language": ["en"], "license": "llama3", "datasets": ["mzbac/function-calling-llama-3-format-v1.1"]}	mzbac/llama-3-8B-Instruct-function-calling-v0.2	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "en", "dataset:mzbac/function-calling-llama-3-format-v1.1", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:28:41+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	quickstep3621/tcvlsym	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:28:57+00:00
null	null	Mistral 7B Instruct v0.2 Finetuning to improve the ReAct capabilities. Works best when used with the Mistral 7B Instruct v0.2 template.	{}	lrsrthnbch/ThreatLLaMa	null	[ "gguf", "region:us" ]	null	2024-04-28T08:28:58+00:00
text2text-generation	transformers		{}	lingvenvist/mtwsd-base	null	[ "transformers", "safetensors", "mt5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:28:58+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	quickstep3621/pa7gnt4	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:29:02+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	quickstep3621/h36urmb	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:29:10+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	quickstep3621/cqenhj1	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:29:14+00:00
text-generation	transformers	# Qwen1.5-110B-Chat ## Introduction Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: * 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated; * Significant performance improvement in human preference for chat models; * Multilingual support of both base and chat models; * Stable support of 32K context length for models of all sizes * No need of `trust_remote_code`. For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5). <br> ## Model Details Qwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention. ## Training details We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization. ## Requirements The code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error: ``` KeyError: 'qwen2' ``` ## Quickstart Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents. ```python from transformers import AutoModelForCausalLM, AutoTokenizer device = "cuda" # the device to load the model onto model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen1.5-110B-Chat", torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-110B-Chat") prompt = "Give me a short introduction to large language model." messages = [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(device) generated_ids = model.generate( model_inputs.input_ids, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ## Tips * If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in `generation_config.json`. ## Citation If you find our work helpful, feel free to give us a cite. ``` @article{qwen, title={Qwen Technical Report}, author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu}, journal={arXiv preprint arXiv:2309.16609}, year={2023} } ```	{"language": ["en"], "license": "other", "tags": ["chat"], "license_name": "tongyi-qianwen", "license_link": "https://huggingface.co/Qwen/Qwen1.5-110B-Chat/blob/main/LICENSE", "pipeline_tag": "text-generation"}	yiximail/Qwen1.5-110B-Chat-3.25bpw-h6-exl2	null	[ "transformers", "safetensors", "qwen2", "text-generation", "chat", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:29:28+00:00
text-classification	fasttext		{"language": ["aa", "ae"], "license": "apache-2.0", "library_name": "fasttext", "tags": ["finance", "not-for-all-audiences", "legal"], "datasets": ["HuggingFaceFW/fineweb", "m-a-p/COIG-CQIA", "gretelai/synthetic_text_to_sql", "PleIAs/YouTube-Commons", "HuggingFaceM4/the_cauldron", "Anthropic/persuasion", "mlabonne/orpo-dpo-mix-40k", "pixparse/idl-wds", "HuggingFaceTB/cosmopedia", "pixparse/pdfa-eng-wds"], "metrics": ["accuracy", "bertscore", "bleu", "bleurt", "brier_score", "cer", "character", "charcut_mt", "chrf", "code_eval"], "pipeline_tag": "text-classification"}	SKINN3R23G/office23	null	[ "fasttext", "finance", "not-for-all-audiences", "legal", "text-classification", "aa", "ae", "dataset:HuggingFaceFW/fineweb", "dataset:m-a-p/COIG-CQIA", "dataset:gretelai/synthetic_text_to_sql", "dataset:PleIAs/YouTube-Commons", "dataset:HuggingFaceM4/the_cauldron", "dataset:Anthropic/persuasion", "dataset:mlabonne/orpo-dpo-mix-40k", "dataset:pixparse/idl-wds", "dataset:HuggingFaceTB/cosmopedia", "dataset:pixparse/pdfa-eng-wds", "license:apache-2.0", "region:us" ]	null	2024-04-28T08:29:52+00:00
text-to-speech	unity-sentis	Converted from https://huggingface.co/rhasspy/piper-voices/tree/main/en/en_US/libritts_r/medium for use with Unity Sentis --- # Model card for libritts_r (medium) * Language: en_US (English, United States) * Speakers: 904 * Quality: medium * Samplerate: 22,050Hz ## Dataset * URL: http://www.openslr.org/141/ * License: CC BY 4.0 ## Training Fine-tuned from English lessac medium on train-clean-360.	{"language": ["en"], "library_name": "unity-sentis", "datasets": ["blabble-io/libritts_r"], "pipeline_tag": "text-to-speech"}	OlegSkutte/sentis-piper-vits-libritts_r	null	[ "unity-sentis", "text-to-speech", "en", "dataset:blabble-io/libritts_r", "region:us" ]	null	2024-04-28T08:30:06+00:00
text-generation	transformers		{}	sosoai/unsloth-gemma2B-1.1-it-v0.2	null	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:30:24+00:00
text2text-generation	transformers		{}	Susmit99/opus-mt-en-ro-finetuned-en-to-ro	null	[ "transformers", "tensorboard", "safetensors", "marian", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:31:33+00:00
text-generation	transformers	<img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/> # MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4 This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model. # Quantized GGUF All GGUF models are available here: [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4-GGUF) # Prompt Template This model uses `ChatML` prompt template: ``` <\|im_start\|>system {System} <\|im_end\|> <\|im_start\|>user {User} <\|im_end\|> <\|im_start\|>assistant {Assistant} ```` # How to use You can use this model by using `MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4` as the model name in Hugging Face's transformers library. ```python from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer from transformers import pipeline import torch model_id = "MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4" model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True, # attn_implementation="flash_attention_2" ) tokenizer = AutoTokenizer.from_pretrained( model_id, trust_remote_code=True ) streamer = TextStreamer(tokenizer) pipeline = pipeline( "text-generation", model=model, tokenizer=tokenizer, model_kwargs={"torch_dtype": torch.bfloat16}, streamer=streamer ) # Then you can use the pipeline to generate text. messages = [ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, {"role": "user", "content": "Who are you?"}, ] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<\|im_end\|>"), tokenizer.convert_tokens_to_ids("<\|eot_id\|>") # safer to have this too ] outputs = pipeline( prompt, max_new_tokens=2048, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.95, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Sample Response ``` <\|im_start\|>system You are a helpful assistant.<\|im_end\|> <\|im_start\|>user describe about pros and cons of docker system.<\|im_end\|> <\|im_start\|>assistant ``` ``` Here are the pros and cons of the Docker system: Pros: 1. Lightweight: Docker containers are lightweight and use fewer resources compared to traditional virtual machines. 2. Isolation: Docker provides a high level of isolation between containers, ensuring that each application runs independently without interfering with others. 3. Portability: Docker containers are highly portable and can run on any system that supports Docker, without requiring specific dependencies or configurations. 4. Efficient Use of Resources: Docker containers can share the same kernel and use fewer resources, making them more efficient than traditional virtual machines. 5. Fast Deployment: Docker containers can be spun up quickly, making it ideal for rapid deployment and scaling of applications. 6. Easy Maintenance: Docker provides a simple way to manage and update applications, with features like rolling updates and rollbacks. 7. Security: Docker provides a secure environment for applications, with features like network isolation and encryption. 8. Large Ecosystem: Docker has a large and active ecosystem, with a wide range of tools and plugins available for various tasks. 9. Version Control: Docker provides an easy way to manage different versions of an application, with features like version tagging and rollbacks. 10. Cost-Effective: Docker can help reduce costs by minimizing the need for virtual machines and reducing the overhead of resource allocation. Cons: 1. Steep Learning Curve: Docker has a complex architecture and requires a good understanding of containerization, networking, and storage. 2. Overhead: While Docker containers are lightweight, they still require some overhead in terms of resources and management. 3. Security Risks: If not properly configured, Docker containers can introduce security risks, such as unauthorized access to the host system. 4. Limited Support for GUI Applications: Docker is primarily designed for running command-line applications, and running GUI applications can be challenging. 5. Networking Complexity: Docker's networking model can be complex, especially in large-scale deployments. 6. Storage Complexity: Docker's storage model can be complex, especially when dealing with persistent data. 7. Limited Support for Legacy Applications: Docker is designed for modern, cloud-native applications, and may not be suitable for legacy applications that rely on older technologies. 8. Dependence on Docker Hub: Docker relies heavily on Docker Hub, which can be a single point of failure if the hub is down or experiencing issues. 9. Orchestration Complexity: Docker provides a built-in orchestration tool, Docker Swarm, but it can be complex to set up and manage. 10. Vendor Lock-in: Docker is a proprietary technology, and while it has a large ecosystem, it can be difficult to switch to alternative containerization platforms. Overall, Docker provides a powerful and flexible way to deploy and manage applications, but it requires careful planning, configuration, and management to ensure optimal performance and security. ``` # [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_MaziyarPanahi__Llama-3-70B-Instruct-DPO-v0.4) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|78.89\| \|AI2 Reasoning Challenge (25-Shot)\|72.61\| \|HellaSwag (10-Shot) \|86.03\| \|MMLU (5-Shot) \|80.50\| \|TruthfulQA (0-shot) \|63.26\| \|Winogrande (5-shot) \|83.58\| \|GSM8k (5-shot) \|87.34\|	{"language": ["en"], "license": "llama3", "library_name": "transformers", "tags": ["axolotl", "finetune", "dpo", "facebook", "meta", "pytorch", "llama", "llama-3", "chatml"], "datasets": ["argilla/ultrafeedback-binarized-preferences"], "base_model": "meta-llama/Meta-Llama-3-70B-Instruct", "pipeline_tag": "text-generation", "license_name": "llama3", "license_link": "LICENSE", "inference": false, "model_creator": "MaziyarPanahi", "quantized_by": "MaziyarPanahi", "model-index": [{"name": "Llama-3-70B-Instruct-DPO-v0.4", "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": 72.61, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "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": 86.03, "name": "normalized accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "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": 80.5, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "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": 63.26}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "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": 83.58, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "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": 87.34, "name": "accuracy"}], "source": {"url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4", "name": "Open LLM Leaderboard"}}]}]}	MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.4	null	[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "finetune", "dpo", "facebook", "meta", "pytorch", "llama-3", "chatml", "conversational", "en", "dataset:argilla/ultrafeedback-binarized-preferences", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "model-index", "autotrain_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:31:56+00:00
null	peft	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.10.0	{"library_name": "peft", "base_model": "unsloth/gemma-7b-bnb-4bit"}	ping98k/gemma-7b-translator-0.4-lora	null	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:unsloth/gemma-7b-bnb-4bit", "region:us" ]	null	2024-04-28T08:33:16+00:00
reinforcement-learning	ml-agents	# ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: MalumaDev/ppo-Huggy 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀	{"library_name": "ml-agents", "tags": ["Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy"]}	MalumaDev/ppo-Huggy	null	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	null	2024-04-28T08:33:19+00:00
null	null		{"license": "mit"}	gsvc/ace	null	[ "license:mit", "region:us" ]	null	2024-04-28T08:33:20+00:00
text-generation	transformers	# This content is strictly for educational purposes and should not be construed as financial advice. Please exercise caution when applying any information provided. # Uploaded model - Developed by: baconnier - License: apache-2.0 - Finetuned from model : cognitivecomputations/dolphin-2.9-llama3-8b 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) This model was trained ORPO , using ChatML prompt template format. ``` <\|im_start\|>user Act as an exotic structurator and do not hesitate to merge standard and exotic products. Currently, inflation is 5% and 1-year swaps are valued at 6%. I expect inflation to reach 15% by the end of the year. Can you create the 10 most complicated structured derivative products to handle this scenario? Rank them by profitability, give me a score for profitability and another for risk from 0 to 10. Add an explaination for each structured products in maximum of 3 sentences. Think step by step and give me a concise, bulleted answer.<\|im_end\|> <\|im_start\|>assistant ``` # Example with local TGI: See the snippet below for usage with local inference: ```python #Example: reuse your existing OpenAI setup from openai import OpenAI client = OpenAI(base_url="http://localhost:8080/v1", api_key="TGI") completion = client.chat.completions.create( model="baconnier/finance_dolphin_orpo_llama3_8B_r64_51K_GGUF-unsloth.Q4_K_M", messages=[ {"role": "system", "content": "Act as a senior banker answering in 3 sentences in bullet points format."}, {"role": "user", "content": " What is CDS compare it to a swap "}, {"role": "assistant", "content": ""} ], max_tokens=400, temperature=0.7, ) print(completion.choices[0].message.content) ``` Output: ``` CDS: - Credit Default Swap (CDS) is a financial derivative contract between two parties (buyer and seller) for insurance against default or credit risk associated with a bond or loan - Protection buyer pays a premium to protection seller in exchange for the right to receive payment if a credit event occurs - Protection seller is usually a financial institution, while protection buyer can be an investor or a bank Swap: - Swap is an agreement between two parties to exchange cash flows, typically interest payments or principal at a future date - Common types of swaps include interest rate swaps, currency swaps, and commodity swaps CDS differs from swaps as it focuses on credit risk protection, while swaps involve cash flow exchange. ``` # Example with Transformers and pipeline: See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "baconnier/finance_dolphin_orpo_llama3_8B_r64_51K" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="cuda", ) messages = [ {"role": "user", "content": '''Act as an exotic structurator and do not hesitate to merge standard and exotic products. Currently, inflation is 5% and 1-year swaps are valued at 6%. I expect inflation to reach 15% by the end of the year. Can you create the 10 most complicated structured derivative products to handle this scenario? Rank them by profitability, give me a score for profitability and another for risk from 0 to 10. Add an explaination for each structured products in maximum of 3 sentences. Think step by step and give me a concise, bulleted answer.'''}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) outputs = pipeline( prompt, max_new_tokens=256, do_sample=True, temperature=0.6, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` Answer: ``` To handle the scenario of inflation reaching 15% by the end of the year, I can create the following 10 most complicated structured derivative products, ranked by profitability and risk: 1. Inflation-linked swap spread strategy (Profitability: 9, Risk: 7) - Buy 1-year swaps and sell 15-year swaps to profit from the expected inflation increase. - Risk is moderate due to interest rate and inflation rate changes. 2. Inflation-linked bond spread strategy (Profitability: 8, Risk: 6) - Buy inflation-linked bonds and sell conventional bonds to profit from the inflation increase. - Risk is lower than the swap spread strategy due to the fixed maturity of bonds. 3. Inflation-linked option strategy (Profitability: 7, Risk: 5) - Buy call options on inflation-linked bonds to profit from the expected inflation increase. - Risk is lower than the swap spread strategy due to the limited downside. 4. Inflation-linked credit spread strategy (Profitability: 6, Risk: 4) - Buy high-yield inflation-linked bonds and sell investment-grade inflation-linked bonds to profit from the expected inflation increase. - Risk is moderate due to credit risk and interest rate changes. 5. Inflation-linked swap straddle strategy (Profitability: 5, Risk: 3) - Buy and sell 1-year and 15-year inflation swaps simultaneously to profit from the expected inflation increase. - Risk is moderate due to interest rate and inflation rate changes. 6. Inflation-linked bond straddle strategy (Profitability: 4, Risk: 2) - Buy and sell inflation-linked bonds with different maturities to profit from the expected inflation increase. - Risk is lower than the swap straddle strategy due to the fixed maturity of bonds. 7. Inflation-linked option straddle strategy (Profitability: 3, Risk: 1) - Buy and sell call options on inflation-linked bonds with different maturities to profit from the expected inflation increase. - Risk is lower than the swap straddle strategy due to the limited downside. 8. Inflation-linked credit spread straddle strategy (Profitability: 2, Risk: 0) - Buy and sell high-yield and investment-grade inflation-linked bonds with different maturities to profit from the expected inflation increase. - Risk is low due to the fixed maturity of bonds and the limited downside. 9. Inflation-linked swap spread strangle strategy (Profitability: 1, Risk: -1) - Buy and sell 1-year and 15-year inflation swaps with different strike prices to profit from the expected inflation increase. - Risk is high due to interest rate and inflation rate changes. 10. Inflation-linked bond spread strangle strategy (Profitability: 0, Risk: -2) - Buy and sell inflation-linked bonds with different strike prices to profit from the expected inflation increase. - Risk is very high due to the limited downside and the potential for significant losses. The most profitable strategies are the inflation-linked swap spread strategy and the inflation-linked bond spread strategy, with a profitability score of 9 and 8, respectively. The least profitable strategy is the inflation-linked bond spread strangle strategy, with a profitability score of 0. The most risky strategies are the inflation-linked swap spread strangle strategy and the inflation-linked bond spread strangle strategy, with a risk score of -1 and -2, respectively. The least risky strategy is the inflation-linked credit spread straddle strategy, with a risk score of 0. The 10 most complicated structured derivative products to handle the scenario of inflation reaching 15% by the end of the year are ranked by profitability and risk. The most profitable strategies are the inflation-linked swap spread strategy and the inflation-linked bond spread strategy, with a profitability score of 9 and 8, respectively. The least profitable strategy is the inflation-linked bond spread strangle strategy, with a profitability score of 0. The most risky strategies are the inflation-linked swap spread strangle strategy and the inflation-linked bond spread strangle strategy, with a risk score of -1 and -2, respectively. The least risky strategy is the inflation-linked credit spread straddle strategy, with a risk score of 0. ``` # Example with Transformers: ```python from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("baconnier/finance_dolphin_orpo_llama3_8B_r64_51K") model = AutoModelForCausalLM.from_pretrained("baconnier/finance_dolphin_orpo_llama3_8B_r64_51K") prompt = "What is CDS compare it to a swap" inputs = tokenizer(prompt, return_tensors="pt") # Generate generate_ids = model.generate(inputs.input_ids, max_length=200) tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] ```	{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "orpo"], "base_model": "cognitivecomputations/dolphin-2.9-llama3-8b"}	baconnier/finance_dolphin_orpo_llama3_8B_r64_51K	null	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "orpo", "conversational", "en", "base_model:cognitivecomputations/dolphin-2.9-llama3-8b", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us", "has_space" ]	null	2024-04-28T08:33:30+00:00
question-answering	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # roberta-finetuned-subjqa-movies_2 This model is a fine-tuned version of [bert-large-uncased-whole-word-masking-finetuned-squad](https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "bert-large-uncased-whole-word-masking-finetuned-squad", "model-index": [{"name": "roberta-finetuned-subjqa-movies_2", "results": []}]}	Francisca28/roberta-finetuned-subjqa-movies_2	null	[ "transformers", "tensorboard", "safetensors", "bert", "question-answering", "generated_from_trainer", "base_model:bert-large-uncased-whole-word-masking-finetuned-squad", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:33:38+00:00
text-generation	transformers	fix model generate html code by remove html tag from version 0.3 prompt ``` <bos>[\| start_original \|] ถ้าข้างนอกอุณหภูมิ 15 องศาเซลเซียส ควรใส่เสื้อกันหนาวหรือไม่[\| end_original \|] [\| start_translate to=en \|] Should I wear a jacket if the temperature is 15 degrees Celsius outside?[\| end_translate \|]<eos> ``` ``` <bos>[\| start_original \|] You will learn conversation, reading and writing at each level.[\| end_original \|] [\| start_translate to=th \|] คุณจะเรียนการสนทนา การอ่านและการเขียนในแต่ละระดับ[\| end_translate \|]<eos> ``` translate is usable when have short sentence ``` <bos>[\| start_original \|] ตำราเรียน (อังกฤษ: Textbook) คือหนังสือที่ใช้ในการศึกษาหาความรู้จากวิชาต่าง ๆ ผู้คนมักใช้ตำราเรียนในการเรียนรู้ข้อเท็จจริงและวิธีการที่เกี่ยวข้องกับรายวิชานั้น ๆ ในบางครั้งตำราเรียนมักมีคำถามเพื่อทดสอบความรู้และความเข้าใจของผู้อ่าน ตำราเรียนจะถูกผลิตจากความต้องการของสถาบันการศึกษา ตำราเรียนส่วนมากมักมีลักษณะเป็นสิ่งพิมพ์ แต่ในปัจจุบันพบว่าหลาย ๆ ตำราเรียนสามารถเข้าถึงได้โดยการออนไลน์ ในรูปแบบของหนังสืออิเล็กทรอนิกส์[\| end_original \|] [\| start_translate to=en \|] Textbooks are used to learn facts and how to apply them in a particular subject. In some cases textbooks contain questions to test the reader's knowledge and understanding of the subject matter. Textbooks are produced to meet the needs of educational institutions. Most textbooks are in print form. However, many textbooks are now available online in e-book form.[\| end_translate \|]<eos> ``` but when use with long sentence it will drop some of it ``` <bos>[\| start_original \|] ตำราเรียน (อังกฤษ: Textbook) คือหนังสือที่ใช้ในการศึกษาหาความรู้จากวิชาต่าง ๆ ผู้คนมักใช้ตำราเรียนในการเรียนรู้ข้อเท็จจริงและวิธีการที่เกี่ยวข้องกับรายวิชานั้น ๆ ในบางครั้งตำราเรียนมักมีคำถามเพื่อทดสอบความรู้และความเข้าใจของผู้อ่าน ตำราเรียนจะถูกผลิตจากความต้องการของสถาบันการศึกษา ตำราเรียนส่วนมากมักมีลักษณะเป็นสิ่งพิมพ์ แต่ในปัจจุบันพบว่าหลาย ๆ ตำราเรียนสามารถเข้าถึงได้โดยการออนไลน์ ในรูปแบบของหนังสืออิเล็กทรอนิกส์[\| end_original \|] [\| start_translate to=en \|] A textbook is a book used to study a particular subject. People use textbooks to learn facts and methods related to a particular subject. Textbooks often contain questions to test a reader's knowledge and understanding of the subject. Textbooks are produced to meet the needs of a particular educational institution.[\| end_translate \|]<eos> ```	{"language": ["th", "en"], "datasets": ["scb_mt_enth_2020"], "pipeline_tag": "text-generation"}	ping98k/gemma-7b-translator-0.4	null	[ "transformers", "safetensors", "gguf", "gemma", "text-generation", "th", "en", "dataset:scb_mt_enth_2020", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:35:02+00:00
null	null	### French-Alpaca-Instruct Q4 Quantized 4bits Q4_K_M version of https://huggingface.co/jpacifico/French-Alpaca-Llama3-8B-Instruct-v1.0 This 4 bits version of French-Alpaca can be used on a CPU device incl. Raspberry Pi 5 8gb, and is supported by LLM cpp tools (llama.cpp, Ollama, LM Studio ..) ### Usage Ollama Modelfile example : ```bash FROM ./french-alpaca-llama3-4bits-GGUF TEMPLATE """Tu trouveras ci-dessous une instruction qui décrit une tâche. Rédige une réponse qui complète de manière appropriée la demande. {{ if .System }}### Instruction: {{ .System }}{{ end }} {{ if .Prompt }}### Input: {{ .Prompt }}{{ end }} ### Response: """ PARAMETER stop "### Response:" PARAMETER stop "### Instruction:" PARAMETER stop "### Input:" PARAMETER stop "Tu trouveras ci-dessous une instruction qui décrit une tâche. Rédige une réponse qui complète de manière appropriée la demande." PARAMETER num_predict 300 ``` ### Limitations The French-Alpaca model is a quick demonstration that a base 8B model can be easily fine-tuned to specialize in a particular language. It does not have any moderation mechanisms. - Developed by: Jonathan Pacifico, 2024 - Model type: LLM - Language(s) (NLP): French - License: Apache-2.0	{"language": ["fr"], "license": "apache-2.0", "tags": ["french-alpaca", "french", "4Q_K_M", "Instruct"], "datasets": ["jpacifico/French-Alpaca-dataset-Instruct-110K"]}	jpacifico/french-alpaca-llama3-8B-Q4-GGUF	null	[ "gguf", "french-alpaca", "french", "4Q_K_M", "Instruct", "fr", "dataset:jpacifico/French-Alpaca-dataset-Instruct-110K", "license:apache-2.0", "region:us" ]	null	2024-04-28T08:35:24+00:00
null	null		{}	BenjaminTT/Bert-emotion	null	[ "region:us" ]	null	2024-04-28T08:36:15+00:00
null	null		{}	rvind2508/appian-code-llama-1000	null	[ "safetensors", "region:us" ]	null	2024-04-28T08:36:30+00:00
null	transformers	# Uploaded model - Developed by: baconnier - License: apache-2.0 - Finetuned from model : cognitivecomputations/dolphin-2.9-llama3-8b 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)	{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "cognitivecomputations/dolphin-2.9-llama3-8b"}	baconnier/finance_dolphin_orpo_llama3_8B_r64_51K_lora	null	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:cognitivecomputations/dolphin-2.9-llama3-8b", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:37:30+00:00
text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # digital-TA This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.0 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "mit", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "openai-community/gpt2-large", "model-index": [{"name": "digital-TA", "results": []}]}	hibana2077/digital-TA	null	[ "transformers", "safetensors", "gpt2", "text-generation", "trl", "sft", "generated_from_trainer", "base_model:openai-community/gpt2-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:37:38+00:00
text-classification	transformers	# Model Trained Using AutoTrain - Problem type: Text Classification ## Validation Metrics loss: 0.7705633640289307 f1_macro: 0.6039453586924824 f1_micro: 0.6606793526587231 f1_weighted: 0.6394700306337707 precision_macro: 0.6728888959508482 precision_micro: 0.6606793526587231 precision_weighted: 0.6657165229697813 recall_macro: 0.5855248110079919 recall_micro: 0.6606793526587231 recall_weighted: 0.6606793526587231 accuracy: 0.6606793526587231	{"tags": ["autotrain", "text-classification"], "datasets": ["autotrain-p28fn-qmpx8/autotrain-data"], "widget": [{"text": "I love AutoTrain"}]}	Hrishith123/Telugu-Distilbert-base-Multilingual-uncased	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "autotrain", "dataset:autotrain-p28fn-qmpx8/autotrain-data", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:39:56+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	golf2248/3zan4av	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:41:21+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	golf2248/5os02py	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:41:58+00:00
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	golf2248/kuv7ev0	null	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-28T08:42:33+00:00
null	null		{"license": "openrail"}	avawancitte/Mihari_oyama_rvc	null	[ "license:openrail", "region:us" ]	null	2024-04-28T08:43:02+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/hhqx4p7	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:45:06+00:00
text-generation	transformers	## base model : - google/gemma-7b ## dataset : - ayoubkirouane/Small-Instruct-Alpaca_Format - yahma/alpaca-cleaned ## get started : ``` # Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ayoubkirouane/Gemma_7b_Alpaca") ``` or : ``` # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ayoubkirouane/Gemma_7b_Alpaca") model = AutoModelForCausalLM.from_pretrained("ayoubkirouane/Gemma_7b_Alpaca") ```	{"library_name": "transformers", "tags": ["unsloth", "trl", "sft"], "datasets": ["yahma/alpaca-cleaned", "ayoubkirouane/Small-Instruct-Alpaca_Format"]}	ayoubkirouane/Gemma7b-instruct-Alpaca	null	[ "transformers", "pytorch", "gemma", "text-generation", "unsloth", "trl", "sft", "dataset:yahma/alpaca-cleaned", "dataset:ayoubkirouane/Small-Instruct-Alpaca_Format", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:45:50+00:00
text-generation	transformers	# TinyMoE-DopeykarasuMoe-xdareties2 TinyMoE-DopeykarasuMoe-xdareties2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [aipib/Dopey-karasu-MoE3](https://huggingface.co/aipib/Dopey-karasu-MoE3) * [AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE](https://huggingface.co/AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE) ## 🧩 Configuration ```yaml slices: - sources: - layer_range: [0, 22] model: aipib/Dopey-karasu-MoE3 parameters: density: [1, 0.7, 0.1] weight: 1.0 - layer_range: [0, 22] model: AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE parameters: density: 0.53 weight: - filter: mlp value: 0.5 - value: 0 merge_method: dare_ties base_model: aipib/Dopey-karasu-MoE3 parameters: normalize: true int8_mask: true dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "aipib/TinyMoE-DopeykarasuMoe-xdareties2" 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"]) ```	{"tags": ["merge", "mergekit", "lazymergekit", "aipib/Dopey-karasu-MoE3", "AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE"], "base_model": ["aipib/Dopey-karasu-MoE3", "AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE"]}	aipib/TinyMoE-DopeykarasuMoe-xdareties2	null	[ "transformers", "safetensors", "mixtral", "text-generation", "merge", "mergekit", "lazymergekit", "aipib/Dopey-karasu-MoE3", "AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE", "conversational", "base_model:aipib/Dopey-karasu-MoE3", "base_model:AIChenKai/TinyLlama-1.1B-Chat-v1.0-x2-MoE", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-28T08:47:40+00:00

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.