Split (1)

train · 845k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-27 00:42:13	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 499 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-27 00:40:00	card stringlengths 11 1.01M
Dev2410/Gemma_7B_cr2	Dev2410	2024-02-29T08:17:44Z	4	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T08:06:57Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
betajuned/gpt2-indonesian-unila	betajuned	2024-02-29T08:16:48Z	0	0	null	[ "safetensors", "autotrain", "text-generation", "conversational", "license:other", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T08:16:45Z	--- tags: - autotrain - text-generation widget: - text: "I love AutoTrain because " license: other --- # Model Trained Using AutoTrain This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain). # Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_path = "PATH_TO_THIS_REPO" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() # Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) # Model response: "Hello! How can I assist you today?" print(response) ```
saadrasheeddev/lora-flan-t5-cv-chatbot	saadrasheeddev	2024-02-29T08:12:53Z	106	0	transformers	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-28T09:57:44Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
KVNAditya/drl__u4__p_ple_v0	KVNAditya	2024-02-29T08:12:17Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2024-02-29T08:12:14Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: drl__u4__p_ple_v0 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 16.70 +/- 19.48 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
kevin1313/code-search-net-tokenizer	kevin1313	2024-02-29T08:09:38Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T08:09:37Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
yechenzhi1/Reinforce-PixelCopter	yechenzhi1	2024-02-29T08:04:29Z	0	0	null	[ "Pixelcopter-PLE-v0", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	reinforcement-learning	2024-02-29T08:04:26Z	--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-PixelCopter results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 27.20 +/- 16.00 name: mean_reward verified: false --- # Reinforce Agent playing Pixelcopter-PLE-v0 This is a trained model of a Reinforce agent playing Pixelcopter-PLE-v0 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
kumatomo/BasicGCN	kumatomo	2024-02-29T08:03:55Z	1	0	pytorch_geometric	[ "pytorch_geometric", "pretrain", "graph-machine-learning", "en", "dataset:QM9", "arxiv:1910.09700", "license:mit", "region:us" ]	null	2024-02-29T07:20:14Z	--- language: en license: mit library_name: pytorch_geometric tags: - graph-machine-learning datasets: QM9 model_name: GCN --- # 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] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): en - License: mit - 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 Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [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 Data 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]
Dohui/embedding_workshop	Dohui	2024-02-29T08:01:36Z	196	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "fill-mask", "generated_from_trainer", "base_model:google-bert/bert-base-uncased", "base_model:finetune:google-bert/bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-02-29T07:58:28Z	--- license: apache-2.0 base_model: bert-base-uncased tags: - generated_from_trainer model-index: - name: embedding_workshop results: [] --- <!-- 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. --> # embedding_workshop This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) 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: 2e-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: 1 ### Training results ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
nilq/lua-mistral-1L-mini	nilq	2024-02-29T07:56:17Z	121	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "generated_from_trainer", "dataset:nilq/small-lua-stack", "model-index", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-28T19:24:11Z	--- tags: - generated_from_trainer datasets: - nilq/small-lua-stack metrics: - accuracy model-index: - name: lua-mistral-1L-mini results: - task: name: Causal Language Modeling type: text-generation dataset: name: nilq/small-lua-stack type: nilq/small-lua-stack metrics: - name: Accuracy type: accuracy value: 0.4208221928842605 --- # lua-mistral-1L-mini This model is a mini single-layer Mistral model pre-trained on on the `nilq/small-lua-stack` dataset. It achieves the following results on the evaluation set: - Loss: 3.0245 - Accuracy: 0.4208 ## Model description This model might contain some very simple model of Lua. ## Intended uses & limitations Let's see if we can find some interesting stuff inside this model. ## Training and evaluation data Trained on the Lua subset of The Stack. ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0006 - train_batch_size: 64 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 3.0 ### Training results - Loss: 3.016 ### Framework versions - Transformers 4.38.1 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
Chattiori/PersikaFurry	Chattiori	2024-02-29T07:51:19Z	0	2	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2024-01-16T08:57:22Z	--- license: creativeml-openrail-m ---
AyanAnsar/llama2-qlora-finetuned-slimorca-1k	AyanAnsar	2024-02-29T07:50:40Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T07:42:16Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
tomaszki/gemma-9	tomaszki	2024-02-29T07:47:41Z	114	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T07:40:08Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo-6.5bpw-exl2	CorticalStack	2024-02-29T07:47:35Z	6	1	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T07:42:09Z	--- license: apache-2.0 --- <img src="neurotic-crown-clown-tak-stack.png" alt="Neurotic crown clown tak stack logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/> # CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo An EXL2 6.5bpw quantised version of [CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo](https://huggingface.co/CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo). An incomplete list of clients and libraries that are known to support EXL2: * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [exllamav2](https://github.com/turboderp/exllamav2), an inference library for running local LLMs on modern consumer GPUs.
Reshphil/lab2_efficient	Reshphil	2024-02-29T07:46:44Z	103	0	transformers	[ "transformers", "safetensors", "marian", "text2text-generation", "generated_from_trainer", "dataset:kde4", "base_model:Helsinki-NLP/opus-mt-en-fr", "base_model:finetune:Helsinki-NLP/opus-mt-en-fr", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-29T07:46:25Z	--- license: apache-2.0 base_model: Helsinki-NLP/opus-mt-en-fr tags: - generated_from_trainer datasets: - kde4 metrics: - bleu model-index: - name: marian-finetuned-kde4-en-to-fr results: - task: name: Sequence-to-sequence Language Modeling type: text2text-generation dataset: name: kde4 type: kde4 config: en-fr split: train args: en-fr metrics: - name: Bleu type: bleu value: 50.03285120906795 --- <!-- 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. --> # marian-finetuned-kde4-en-to-fr This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset. It achieves the following results on the evaluation set: - Loss: 0.9574 - Bleu: 50.0329 ## 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: 32 - eval_batch_size: 64 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 2 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
Yukino666/a2c-PandaReachDense-v3	Yukino666	2024-02-29T07:44:44Z	0	0	stable-baselines3	[ "stable-baselines3", "PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-02-29T07:36:22Z	--- 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: -0.21 +/- 0.08 name: mean_reward verified: false --- # 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 ... ```
Dev2410/Gemma_adapter_cr2	Dev2410	2024-02-29T07:42:26Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T07:40:03Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ahmedrizwan239/NativeSQL-with-schema	ahmedrizwan239	2024-02-29T07:37:36Z	107	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "en", "arxiv:1910.09700", "license:cc-by-sa-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-28T09:07:33Z	--- language: en widget: - text: >- tables: student(id,name, age). question: how many students with name ahmed and age less than 25 license: cc-by-sa-4.0 pipeline_tag: text2text-generation inference: parameters: max_length: 512 num_beams: 10 top_k: 10 --- # 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]
renyiyu/llama-2-7b-ppo-lora-v0.1	renyiyu	2024-02-29T07:35:49Z	0	0	null	[ "pytorch", "safetensors", "base_model:meta-llama/Llama-2-7b-hf", "base_model:finetune:meta-llama/Llama-2-7b-hf", "region:us" ]	null	2024-02-23T10:26:56Z	--- base_model: meta-llama/Llama-2-7b-hf --- # Model Details - SFT based on [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) with merged alpaca datasets - DPO: trained on top of SFT model as LoRa Adapter, with merged [hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf) data - PPO: trained on top of dpo model and reward model, with multi-adapters, with [PKU-SafeRLHF](https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF) data for futher RLHF - Trained with Deepspeed ZeRO-1 + TRL + QLoRA + Flash-Attntion 2 ## Model and Training Details - Finetuned from model: [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) - Dataset: - SFT (mixed train): - [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned) - [vicgalle/alpaca-gpt4](https://huggingface.co/datasets/vicgalle/alpaca-gpt4) - DPO (mixed train): - [Anthropic/hh-rlhf](https://huggingface.co/datasets/Anthropic/hh-rlhf) - [Unified-Language-Model-Alignment/Anthropic_HH_Golden](https://huggingface.co/datasets/Unified-Language-Model-Alignment/Anthropic_HH_Golden) - PPO: - [PKU-Alignment/PKU-SafeRLHF-10K](https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF-10K) - [PKU-Alignment/PKU-SafeRLHF-30K](https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF-30K) - [PKU-Alignment/PKU-SafeRLHF](https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF) ### Training Results ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b1dd2a855f6b5fe621bc0e/miik5Tb6A8G6sDTlnQA-V.png) ### Evaluation The reward score and toxicity scores are computed and compared with [PKU-Alignment/PKU-SafeRLHF-30K](https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF-30K) data on SFT/DPO/PPO models \| Model \| Toxicity \| Reward \| \| ----- \|:--------:\|:--------:\| \| SFT_v0.1 \| 0.0698 \| -0.2828 \| \| DPO_v0.1 \| 0.0356 \| -0.2633 \| \| PPO_v0.1 \| 0.0321 \| 0.38 \| ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65b1dd2a855f6b5fe621bc0e/m-k6kUuIJVTkYM2l3uBPd.png) ### Compute Infrastructure The model is trained using 8 * RTX-3090-24GB/A100-PCIE-40GB ### Inference ```python from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, trust_remote_code=True,) tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True,) tokenizer.pad_token = tokenizer.eos_token tokenizer.eos_token = DEFINE_EOS_TOKEN model.config.eos_token = DEFINE_EOS_TOKEN model.config.eos_token_id = tokenizer.eos_token_id def format_prompt(question): return f"###Question: {question}\n###Answer: " instruction = "Your text here" input = format_prompt(instruction) inputs = tokenizer(input, return_tensors='pt') output = model.generate(inputs['input_ids'], max_new_tokens=512, do_sample=False, top_p=1) output = tokenizer.decode(output[0], skip_special_tokens=True) print(output) ``` ## Model Card Authors Yiyu (Michael) Ren ## Model Card Contact Email: [email protected] ### Framework versions - PEFT 0.8.2
vignesh-spericorn/test-dialogue-summarization	vignesh-spericorn	2024-02-29T07:35:23Z	103	0	transformers	[ "transformers", "tensorboard", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-base", "base_model:finetune:facebook/bart-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-29T07:35:04Z	--- license: apache-2.0 base_model: facebook/bart-base tags: - generated_from_trainer metrics: - rouge model-index: - name: test-dialogue-summarization results: [] --- <!-- 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. --> # test-dialogue-summarization 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: 1.8387 - Rouge1: 48.1775 - Rouge2: 24.5925 - Rougel: 40.3237 - Rougelsum: 43.9647 - Gen Len: 18.4707 ## 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: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:-------:\| \| 1.8408 \| 1.0 \| 1841 \| 1.5902 \| 47.4895 \| 24.7763 \| 40.0228 \| 44.4895 \| 18.5159 \| \| 1.5348 \| 2.0 \| 3683 \| 1.5498 \| 48.0242 \| 24.8392 \| 40.559 \| 44.2542 \| 17.6015 \| \| 1.3076 \| 3.0 \| 5524 \| 1.5561 \| 48.5695 \| 25.9259 \| 41.4698 \| 44.6406 \| 17.4658 \| \| 1.1286 \| 4.0 \| 7366 \| 1.5796 \| 48.5079 \| 25.1521 \| 40.8084 \| 44.6149 \| 18.4364 \| \| 0.9956 \| 5.0 \| 9207 \| 1.6134 \| 49.1351 \| 25.6367 \| 41.3139 \| 45.0814 \| 18.3313 \| \| 0.8668 \| 6.0 \| 11049 \| 1.6679 \| 49.002 \| 25.4589 \| 41.1276 \| 44.787 \| 18.4853 \| \| 0.7696 \| 7.0 \| 12890 \| 1.7327 \| 48.1978 \| 25.0238 \| 40.6671 \| 44.3866 \| 18.3374 \| \| 0.69 \| 8.0 \| 14732 \| 1.7603 \| 48.7522 \| 25.0831 \| 40.8193 \| 44.4452 \| 18.4597 \| \| 0.6175 \| 9.0 \| 16573 \| 1.8092 \| 48.2747 \| 24.8563 \| 40.3027 \| 44.1975 \| 18.3729 \| \| 0.5701 \| 10.0 \| 18410 \| 1.8387 \| 48.1775 \| 24.5925 \| 40.3237 \| 43.9647 \| 18.4707 \| ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
idn123009/ppo-Huggy	idn123009	2024-02-29T07:30:50Z	2	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	reinforcement-learning	2024-02-29T07:15:42Z	--- library_name: ml-agents tags: - Huggy - deep-reinforcement-learning - reinforcement-learning - ML-Agents-Huggy --- # 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: idn123009/ppo-Huggy 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
uni-zhuan/Taxi-v3	uni-zhuan	2024-02-29T07:29:11Z	0	0	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2024-02-29T07:29:09Z	--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.56 +/- 2.71 name: mean_reward verified: false --- # Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="uni-zhuan/Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
vignesh-spericorn/t5-small-samsum	vignesh-spericorn	2024-02-29T07:22:33Z	104	0	transformers	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:google-t5/t5-small", "base_model:finetune:google-t5/t5-small", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-29T07:22:21Z	--- license: apache-2.0 base_model: google-t5/t5-small tags: - generated_from_trainer metrics: - rouge model-index: - name: t5-small-samsum results: [] --- <!-- 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. --> # t5-small-samsum This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.6707 - Rouge1: 43.8206 - Rouge2: 19.9652 - Rougel: 36.0416 - Rougelsum: 40.0887 - Gen Len: 17.0305 ## 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: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:-------:\| \| 2.016 \| 1.0 \| 1842 \| 1.7872 \| 40.6656 \| 17.0772 \| 33.6487 \| 37.3124 \| 16.9829 \| \| 1.8798 \| 2.0 \| 3684 \| 1.7375 \| 42.1059 \| 18.6064 \| 35.0368 \| 38.6458 \| 16.7045 \| \| 1.8219 \| 3.0 \| 5526 \| 1.7062 \| 43.2636 \| 19.4321 \| 35.6415 \| 39.5613 \| 16.8266 \| \| 1.77 \| 4.0 \| 7368 \| 1.6990 \| 43.2211 \| 19.5021 \| 35.5155 \| 39.6933 \| 17.1905 \| \| 1.7408 \| 5.0 \| 9210 \| 1.6878 \| 43.9084 \| 19.8501 \| 36.2255 \| 40.2666 \| 16.7766 \| \| 1.7113 \| 6.0 \| 11052 \| 1.6816 \| 44.0573 \| 20.1359 \| 36.426 \| 40.4933 \| 16.9829 \| \| 1.692 \| 7.0 \| 12894 \| 1.6771 \| 43.9234 \| 19.9018 \| 36.0759 \| 40.1654 \| 16.9158 \| \| 1.6771 \| 8.0 \| 14736 \| 1.6723 \| 43.5824 \| 19.8023 \| 35.9709 \| 39.963 \| 16.9731 \| \| 1.6604 \| 9.0 \| 16578 \| 1.6718 \| 43.8502 \| 19.9263 \| 36.157 \| 40.1653 \| 17.0134 \| \| 1.6575 \| 10.0 \| 18420 \| 1.6707 \| 43.8206 \| 19.9652 \| 36.0416 \| 40.0887 \| 17.0305 \| ### Framework versions - Transformers 4.38.1 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
holyofferings/roberta-finetuned-subjqa-movies_2	holyofferings	2024-02-29T07:21:33Z	121	0	transformers	[ "transformers", "tensorboard", "safetensors", "roberta", "question-answering", "generated_from_trainer", "base_model:deepset/roberta-base-squad2", "base_model:finetune:deepset/roberta-base-squad2", "license:cc-by-4.0", "endpoints_compatible", "region:us" ]	question-answering	2024-02-29T07:00:56Z	--- license: cc-by-4.0 base_model: deepset/roberta-base-squad2 tags: - generated_from_trainer model-index: - name: roberta-finetuned-subjqa-movies_2 results: [] --- <!-- 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 [deepset/roberta-base-squad2](https://huggingface.co/deepset/roberta-base-squad2) 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: 2e-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: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.38.1 - Pytorch 2.1.2 - Datasets 2.1.0 - Tokenizers 0.15.2
KVNAditya/drl__u8_2__dhgs	KVNAditya	2024-02-29T07:20:33Z	0	0	sample-factory	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-02-29T07:10:08Z	--- library_name: sample-factory tags: - deep-reinforcement-learning - reinforcement-learning - sample-factory model-index: - name: APPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: doom_health_gathering_supreme type: doom_health_gathering_supreme metrics: - type: mean_reward value: 11.02 +/- 5.78 name: mean_reward verified: false --- A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r KVNAditya/drl__u8_2__dhgs ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=drl__u8_2__dhgs ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=drl__u8_2__dhgs --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
ultimecia/xlm-roberta-base-finetuned-panx-all	ultimecia	2024-02-29T07:19:23Z	104	0	transformers	[ "transformers", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-02-29T07:01:24Z	--- license: mit base_model: xlm-roberta-base tags: - generated_from_trainer metrics: - f1 model-index: - name: xlm-roberta-base-finetuned-panx-all results: [] --- <!-- 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-all This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1698 - F1: 0.8482 ## 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: 96 - eval_batch_size: 96 - 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 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| No log \| 1.0 \| 209 \| 0.1982 \| 0.8129 \| \| No log \| 2.0 \| 418 \| 0.1723 \| 0.8407 \| \| No log \| 3.0 \| 627 \| 0.1698 \| 0.8482 \| ### Framework versions - Transformers 4.38.1 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
DouglasPontes/2020-Q4-50p-filtered-random-prog_from_Q3	DouglasPontes	2024-02-29T07:15:09Z	1	0	transformers	[ "transformers", "pytorch", "roberta", "fill-mask", "generated_from_trainer", "base_model:DouglasPontes/2020-Q3-50p-filtered-random", "base_model:finetune:DouglasPontes/2020-Q3-50p-filtered-random", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-02-26T14:36:40Z	--- license: mit base_model: DouglasPontes/2020-Q3-50p-filtered-random tags: - generated_from_trainer model-index: - name: 2020-Q4-50p-filtered-random-prog_from_Q3 results: [] --- <!-- 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. --> # 2020-Q4-50p-filtered-random-prog_from_Q3 This model is a fine-tuned version of [DouglasPontes/2020-Q3-50p-filtered-random](https://huggingface.co/DouglasPontes/2020-Q3-50p-filtered-random) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.2730 ## 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: 4.1e-07 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 2400000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-------:\|:---------------:\| \| No log \| 0.03 \| 8000 \| 2.3816 \| \| 2.5089 \| 0.07 \| 16000 \| 2.3647 \| \| 2.5089 \| 0.1 \| 24000 \| 2.3552 \| \| 2.4989 \| 0.13 \| 32000 \| 2.3528 \| \| 2.4989 \| 0.17 \| 40000 \| 2.3486 \| \| 2.4836 \| 0.2 \| 48000 \| 2.3463 \| \| 2.4836 \| 0.24 \| 56000 \| 2.3411 \| \| 2.4904 \| 0.27 \| 64000 \| 2.3394 \| \| 2.4904 \| 0.3 \| 72000 \| 2.3350 \| \| 2.4733 \| 0.34 \| 80000 \| 2.3309 \| \| 2.4733 \| 0.37 \| 88000 \| 2.3289 \| \| 2.4675 \| 0.4 \| 96000 \| 2.3381 \| \| 2.4675 \| 0.44 \| 104000 \| 2.3317 \| \| 2.4762 \| 0.47 \| 112000 \| 2.3218 \| \| 2.4762 \| 0.51 \| 120000 \| 2.3267 \| \| 2.4616 \| 0.54 \| 128000 \| 2.3241 \| \| 2.4616 \| 0.57 \| 136000 \| 2.3281 \| \| 2.4601 \| 0.61 \| 144000 \| 2.3152 \| \| 2.4601 \| 0.64 \| 152000 \| 2.3243 \| \| 2.4563 \| 0.67 \| 160000 \| 2.3202 \| \| 2.4563 \| 0.71 \| 168000 \| 2.3193 \| \| 2.459 \| 0.74 \| 176000 \| 2.3182 \| \| 2.459 \| 0.77 \| 184000 \| 2.3247 \| \| 2.4639 \| 0.81 \| 192000 \| 2.3201 \| \| 2.4639 \| 0.84 \| 200000 \| 2.3243 \| \| 2.4561 \| 0.88 \| 208000 \| 2.3218 \| \| 2.4561 \| 0.91 \| 216000 \| 2.3137 \| \| 2.4556 \| 0.94 \| 224000 \| 2.3180 \| \| 2.4556 \| 0.98 \| 232000 \| 2.3147 \| \| 2.4573 \| 1.01 \| 240000 \| 2.3100 \| \| 2.4573 \| 1.04 \| 248000 \| 2.3118 \| \| 2.4516 \| 1.08 \| 256000 \| 2.3158 \| \| 2.4516 \| 1.11 \| 264000 \| 2.3133 \| \| 2.4561 \| 1.15 \| 272000 \| 2.3065 \| \| 2.4561 \| 1.18 \| 280000 \| 2.3183 \| \| 2.4476 \| 1.21 \| 288000 \| 2.3106 \| \| 2.4476 \| 1.25 \| 296000 \| 2.3131 \| \| 2.4503 \| 1.28 \| 304000 \| 2.3104 \| \| 2.4503 \| 1.31 \| 312000 \| 2.3101 \| \| 2.4495 \| 1.35 \| 320000 \| 2.3086 \| \| 2.4495 \| 1.38 \| 328000 \| 2.3057 \| \| 2.4534 \| 1.41 \| 336000 \| 2.3086 \| \| 2.4534 \| 1.45 \| 344000 \| 2.3093 \| \| 2.4486 \| 1.48 \| 352000 \| 2.3018 \| \| 2.4486 \| 1.52 \| 360000 \| 2.3060 \| \| 2.4457 \| 1.55 \| 368000 \| 2.3083 \| \| 2.4457 \| 1.58 \| 376000 \| 2.3110 \| \| 2.4443 \| 1.62 \| 384000 \| 2.2975 \| \| 2.4443 \| 1.65 \| 392000 \| 2.3009 \| \| 2.4405 \| 1.68 \| 400000 \| 2.3067 \| \| 2.4405 \| 1.72 \| 408000 \| 2.3027 \| \| 2.4531 \| 1.75 \| 416000 \| 2.3050 \| \| 2.4531 \| 1.79 \| 424000 \| 2.3026 \| \| 2.4539 \| 1.82 \| 432000 \| 2.2929 \| \| 2.4539 \| 1.85 \| 440000 \| 2.3051 \| \| 2.4499 \| 1.89 \| 448000 \| 2.3035 \| \| 2.4499 \| 1.92 \| 456000 \| 2.3011 \| \| 2.4401 \| 1.95 \| 464000 \| 2.2920 \| \| 2.4401 \| 1.99 \| 472000 \| 2.2999 \| \| 2.4401 \| 2.02 \| 480000 \| 2.3034 \| \| 2.4401 \| 2.05 \| 488000 \| 2.3021 \| \| 2.4433 \| 2.09 \| 496000 \| 2.3102 \| \| 2.4433 \| 2.12 \| 504000 \| 2.2985 \| \| 2.4445 \| 2.16 \| 512000 \| 2.3018 \| \| 2.4445 \| 2.19 \| 520000 \| 2.2996 \| \| 2.4379 \| 2.22 \| 528000 \| 2.3006 \| \| 2.4379 \| 2.26 \| 536000 \| 2.2970 \| \| 2.4454 \| 2.29 \| 544000 \| 2.3014 \| \| 2.4454 \| 2.32 \| 552000 \| 2.2992 \| \| 2.4457 \| 2.36 \| 560000 \| 2.2962 \| \| 2.4457 \| 2.39 \| 568000 \| 2.3009 \| \| 2.4354 \| 2.43 \| 576000 \| 2.2960 \| \| 2.4354 \| 2.46 \| 584000 \| 2.3008 \| \| 2.4361 \| 2.49 \| 592000 \| 2.2898 \| \| 2.4361 \| 2.53 \| 600000 \| 2.3060 \| \| 2.4377 \| 2.56 \| 608000 \| 2.2990 \| \| 2.4377 \| 2.59 \| 616000 \| 2.2989 \| \| 2.4416 \| 2.63 \| 624000 \| 2.2969 \| \| 2.4416 \| 2.66 \| 632000 \| 2.2933 \| \| 2.434 \| 2.69 \| 640000 \| 2.2998 \| \| 2.434 \| 2.73 \| 648000 \| 2.2948 \| \| 2.433 \| 2.76 \| 656000 \| 2.2892 \| \| 2.433 \| 2.8 \| 664000 \| 2.2929 \| \| 2.44 \| 2.83 \| 672000 \| 2.2973 \| \| 2.44 \| 2.86 \| 680000 \| 2.2926 \| \| 2.4291 \| 2.9 \| 688000 \| 2.2990 \| \| 2.4291 \| 2.93 \| 696000 \| 2.2937 \| \| 2.4336 \| 2.96 \| 704000 \| 2.2894 \| \| 2.4336 \| 3.0 \| 712000 \| 2.2958 \| \| 2.439 \| 3.03 \| 720000 \| 2.2956 \| \| 2.439 \| 3.07 \| 728000 \| 2.2928 \| \| 2.4405 \| 3.1 \| 736000 \| 2.2956 \| \| 2.4405 \| 3.13 \| 744000 \| 2.2905 \| \| 2.4332 \| 3.17 \| 752000 \| 2.2921 \| \| 2.4332 \| 3.2 \| 760000 \| 2.2907 \| \| 2.4353 \| 3.23 \| 768000 \| 2.2879 \| \| 2.4353 \| 3.27 \| 776000 \| 2.2929 \| \| 2.4273 \| 3.3 \| 784000 \| 2.2953 \| \| 2.4273 \| 3.33 \| 792000 \| 2.2917 \| \| 2.4233 \| 3.37 \| 800000 \| 2.2947 \| \| 2.4233 \| 3.4 \| 808000 \| 2.2943 \| \| 2.4324 \| 3.44 \| 816000 \| 2.2940 \| \| 2.4324 \| 3.47 \| 824000 \| 2.2911 \| \| 2.4461 \| 3.5 \| 832000 \| 2.2920 \| \| 2.4461 \| 3.54 \| 840000 \| 2.2911 \| \| 2.4267 \| 3.57 \| 848000 \| 2.2940 \| \| 2.4267 \| 3.6 \| 856000 \| 2.2890 \| \| 2.4313 \| 3.64 \| 864000 \| 2.2913 \| \| 2.4313 \| 3.67 \| 872000 \| 2.2967 \| \| 2.4388 \| 3.71 \| 880000 \| 2.2907 \| \| 2.4388 \| 3.74 \| 888000 \| 2.2952 \| \| 2.4326 \| 3.77 \| 896000 \| 2.2873 \| \| 2.4326 \| 3.81 \| 904000 \| 2.2871 \| \| 2.4312 \| 3.84 \| 912000 \| 2.2880 \| \| 2.4312 \| 3.87 \| 920000 \| 2.2941 \| \| 2.4398 \| 3.91 \| 928000 \| 2.2925 \| \| 2.4398 \| 3.94 \| 936000 \| 2.2965 \| \| 2.441 \| 3.97 \| 944000 \| 2.2890 \| \| 2.441 \| 4.01 \| 952000 \| 2.2946 \| \| 2.4345 \| 4.04 \| 960000 \| 2.2910 \| \| 2.4345 \| 4.08 \| 968000 \| 2.2792 \| \| 2.4332 \| 4.11 \| 976000 \| 2.2856 \| \| 2.4332 \| 4.14 \| 984000 \| 2.2879 \| \| 2.4375 \| 4.18 \| 992000 \| 2.2861 \| \| 2.4375 \| 4.21 \| 1000000 \| 2.2892 \| \| 2.4282 \| 4.24 \| 1008000 \| 2.2894 \| \| 2.4282 \| 4.28 \| 1016000 \| 2.2902 \| \| 2.4231 \| 4.31 \| 1024000 \| 2.2830 \| \| 2.4231 \| 4.35 \| 1032000 \| 2.2948 \| \| 2.4299 \| 4.38 \| 1040000 \| 2.2915 \| \| 2.4299 \| 4.41 \| 1048000 \| 2.2922 \| \| 2.4353 \| 4.45 \| 1056000 \| 2.2876 \| \| 2.4353 \| 4.48 \| 1064000 \| 2.2893 \| \| 2.4308 \| 4.51 \| 1072000 \| 2.2920 \| \| 2.4308 \| 4.55 \| 1080000 \| 2.2860 \| \| 2.4358 \| 4.58 \| 1088000 \| 2.2907 \| \| 2.4358 \| 4.61 \| 1096000 \| 2.2808 \| \| 2.4341 \| 4.65 \| 1104000 \| 2.2902 \| \| 2.4341 \| 4.68 \| 1112000 \| 2.2815 \| \| 2.4315 \| 4.72 \| 1120000 \| 2.2961 \| \| 2.4315 \| 4.75 \| 1128000 \| 2.2885 \| \| 2.434 \| 4.78 \| 1136000 \| 2.2917 \| \| 2.434 \| 4.82 \| 1144000 \| 2.2851 \| \| 2.4324 \| 4.85 \| 1152000 \| 2.2837 \| \| 2.4324 \| 4.88 \| 1160000 \| 2.2883 \| \| 2.4297 \| 4.92 \| 1168000 \| 2.2824 \| \| 2.4297 \| 4.95 \| 1176000 \| 2.2832 \| \| 2.436 \| 4.99 \| 1184000 \| 2.2865 \| \| 2.436 \| 5.02 \| 1192000 \| 2.2816 \| \| 2.4329 \| 5.05 \| 1200000 \| 2.2862 \| \| 2.4329 \| 5.09 \| 1208000 \| 2.2847 \| \| 2.4276 \| 5.12 \| 1216000 \| 2.2951 \| \| 2.4276 \| 5.15 \| 1224000 \| 2.2980 \| \| 2.4362 \| 5.19 \| 1232000 \| 2.2889 \| \| 2.4362 \| 5.22 \| 1240000 \| 2.2914 \| \| 2.4309 \| 5.25 \| 1248000 \| 2.2915 \| \| 2.4309 \| 5.29 \| 1256000 \| 2.2822 \| \| 2.4414 \| 5.32 \| 1264000 \| 2.2871 \| \| 2.4414 \| 5.36 \| 1272000 \| 2.2890 \| \| 2.4241 \| 5.39 \| 1280000 \| 2.2844 \| \| 2.4241 \| 5.42 \| 1288000 \| 2.2812 \| \| 2.4251 \| 5.46 \| 1296000 \| 2.2874 \| \| 2.4251 \| 5.49 \| 1304000 \| 2.2846 \| \| 2.4318 \| 5.52 \| 1312000 \| 2.2831 \| \| 2.4318 \| 5.56 \| 1320000 \| 2.2895 \| \| 2.4247 \| 5.59 \| 1328000 \| 2.2796 \| \| 2.4247 \| 5.63 \| 1336000 \| 2.2834 \| \| 2.4305 \| 5.66 \| 1344000 \| 2.2811 \| \| 2.4305 \| 5.69 \| 1352000 \| 2.2922 \| \| 2.4336 \| 5.73 \| 1360000 \| 2.2830 \| \| 2.4336 \| 5.76 \| 1368000 \| 2.2904 \| \| 2.428 \| 5.79 \| 1376000 \| 2.2843 \| \| 2.428 \| 5.83 \| 1384000 \| 2.2804 \| \| 2.4254 \| 5.86 \| 1392000 \| 2.2852 \| \| 2.4254 \| 5.89 \| 1400000 \| 2.2858 \| \| 2.4287 \| 5.93 \| 1408000 \| 2.2922 \| \| 2.4287 \| 5.96 \| 1416000 \| 2.2847 \| \| 2.4291 \| 6.0 \| 1424000 \| 2.2856 \| \| 2.4291 \| 6.03 \| 1432000 \| 2.2876 \| \| 2.4289 \| 6.06 \| 1440000 \| 2.2822 \| \| 2.4289 \| 6.1 \| 1448000 \| 2.2787 \| \| 2.4272 \| 6.13 \| 1456000 \| 2.2811 \| \| 2.4272 \| 6.16 \| 1464000 \| 2.2853 \| \| 2.4267 \| 6.2 \| 1472000 \| 2.2818 \| \| 2.4267 \| 6.23 \| 1480000 \| 2.2765 \| \| 2.4237 \| 6.27 \| 1488000 \| 2.2791 \| \| 2.4237 \| 6.3 \| 1496000 \| 2.2768 \| \| 2.4277 \| 6.33 \| 1504000 \| 2.2866 \| \| 2.4277 \| 6.37 \| 1512000 \| 2.2821 \| \| 2.4316 \| 6.4 \| 1520000 \| 2.2856 \| \| 2.4316 \| 6.43 \| 1528000 \| 2.2820 \| \| 2.4222 \| 6.47 \| 1536000 \| 2.2891 \| \| 2.4222 \| 6.5 \| 1544000 \| 2.2803 \| \| 2.426 \| 6.53 \| 1552000 \| 2.2797 \| \| 2.426 \| 6.57 \| 1560000 \| 2.2844 \| \| 2.422 \| 6.6 \| 1568000 \| 2.2872 \| \| 2.422 \| 6.64 \| 1576000 \| 2.2904 \| \| 2.4323 \| 6.67 \| 1584000 \| 2.2797 \| \| 2.4323 \| 6.7 \| 1592000 \| 2.2757 \| \| 2.4315 \| 6.74 \| 1600000 \| 2.2874 \| \| 2.4315 \| 6.77 \| 1608000 \| 2.2763 \| \| 2.421 \| 6.8 \| 1616000 \| 2.2857 \| \| 2.421 \| 6.84 \| 1624000 \| 2.2804 \| \| 2.4299 \| 6.87 \| 1632000 \| 2.2825 \| \| 2.4299 \| 6.91 \| 1640000 \| 2.2819 \| \| 2.4289 \| 6.94 \| 1648000 \| 2.2824 \| \| 2.4289 \| 6.97 \| 1656000 \| 2.2821 \| \| 2.4257 \| 7.01 \| 1664000 \| 2.2802 \| \| 2.4257 \| 7.04 \| 1672000 \| 2.2760 \| \| 2.4227 \| 7.07 \| 1680000 \| 2.2810 \| \| 2.4227 \| 7.11 \| 1688000 \| 2.2777 \| \| 2.4287 \| 7.14 \| 1696000 \| 2.2772 \| \| 2.4287 \| 7.17 \| 1704000 \| 2.2786 \| \| 2.4227 \| 7.21 \| 1712000 \| 2.2859 \| \| 2.4227 \| 7.24 \| 1720000 \| 2.2862 \| \| 2.4262 \| 7.28 \| 1728000 \| 2.2789 \| \| 2.4262 \| 7.31 \| 1736000 \| 2.2848 \| \| 2.4263 \| 7.34 \| 1744000 \| 2.2754 \| \| 2.4263 \| 7.38 \| 1752000 \| 2.2778 \| \| 2.4246 \| 7.41 \| 1760000 \| 2.2735 \| \| 2.4246 \| 7.44 \| 1768000 \| 2.2827 \| \| 2.4147 \| 7.48 \| 1776000 \| 2.2850 \| \| 2.4147 \| 7.51 \| 1784000 \| 2.2821 \| \| 2.4288 \| 7.55 \| 1792000 \| 2.2803 \| \| 2.4288 \| 7.58 \| 1800000 \| 2.2760 \| \| 2.4231 \| 7.61 \| 1808000 \| 2.2749 \| \| 2.4231 \| 7.65 \| 1816000 \| 2.2749 \| \| 2.4243 \| 7.68 \| 1824000 \| 2.2743 \| \| 2.4243 \| 7.71 \| 1832000 \| 2.2792 \| \| 2.4215 \| 7.75 \| 1840000 \| 2.2752 \| \| 2.4215 \| 7.78 \| 1848000 \| 2.2770 \| \| 2.4213 \| 7.81 \| 1856000 \| 2.2802 \| \| 2.4213 \| 7.85 \| 1864000 \| 2.2796 \| \| 2.4236 \| 7.88 \| 1872000 \| 2.2883 \| \| 2.4236 \| 7.92 \| 1880000 \| 2.2792 \| \| 2.4237 \| 7.95 \| 1888000 \| 2.2726 \| \| 2.4237 \| 7.98 \| 1896000 \| 2.2816 \| \| 2.4183 \| 8.02 \| 1904000 \| 2.2790 \| \| 2.4183 \| 8.05 \| 1912000 \| 2.2815 \| \| 2.4215 \| 8.08 \| 1920000 \| 2.2774 \| \| 2.4215 \| 8.12 \| 1928000 \| 2.2700 \| \| 2.4258 \| 8.15 \| 1936000 \| 2.2763 \| \| 2.4258 \| 8.19 \| 1944000 \| 2.2786 \| \| 2.4209 \| 8.22 \| 1952000 \| 2.2763 \| \| 2.4209 \| 8.25 \| 1960000 \| 2.2789 \| \| 2.4217 \| 8.29 \| 1968000 \| 2.2784 \| \| 2.4217 \| 8.32 \| 1976000 \| 2.2773 \| \| 2.4279 \| 8.35 \| 1984000 \| 2.2861 \| \| 2.4279 \| 8.39 \| 1992000 \| 2.2728 \| \| 2.4268 \| 8.42 \| 2000000 \| 2.2762 \| \| 2.4268 \| 8.45 \| 2008000 \| 2.2789 \| \| 2.4177 \| 8.49 \| 2016000 \| 2.2822 \| \| 2.4177 \| 8.52 \| 2024000 \| 2.2759 \| \| 2.4166 \| 8.56 \| 2032000 \| 2.2792 \| \| 2.4166 \| 8.59 \| 2040000 \| 2.2721 \| \| 2.4223 \| 8.62 \| 2048000 \| 2.2768 \| \| 2.4223 \| 8.66 \| 2056000 \| 2.2726 \| \| 2.4139 \| 8.69 \| 2064000 \| 2.2825 \| \| 2.4139 \| 8.72 \| 2072000 \| 2.2739 \| \| 2.4236 \| 8.76 \| 2080000 \| 2.2834 \| \| 2.4236 \| 8.79 \| 2088000 \| 2.2750 \| \| 2.4235 \| 8.83 \| 2096000 \| 2.2752 \| \| 2.4235 \| 8.86 \| 2104000 \| 2.2803 \| \| 2.4193 \| 8.89 \| 2112000 \| 2.2763 \| \| 2.4193 \| 8.93 \| 2120000 \| 2.2755 \| \| 2.4179 \| 8.96 \| 2128000 \| 2.2794 \| \| 2.4179 \| 8.99 \| 2136000 \| 2.2711 \| \| 2.4181 \| 9.03 \| 2144000 \| 2.2792 \| \| 2.4181 \| 9.06 \| 2152000 \| 2.2752 \| \| 2.4173 \| 9.09 \| 2160000 \| 2.2775 \| \| 2.4173 \| 9.13 \| 2168000 \| 2.2752 \| \| 2.4242 \| 9.16 \| 2176000 \| 2.2729 \| \| 2.4242 \| 9.2 \| 2184000 \| 2.2793 \| \| 2.4166 \| 9.23 \| 2192000 \| 2.2719 \| \| 2.4166 \| 9.26 \| 2200000 \| 2.2820 \| \| 2.4181 \| 9.3 \| 2208000 \| 2.2716 \| \| 2.4181 \| 9.33 \| 2216000 \| 2.2855 \| \| 2.4245 \| 9.36 \| 2224000 \| 2.2805 \| \| 2.4245 \| 9.4 \| 2232000 \| 2.2721 \| \| 2.4204 \| 9.43 \| 2240000 \| 2.2707 \| \| 2.4204 \| 9.47 \| 2248000 \| 2.2767 \| \| 2.4255 \| 9.5 \| 2256000 \| 2.2710 \| \| 2.4255 \| 9.53 \| 2264000 \| 2.2814 \| \| 2.4254 \| 9.57 \| 2272000 \| 2.2746 \| \| 2.4254 \| 9.6 \| 2280000 \| 2.2766 \| \| 2.4232 \| 9.63 \| 2288000 \| 2.2725 \| \| 2.4232 \| 9.67 \| 2296000 \| 2.2765 \| \| 2.4189 \| 9.7 \| 2304000 \| 2.2756 \| \| 2.4189 \| 9.73 \| 2312000 \| 2.2768 \| \| 2.4105 \| 9.77 \| 2320000 \| 2.2804 \| \| 2.4105 \| 9.8 \| 2328000 \| 2.2873 \| \| 2.415 \| 9.84 \| 2336000 \| 2.2783 \| \| 2.415 \| 9.87 \| 2344000 \| 2.2737 \| \| 2.4174 \| 9.9 \| 2352000 \| 2.2786 \| \| 2.4174 \| 9.94 \| 2360000 \| 2.2730 \| \| 2.4199 \| 9.97 \| 2368000 \| 2.2794 \| \| 2.4199 \| 10.0 \| 2376000 \| 2.2848 \| \| 2.4224 \| 10.04 \| 2384000 \| 2.2811 \| \| 2.4224 \| 10.07 \| 2392000 \| 2.2818 \| \| 2.4226 \| 10.11 \| 2400000 \| 2.2798 \| ### Framework versions - Transformers 4.35.0.dev0 - Pytorch 2.0.1+cu117 - Datasets 2.14.5 - Tokenizers 0.14.0
pokjay/poca-SoccerTwos-15M-Steps	pokjay	2024-02-29T07:13:57Z	0	0	ml-agents	[ "ml-agents", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]	reinforcement-learning	2024-02-29T07:13:54Z	--- library_name: ml-agents tags: - SoccerTwos - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SoccerTwos --- # poca Agent playing SoccerTwos This is a trained model of a poca agent playing SoccerTwos 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: pokjay/poca-SoccerTwos-15M-Steps 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
22x99/w2v2-ru-pre	22x99	2024-02-29T07:13:25Z	77	0	transformers	[ "transformers", "safetensors", "wav2vec2-bert", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-02-29T06:23:13Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
lamini/lamini_docs_finetuned	lamini	2024-02-29T07:13:15Z	3,206	9	transformers	[ "transformers", "pytorch", "safetensors", "gpt_neox", "text-generation", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-07-24T01:07:55Z	--- license: apache-2.0 --- This model was finetuned on EleutherAI/pythia-70m. The dataset used was lamini documents in the form of Q/A which tell more about how to use the platform. This is a sample task.
uni-zhuan/q-FrozenLake-v1-4x4-noSlippery	uni-zhuan	2024-02-29T07:10:24Z	0	0	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2024-02-29T07:10:22Z	--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="uni-zhuan/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```
CatBarks/t5_esSEC4_2_tokenizer	CatBarks	2024-02-29T07:05:47Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T07:05:46Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ultimecia/xlm-roberta-base-finetuned-panx-en	ultimecia	2024-02-29T07:01:18Z	104	0	transformers	[ "transformers", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-02-29T06:56:44Z	--- license: mit base_model: xlm-roberta-base tags: - generated_from_trainer metrics: - f1 model-index: - name: xlm-roberta-base-finetuned-panx-en results: [] --- <!-- 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-en 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: 0.5819 - F1: 0.5333 ## 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: 96 - eval_batch_size: 96 - 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 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| No log \| 1.0 \| 13 \| 1.0130 \| 0.2401 \| \| No log \| 2.0 \| 26 \| 0.6741 \| 0.4890 \| \| No log \| 3.0 \| 39 \| 0.5819 \| 0.5333 \| ### Framework versions - Transformers 4.38.1 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
hemanthkandimalla/HemanthLLM_tiny1.1b	hemanthkandimalla	2024-02-29T06:58:52Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T05:01:19Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses ```python %%time from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b") from peft import PeftModel model_name='google/gemma-2b' inference_model = AutoModelForCausalLM.from_pretrained( model_name, low_cpu_mem_usage=True, # use_flash_attention_2=True, ) inference_model.resize_token_embeddings(len(tokenizer)) inference_model = PeftModel.from_pretrained(inference_model, "hemanthkandimalla/HemanthLLM_tiny1.1b") inference_model.eval() text="attacks names" tokenizer_input=tokenizer(text=text, return_tensors="pt") output_tokens = inference_model.generate( tokenizer_input, max_new_tokens=256, do_sample=True, temperature=0.2, top_p=0.95, top_k=50, eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.pad_token_id, ) text=tokenizer.decode(output_tokens[0], skip_special_tokens=False) print(text) ``` ### 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]
Noel-lawrence/ppo-SnowballTarget	Noel-lawrence	2024-02-29T06:58:37Z	23	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]	reinforcement-learning	2024-02-27T12:43:39Z	--- library_name: ml-agents tags: - SnowballTarget - deep-reinforcement-learning - reinforcement-learning - ML-Agents-SnowballTarget --- # ppo Agent playing SnowballTarget This is a trained model of a ppo agent playing SnowballTarget 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: Noel-lawrence/ppo-SnowballTarget 3. Step 2: Select your .nn /.onnx file 4. Click on Watch the agent play 👀
ultimecia/xlm-roberta-base-finetuned-panx-it	ultimecia	2024-02-29T06:56:37Z	104	0	transformers	[ "transformers", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-02-29T06:51:47Z	--- license: mit base_model: xlm-roberta-base tags: - generated_from_trainer metrics: - f1 model-index: - name: xlm-roberta-base-finetuned-panx-it results: [] --- <!-- 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-it 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: 0.3623 - F1: 0.7313 ## 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: 96 - eval_batch_size: 96 - 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 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| No log \| 1.0 \| 18 \| 0.7339 \| 0.4485 \| \| No log \| 2.0 \| 36 \| 0.4065 \| 0.6765 \| \| No log \| 3.0 \| 54 \| 0.3623 \| 0.7313 \| ### Framework versions - Transformers 4.38.1 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
jjlee6496/LDCC-SOLAR-10.7B-finetuned	jjlee6496	2024-02-29T06:49:27Z	1	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "license:cc-by-nc-4.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T05:30:42Z	--- license: cc-by-nc-4.0 --- ## Base Model - [LDCC/LDCC-SOLAR-10.7B](https://huggingface.co/LDCC/LDCC-SOLAR-10.7B)
shivanikerai/Llama-2-7b-chat-hf-adapter-sku-title-ner-generation-reversed-v2.1	shivanikerai	2024-02-29T06:46:29Z	0	0	peft	[ "peft", "arxiv:1910.09700", "base_model:meta-llama/Llama-2-7b-chat-hf", "base_model:adapter:meta-llama/Llama-2-7b-chat-hf", "region:us" ]	null	2024-02-29T06:45:46Z	--- library_name: peft base_model: meta-llama/Llama-2-7b-chat-hf --- # 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 0.9.0
pockypocky/distilbert-base-uncased-finetuned-emotion	pockypocky	2024-02-29T06:29:34Z	106	0	transformers	[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-02-29T06:09:19Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer datasets: - emotion metrics: - accuracy - f1 model-index: - name: distilbert-base-uncased-finetuned-emotion results: - task: name: Text Classification type: text-classification dataset: name: emotion type: emotion config: split split: validation args: split metrics: - name: Accuracy type: accuracy value: 0.927 - name: F1 type: f1 value: 0.9268755922056178 --- <!-- 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. --> # distilbert-base-uncased-finetuned-emotion This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset. It achieves the following results on the evaluation set: - Loss: 0.2132 - Accuracy: 0.927 - F1: 0.9269 ## 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: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| F1 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:------:\| \| 0.8076 \| 1.0 \| 250 \| 0.3047 \| 0.9155 \| 0.9150 \| \| 0.2454 \| 2.0 \| 500 \| 0.2132 \| 0.927 \| 0.9269 \| ### Framework versions - Transformers 4.38.1 - Pytorch 2.2.1+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
lole25/phi-2-gpo-ultrachat-lora-0.1	lole25	2024-02-29T06:20:54Z	0	0	peft	[ "peft", "tensorboard", "safetensors", "phi", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "custom_code", "dataset:HuggingFaceH4/ultrafeedback_binarized", "base_model:microsoft/phi-2", "base_model:adapter:microsoft/phi-2", "license:mit", "region:us" ]	null	2024-02-29T05:56:32Z	--- license: mit library_name: peft tags: - alignment-handbook - generated_from_trainer - trl - dpo - generated_from_trainer datasets: - HuggingFaceH4/ultrafeedback_binarized base_model: microsoft/phi-2 model-index: - name: phi-2-gpo-ultrachat-lora-0.1 results: [] --- <!-- 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. --> # phi-2-gpo-ultrachat-lora-0.1 This model is a fine-tuned version of [lole25/phi-2-sft-ultrachat-lora](https://huggingface.co/lole25/phi-2-sft-ultrachat-lora) on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set: - Loss: 0.0100 - Rewards/chosen: -0.0001 - Rewards/rejected: -0.0003 - Rewards/accuracies: 0.2620 - Rewards/margins: 0.0002 - Logps/rejected: -94.2224 - Logps/chosen: -91.7363 - Logits/rejected: 0.8196 - Logits/chosen: 0.8018 ## 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: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - total_eval_batch_size: 16 - 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 - PEFT 0.7.1 - Transformers 4.36.2 - Pytorch 2.1.2+cu118 - Datasets 2.14.6 - Tokenizers 0.15.2
nerone/ppo-LunarLander-v2	nerone	2024-02-29T06:13:07Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-02-29T06:12:49Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 235.30 +/- 20.40 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 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 ... ```
rlawjdghek/StableVITON	rlawjdghek	2024-02-29T06:06:45Z	0	10	null	[ "arxiv:2312.01725", "region:us" ]	null	2024-02-29T06:01:49Z	# [CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On This repository is the official implementation of [StableVITON](https://arxiv.org/abs/2312.01725) > StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On<br> > [Jeongho Kim](https://scholar.google.co.kr/citations?user=ucoiLHQAAAAJ&hl=ko), [Gyojung Gu](https://www.linkedin.com/in/gyojung-gu-29033118b/), [Minho Park](https://pmh9960.github.io/), [Sunghyun Park](https://psh01087.github.io/), [Jaegul Choo](https://sites.google.com/site/jaegulchoo/) [[Arxiv Paper](https://arxiv.org/abs/2312.01725)]  [[Website Page](https://rlawjdghek.github.io/StableVITON/)]  ![teaser](assets/teaser.png)  ## TODO List - [x] ~~Inference code~~ - [x] ~~Release model weights~~ - [x] ~~Training code~~ ## Environments ```bash git clone https://github.com/rlawjdghek/StableVITON cd StableVITON conda create --name StableVITON python=3.10 -y conda activate StableVITON # install packages pip install torch==2.0.0+cu117 torchvision==0.15.1+cu117 torchaudio==2.0.1 --index-url https://download.pytorch.org/whl/cu117 pip install pytorch-lightning==1.5.0 pip install einops pip install opencv-python==4.7.0.72 pip install matplotlib pip install omegaconf pip install albumentations pip install transformers==4.33.2 pip install xformers==0.0.19 pip install triton==2.0.0 pip install open-clip-torch==2.19.0 pip install diffusers==0.20.2 pip install scipy==1.10.1 conda install -c anaconda ipython -y ``` ## Weights and Data Our [checkpoint](https://kaistackr-my.sharepoint.com/:f:/g/personal/rlawjdghek_kaist_ac_kr/EjzAZHJu9MlEoKIxG4tqPr0BM_Ry20NHyNw5Sic2vItxiA?e=5mGa1c) on VITONHD have been released! <br> You can download the VITON-HD dataset from [here](https://github.com/shadow2496/VITON-HD).<br> For both training and inference, the following dataset structure is required: ``` train \|-- image \|-- image-densepose \|-- agnostic \|-- agnostic-mask \|-- cloth \|-- cloth_mask \|-- gt_cloth_warped_mask (for ATV loss) test \|-- image \|-- image-densepose \|-- agnostic \|-- agnostic-mask \|-- cloth \|-- cloth_mask ``` ## Preprocessing The VITON-HD dataset serves as a benchmark and provides an agnostic mask. However, you can attempt virtual try-on on arbitrary images using segmentation tools like [SAM](https://github.com/facebookresearch/segment-anything). Please note that for densepose, you should use the same densepose model as used in VITON-HD. ## Inference ```bash #### paired CUDA_VISIBLE_DEVICES=4 python inference.py \ --config_path ./configs/VITONHD.yaml \ --batch_size 4 \ --model_load_path <model weight path> \ --save_dir <save directory> #### unpaired CUDA_VISIBLE_DEVICES=4 python inference.py \ --config_path ./configs/VITONHD.yaml \ --batch_size 4 \ --model_load_path <model weight path> \ --unpair \ --save_dir <save directory> #### paired repaint CUDA_VISIBLE_DEVICES=4 python inference.py \ --config_path ./configs/VITONHD.yaml \ --batch_size 4 \ --model_load_path <model weight path>t \ --repaint \ --save_dir <save directory> #### unpaired repaint CUDA_VISIBLE_DEVICES=4 python inference.py \ --config_path ./configs/VITONHD.yaml \ --batch_size 4 \ --model_load_path <model weight path> \ --unpair \ --repaint \ --save_dir <save directory> ``` You can also preserve the unmasked region by '--repaint' option. ## Training For VITON training, we increased the first block of U-Net from 9 to 13 channels (add zero conv) based on the Paint-by-Example (PBE) model. Therefore, you should download the modified checkpoint (named as 'VITONHD_PBE_pose.ckpt') from the [Link](https://kaistackr-my.sharepoint.com/:f:/g/personal/rlawjdghek_kaist_ac_kr/EjzAZHJu9MlEoKIxG4tqPr0BM_Ry20NHyNw5Sic2vItxiA?e=5mGa1c) and place it in the './ckpts/' folder first. Additionally, for more refined person texture, we utilized a VAE fine-tuned on the VITONHD dataset. You should also download the checkpoint (named as VITONHD_VAE_finetuning.ckpt') from the [Link](https://kaistackr-my.sharepoint.com/:f:/g/personal/rlawjdghek_kaist_ac_kr/EjzAZHJu9MlEoKIxG4tqPr0BM_Ry20NHyNw5Sic2vItxiA?e=5mGa1c) and place it in the './ckpts/' folder. ```bash ### Base model training CUDA_VISIBLE_DEVICES=3,4 python train.py \ --config_name VITONHD \ --transform_size shiftscale3 hflip \ --transform_color hsv bright_contrast \ --save_name Base_test ### ATV loss finetuning CUDA_VISIBLE_DEVICES=5,6 python train.py \ --config_name VITONHD \ --transform_size shiftscale3 hflip \ --transform_color hsv bright_contrast \ --use_atv_loss \ --resume_path <first stage model path> \ --save_name ATVloss_test ``` ## Citation If you find our work useful for your research, please cite us: ``` @artical{kim2023stableviton, title={StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On}, author={Kim, Jeongho and Gu, Gyojung and Park, Minho and Park, Sunghyun and Choo, Jaegul}, booktitle={arXiv preprint arxiv:2312.01725}, year={2023} } ``` Acknowledgements Sunghyun Park is the corresponding author. ## License Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
bartowski/opus-v1.2-7b-exl2	bartowski	2024-02-29T06:02:36Z	3	0	null	[ "unsloth", "axolotl", "text-generation", "en", "region:us" ]	text-generation	2024-02-29T05:48:16Z	--- language: - en pipeline_tag: text-generation tags: - unsloth - axolotl quantized_by: bartowski --- ## Exllama v2 Quantizations of opus-v1.2-7b Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.14">turboderp's ExLlamaV2 v0.0.14</a> for quantization. <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b> Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions. Original model: https://huggingface.co/dreamgen/opus-v1.2-7b \| Branch \| Bits \| lm_head bits \| VRAM (4k) \| VRAM (16k) \| VRAM (32k) \| Description \| \| ----- \| ---- \| ------- \| ------ \| ------ \| ------ \| ------------ \| \| [8_0](https://huggingface.co/bartowski/opus-v1.2-7b-exl2/tree/8_0) \| 8.0 \| 8.0 \| 8.4 GB \| 9.8 GB \| 11.8 GB \| Maximum quality that ExLlamaV2 can produce, near unquantized performance. \| \| [6_5](https://huggingface.co/bartowski/opus-v1.2-7b-exl2/tree/6_5) \| 6.5 \| 8.0 \| 7.2 GB \| 8.6 GB \| 10.6 GB \| Very similar to 8.0, good tradeoff of size vs performance, recommended. \| \| [5_0](https://huggingface.co/bartowski/opus-v1.2-7b-exl2/tree/5_0) \| 5.0 \| 6.0 \| 6.0 GB \| 7.4 GB \| 9.4 GB \| Slightly lower quality vs 6.5, but usable on 8GB cards. \| \| [4_25](https://huggingface.co/bartowski/opus-v1.2-7b-exl2/tree/4_25) \| 4.25 \| 6.0 \| 5.3 GB \| 6.7 GB \| 8.7 GB \| GPTQ equivalent bits per weight, slightly higher quality. \| \| [3_5](https://huggingface.co/bartowski/opus-v1.2-7b-exl2/tree/3_5) \| 3.5 \| 6.0 \| 4.7 GB \| 6.1 GB \| 8.1 GB \| Lower quality, only use if you have to. \| ## Download instructions With git: ```shell git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/opus-v1.2-7b-exl2 opus-v1.2-7b-exl2-6_5 ``` With huggingface hub (credit to TheBloke for instructions): ```shell pip3 install huggingface-hub ``` To download the `main` (only useful if you only care about measurement.json) branch to a folder called `opus-v1.2-7b-exl2`: ```shell mkdir opus-v1.2-7b-exl2 huggingface-cli download bartowski/opus-v1.2-7b-exl2 --local-dir opus-v1.2-7b-exl2 --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: Linux: ```shell mkdir opus-v1.2-7b-exl2-6_5 huggingface-cli download bartowski/opus-v1.2-7b-exl2 --revision 6_5 --local-dir opus-v1.2-7b-exl2-6_5 --local-dir-use-symlinks False ``` Windows (which apparently doesn't like _ in folders sometimes?): ```shell mkdir opus-v1.2-7b-exl2-6.5 huggingface-cli download bartowski/opus-v1.2-7b-exl2 --revision 6_5 --local-dir opus-v1.2-7b-exl2-6.5 --local-dir-use-symlinks False ``` Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
VietDo26/distilbert-finetuned-squadv2	VietDo26	2024-02-29T06:00:59Z	113	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	question-answering	2024-02-29T04:53:07Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer model-index: - name: distilbert-finetuned-squadv2 results: [] --- <!-- 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. --> # distilbert-finetuned-squadv2 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) 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 - 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 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.16.1 - Tokenizers 0.15.2
Zacksabrach/Pila	Zacksabrach	2024-02-29T05:58:41Z	0	0	null	[ "license:openrail", "region:us" ]	null	2024-02-29T05:58:41Z	--- license: openrail license_name: openrail license_link: >- https://drive.google.com/drive/folders/19TqheZva44yIWWevYBHGkaENhGH8206f?usp=sharing ---
FINNUMBER/Yi-Ko-6B-Finch-Full-Epoch3	FINNUMBER	2024-02-29T05:54:57Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-26T15:03:27Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
souvik0306/whisper_pre_prod_test	souvik0306	2024-02-29T05:54:50Z	5	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "region:us" ]	null	2024-02-29T05:54:48Z	--- library_name: peft base_model: OpenAI/whisper-large-v3 --- # 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 0.8.2
lole25/phi-2-gpo-ultrachat-lora	lole25	2024-02-29T05:53:01Z	0	0	peft	[ "peft", "tensorboard", "safetensors", "phi", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "custom_code", "dataset:HuggingFaceH4/ultrafeedback_binarized", "base_model:microsoft/phi-2", "base_model:adapter:microsoft/phi-2", "license:mit", "region:us" ]	null	2024-02-29T04:58:35Z	--- license: mit library_name: peft tags: - alignment-handbook - generated_from_trainer - trl - dpo - generated_from_trainer datasets: - HuggingFaceH4/ultrafeedback_binarized base_model: microsoft/phi-2 model-index: - name: phi-2-gpo-ultrachat-lora results: [] --- <!-- 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. --> # phi-2-gpo-ultrachat-lora This model is a fine-tuned version of [lole25/phi-2-sft-ultrachat-lora](https://huggingface.co/lole25/phi-2-sft-ultrachat-lora) on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set: - Loss: 0.0001 - Rewards/chosen: -0.0000 - Rewards/rejected: -0.0004 - Rewards/accuracies: 0.2600 - Rewards/margins: 0.0004 - Logps/rejected: -94.2372 - Logps/chosen: -91.7275 - Logits/rejected: 0.8188 - Logits/chosen: 0.8013 ## 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: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - total_eval_batch_size: 16 - 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 - PEFT 0.7.1 - Transformers 4.36.2 - Pytorch 2.1.2+cu118 - Datasets 2.14.6 - Tokenizers 0.15.2
universalml/wf	universalml	2024-02-29T05:50:46Z	166	0	transformers	[ "transformers", "pytorch", "vit", "image-classification", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2024-02-29T05:48:08Z	--- tags: - generated_from_trainer model-index: - name: wf results: [] --- <!-- 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. --> # wf This model was trained from scratch 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: 16 - eval_batch_size: 16 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 3 ### Framework versions - Transformers 4.34.1 - Pytorch 1.13.0+cpu - Datasets 2.14.5 - Tokenizers 0.14.1
abdullaharean/regipa_bangla	abdullaharean	2024-02-29T05:48:54Z	109	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "bn", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-27T12:22:15Z	--- license: mit language: - bn --- # Team_Khita_Kortesi_Model: Bengali Text to IPA Transcription based on fine-tuned ByT5-small ## Solution Summary: Our team's solution focuses on developing a robust model for transcribing Bengali text into International Phonetic Alphabet (IPA), contributing to computational linguistics and NLP research in Bengali. Leveraging a linguist-validated dataset encompassing diverse domains of Bengali text, our model aims to accurately capture the phonetic nuances and regional dialects present in Bengali language. ## Approach: ### Data Preprocessing: We preprocess the Bengali text data to handle linguistic variations, tokenization, and normalization. ### Model Architecture: Our model architecture employs state-of-the-art deep learning techniques, such as recurrent neural networks (RNNs) or transformer-based models, to capture the sequential and contextual information inherent in language. ### Training: The model is trained on the linguist-validated dataset, optimizing for accuracy, robustness, and generalization across various dialects and linguistic contexts. ### Validation: We validate the model's performance using rigorous evaluation metrics, ensuring its effectiveness in accurately transcribing Bengali text into IPA. ### Deployment: Upon successful validation, the model is deployed as an open-source tool, extending the capabilities of generalized Bengali Text-to-Speech systems and facilitating further research in Bengali computational linguistics. ## Key Features: - Phonetic Accuracy: Our model prioritizes phonetic accuracy, ensuring faithful transcription of Bengali text into IPA symbols. - Regional Dialects: The model is designed to accommodate the diverse regional dialects and linguistic variations present in Bengali language, capturing the nuances specific to each region. - Scalability: With a scalable architecture, our solution can handle large volumes of text data efficiently, making it suitable for real-world applications and research purposes. - Accessibility: By open-sourcing our model, we aim to make IPA transcription accessible to a wider audience, fostering collaboration and innovation in Bengali computational linguistics. ## Impact: - Advancing Research: Our solution contributes to advancing research in Bengali computational linguistics and NLP, providing researchers with a valuable tool for studying language dynamics and linguistic diversity. - Community Engagement: By open-sourcing our model and making it accessible to all, we empower the Bengali language community to engage in linguistic research and exploration. - Technological Innovation: Our model extends the capabilities of existing Bengali Text-to-Speech systems, paving the way for innovative applications in speech synthesis, language learning, and accessibility. ## Example Inference: ```python from transformers import T5ForConditionalGeneration import torch model = T5ForConditionalGeneration.from_pretrained('abdullaharean/regipa_bangla') input_ids = torch.tensor([list("Life is like a box of chocolates.".encode("utf-8"))]) + 3 # add 3 for special tokens labels = torch.tensor([list("La vie est comme une boîte de chocolat.".encode("utf-8"))]) + 3 # add 3 for special tokens loss = model(input_ids, labels=labels).loss # forward pass ```
youndukn/MythoMax-L2-13b	youndukn	2024-02-29T05:47:08Z	5	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "en", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-22T02:17:22Z	--- license: other language: - en --- An improved, potentially even perfected variant of MythoMix, my [MythoLogic-L2](https://huggingface.co/Gryphe/MythoLogic-L2-13b) and [Huginn](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16) merge using a highly experimental tensor type merge technique. The main difference with MythoMix is that I allowed more of Huginn to intermingle with the single tensors located at the front and end of a model, resulting in increased coherency across the entire structure. The script and the acccompanying templates I used to produce both can [be found here](https://github.com/Gryphe/BlockMerge_Gradient/tree/main/YAML). This model is proficient at both roleplaying and storywriting due to its unique nature. Quantized models are available from TheBloke: [GGUF](https://huggingface.co/TheBloke/MythoMax-L2-13B-GGUF) - [GPTQ](https://huggingface.co/TheBloke/MythoMax-L2-13B-GPTQ) - [AWQ](https://huggingface.co/TheBloke/MythoMax-L2-13B-AWQ) (You're the best!) ## Model details The idea behind this merge is that each layer is composed of several tensors, which are in turn responsible for specific functions. Using MythoLogic-L2's robust understanding as its input and Huginn's extensive writing capability as its output seems to have resulted in a model that exceeds at both, confirming my theory. (More details to be released at a later time) This type of merge is incapable of being illustrated, as each of its 363 tensors had an unique ratio applied to it. As with my prior merges, gradients were part of these ratios to further finetune its behaviour. ## Prompt Format This model primarily uses Alpaca formatting, so for optimal model performance, use: ``` <System prompt/Character Card> ### Instruction: Your instruction or question here. For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only. ### Response: ``` --- license: other ---
CatBarks/t5_esSEC4_1	CatBarks	2024-02-29T05:43:17Z	48	0	transformers	[ "transformers", "safetensors", "t5", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	2024-02-29T05:41:37Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
morissu/camelot	morissu	2024-02-29T05:41:42Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-15T14:57:36Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
hcapp/hcapp	hcapp	2024-02-29T05:39:36Z	4	1	diffusers	[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2024-02-29T05:35:48Z	--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### hcapp Dreambooth model trained by hcapp with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:
Abdulrhman3133/AceGPT_3	Abdulrhman3133	2024-02-29T05:38:02Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T05:30:08Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
MIMASA24/my-panda	MIMASA24	2024-02-29T05:31:09Z	0	0	diffusers	[ "diffusers", "safetensors", "NxtWave-GenAI-Webinar", "text-to-image", "stable-diffusion", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2024-02-29T05:26:51Z	--- license: creativeml-openrail-m tags: - NxtWave-GenAI-Webinar - text-to-image - stable-diffusion --- ### My-PANDA Dreambooth model trained by MIMASA24 following the "Build your own Gen AI model" session by NxtWave. Project Submission Code: 220349106096 Sample pictures of this concept: ![0](https://huggingface.co/MIMASA24/my-panda/resolve/main/sample_images/xzg5.jpeg)
PavanDeepak/Topic_Classification	PavanDeepak	2024-02-29T05:29:41Z	111	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-02-28T12:51:23Z	--- license: mit --- ## BERT-based Text Classification Model This model is a fine-tuned version of the bert-base-uncased model, specifically adapted for text classification across a diverse set of categories. The model has been trained on a dataset collected from multiple sources, including the News Category Dataset on Kaggle and various other websites. The model classifies text into one of the following 12 categories: * Food * Videogames & Shows * Kids and fun * Homestyle * Travel * Health * Charity * Electronics & Technology * Sports * Cultural & Music * Education * Convenience The model has demonstrated robust performance with an accuracy of 0.721459, F1 score of 0.659451, precision of 0.707620, and recall of 0.635155. ## Model Architecture The model leverages the BertForSequenceClassification architecture, It has been fine-tuned on the aforementioned dataset, with the following key configuration parameters: * Hidden size: 768 * Number of attention heads: 12 * Number of hidden layers: 12 * Max position embeddings: 512 * Type vocab size: 2 * Vocab size: 30522 * The model uses the GELU activation function in its hidden layers and applies dropout with a probability of 0.1 to the attention probabilities to prevent overfitting. ## Example ```python from transformers import AutoModelForSequenceClassification, AutoTokenizer import numpy as np from scipy.special import expit MODEL = "PavanDeepak/Topic_Classification" tokenizer = AutoTokenizer.from_pretrained(MODEL) model = AutoModelForSequenceClassification.from_pretrained(MODEL) class_mapping = model.config.id2label text = "I love chicken manchuria" tokens = tokenizer(text, return_tensors="pt") output = model(*tokens) scores = output.logits[0][0].detach().numpy() scores = expit(scores) predictions = (scores >= 0.5) 1 for i in range(len(predictions)): if predictions[i]: print(class_mapping[i]) ``` ## Output: * Food * Videogames & Shows * Homestyle * Travel * Health
Lichang-Chen/ODIN_L1_O1	Lichang-Chen	2024-02-29T05:14:39Z	4	0	transformers	[ "transformers", "pytorch", "llama", "text-generation", "RM", "dataset:OpenAssistant/oasst1", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-05T13:33:36Z	--- license: mit datasets: - OpenAssistant/oasst1 tags: - RM --- The model trained with L=1 (Length loss weight) and O=1 (Orthogonal loss weight).
Denilah/CoMA-7B	Denilah	2024-02-29T05:10:17Z	13	5	transformers	[ "transformers", "pytorch", "llama", "text-generation", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2023-06-24T01:55:41Z	# CoLLaMA: A Multi-task Instruction Dataset and Large Language Model for Code <p align="center" width="100%"> <img src="https://i.postimg.cc/J7Ds1tw6/CoLLaMA.jpg" width="40%" height="20%"> </p> ## Model details Trained in June 2023. CoMA comprises a fine-tuned coding LLM and a multi-task instruction tuning dataset featuring 77K data samples encompassing 8 diverse tasks. Please refer to [the README of the GitHub repository](https://github.com/Denilah/CoLLaMA) for detailed information. ### Training dataset The model was trained on a 77k rows instruction following dataset, which is released in the [GitHub repository](https://github.com/Denilah/CoLLaMA). ### Citation <div> <div align="center"> <a target='_blank'>Gang Hu<sup>1</sup></span>&emsp; <a target='_blank'>Xi Wen<sup>1</sup></span>&emsp; <a target='_blank'>Xin Liu<sup>1</sup></a>&emsp; <a href='https://jimin.chancefocus.com/' target='_blank'>Jimin Huang<sup>2</sup></a>&emsp; <a target='_blank'>Qianqian Xie*<sup>3</sup></a>&emsp; </div> <div> <div align="center"> <sup>1</sup>School of Information Science & Engineering, Yunnan University&emsp; <sup>2</sup>ChanceFocus AMC&emsp; <sup>3</sup>School of Computer Science, Wuhan University&emsp; </div> ``` @misc{Hu2023CoLLaMA, title={CoLLaMA: A Multi-task Instruction Dataset and Large Language Model for Code}, author={Gang Hu and Xi Wen and Xin Liu and Jimin Huang and Qianqian Xie}, year={2023}, } ```
JinghuiLuAstronaut/DocLLM_baichuan2_7b	JinghuiLuAstronaut	2024-02-29T04:58:18Z	134	5	transformers	[ "transformers", "safetensors", "baichuan", "text-generation", "custom_code", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T03:41:01Z	See https://github.com/GeorgeLuImmortal/DocLLM_reimplementation/
aisuko/ft-facebook-bart-large-xsum-on-samsum	aisuko	2024-02-29T04:54:13Z	108	0	transformers	[ "transformers", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "dataset:text-summatization", "base_model:facebook/bart-large-xsum", "base_model:finetune:facebook/bart-large-xsum", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-20T06:01:20Z	--- license: mit base_model: facebook/bart-large-xsum tags: - generated_from_trainer datasets: - text-summatization model-index: - name: ft-facebook-bart-large-xsum-on-samsum results: [] --- <!-- 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. --> # ft-facebook-bart-large-xsum-on-samsum This model is a fine-tuned version of [facebook/bart-large-xsum](https://huggingface.co/facebook/bart-large-xsum) on the Samsum 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: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 100 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:-------:\| \| No log \| 0.22 \| 100 \| 1.5051 \| 49.5382 \| 24.4845 \| 40.7456 \| 45.3284 \| 26.1722 \| ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.2 - Datasets 2.17.0 - Tokenizers 0.15.1
LarryAIDraw/yorktownii-lora-v1-32dim-20ep-naivae	LarryAIDraw	2024-02-29T04:45:22Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2024-02-26T15:36:08Z	--- license: creativeml-openrail-m --- https://civitai.com/models/18699?modelVersionId=22186
JC9027/finetuning-gpt2-finetunned	JC9027	2024-02-29T04:44:43Z	116	0	transformers	[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:openai-community/gpt2", "base_model:finetune:openai-community/gpt2", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-26T05:45:10Z	--- license: mit base_model: openai-community/gpt2 tags: - generated_from_trainer model-index: - name: finetuning-gpt2-finetunned results: [] --- <!-- 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. --> # finetuning-gpt2-finetunned This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) 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: 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: 3 ### Training results ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
jonquimbly/shap-e	jonquimbly	2024-02-29T04:36:13Z	4	1	diffusers	[ "diffusers", "text-to-image", "shap-e", "text-to-3d", "arxiv:2305.02463", "license:mit", "diffusers:ShapEPipeline", "region:us" ]	text-to-3d	2024-02-29T04:36:13Z	--- license: mit tags: - text-to-image - shap-e - diffusers pipeline_tag: text-to-3d --- # Shap-E Shap-E introduces a diffusion process that can generate a 3D image from a text prompt. It was introduced in [Shap-E: Generating Conditional 3D Implicit Functions](https://arxiv.org/abs/2305.02463) by Heewoo Jun and Alex Nichol from OpenAI. Original repository of Shap-E can be found here: https://github.com/openai/shap-e. _The authors of Shap-E didn't author this model card. They provide a separate model card [here](https://github.com/openai/shap-e/blob/main/model-card.md)._ ## Introduction The abstract of the Shap-E paper: We present Shap-E, a conditional generative model for 3D assets. Unlike recent work on 3D generative models which produce a single output representation, Shap-E directly generates the parameters of implicit functions that can be rendered as both textured meshes and neural radiance fields. We train Shap-E in two stages: first, we train an encoder that deterministically maps 3D assets into the parameters of an implicit function; second, we train a conditional diffusion model on outputs of the encoder. When trained on a large dataset of paired 3D and text data, our resulting models are capable of generating complex and diverse 3D assets in a matter of seconds. When compared to Point-E, an explicit generative model over point clouds, Shap-E converges faster and reaches comparable or better sample quality despite modeling a higher-dimensional, multi-representation output space. We release model weights, inference code, and samples at [this https URL](https://github.com/openai/shap-e). ## Released checkpoints The authors released the following checkpoints: * [openai/shap-e](https://hf.co/openai/shap-e): produces a 3D image from a text input prompt * [openai/shap-e-img2img](https://hf.co/openai/shap-e-img2img): samples a 3D image from synthetic 2D image ## Usage examples in 🧨 diffusers First make sure you have installed all the dependencies: ```bash pip install transformers accelerate -q pip install git+https://github.com/huggingface/diffusers@@shap-ee ``` Once the dependencies are installed, use the code below: ```python import torch from diffusers import ShapEPipeline from diffusers.utils import export_to_gif ckpt_id = "openai/shap-e" pipe = ShapEPipeline.from_pretrained(repo).to("cuda") guidance_scale = 15.0 prompt = "a shark" images = pipe( prompt, guidance_scale=guidance_scale, num_inference_steps=64, size=256, ).images gif_path = export_to_gif(images, "shark_3d.gif") ``` ## Results <table> <tbody> <tr> <td align="center"> <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/shap-e/bird_3d.gif" alt="a bird"> </td> <td align="center"> <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/shap-e/shark_3d.gif" alt="a shark"> </td align="center"> <td align="center"> <img src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/shap-e/veg_3d.gif" alt="A bowl of vegetables"> </td> </tr> <tr> <td align="center">A bird</td> <td align="center">A shark</td> <td align="center">A bowl of vegetables</td> </tr> </tr> </tbody> <table> ## Training details Refer to the [original paper](https://arxiv.org/abs/2305.02463). ## Known limitations and potential biases Refer to the [original model card](https://github.com/openai/shap-e/blob/main/model-card.md). ## Citation ```bibtex @misc{jun2023shape, title={Shap-E: Generating Conditional 3D Implicit Functions}, author={Heewoo Jun and Alex Nichol}, year={2023}, eprint={2305.02463}, archivePrefix={arXiv}, primaryClass={cs.CV} } ```
suthanhcong/bert-base-japanese-v3-marc_ja	suthanhcong	2024-02-29T04:33:47Z	106	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-02-29T04:33:19Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
atakanince/whisper-small-turkish-v1	atakanince	2024-02-29T04:27:04Z	116	0	transformers	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "hf-asr-leaderboard", "generated_from_trainer", "tr", "dataset:mozilla-foundation/common_voice_11_0", "base_model:openai/whisper-small", "base_model:finetune:openai/whisper-small", "license:apache-2.0", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-02-27T21:32:31Z	--- language: - tr license: apache-2.0 base_model: openai/whisper-small tags: - hf-asr-leaderboard - generated_from_trainer datasets: - mozilla-foundation/common_voice_11_0 model-index: - name: Whisper Small Tr V1 - Atakan Ince results: [] --- <!-- 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. --> # Whisper Small Tr V1 - Atakan Ince This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 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: 16 - 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: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Framework versions - Transformers 4.38.1 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
kumatomo/TopK_GNN	kumatomo	2024-02-29T04:12:49Z	1	0	pytorch_geometric	[ "pytorch_geometric", "pretrain", "graph-machine-learning", "en", "dataset:QM9", "arxiv:1910.09700", "license:mit", "region:us" ]	null	2024-02-29T03:13:32Z	--- language: en license: mit library_name: pytorch_geometric tags: - graph-machine-learning datasets: QM9 model_name: TopK --- # 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] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): en - License: mit - 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 Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [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 Data 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]
dagbs/Gemma-Wukong-2b-GGUF	dagbs	2024-02-29T03:59:36Z	13	1	null	[ "gguf", "license:other", "endpoints_compatible", "region:us", "conversational" ]	null	2024-02-28T03:32:17Z	--- license: other license_name: gemma-terms-of-use license_link: https://ai.google.dev/gemma/terms --- Note: This results in very weird responses. We are working on fixing the vocab but don't have an ETA. # Gemma-Wukong-2b GGUF Original Model: https://huggingface.co/RESMPDEV/Gemma-Wukong-2b ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/655dc641accde1bbc8b41aec/xOe1Nb3S9Nb53us7_Ja3s.jpeg)
AIMindaeng/hansoldeco-KGOAT	AIMindaeng	2024-02-29T03:52:33Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T03:52:27Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ArthurZ/mamba-790m	ArthurZ	2024-02-29T03:47:39Z	373	0	transformers	[ "transformers", "safetensors", "mamba", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-19T12:21:24Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
yjchenbe/sd-class-butterflies-32	yjchenbe	2024-02-29T03:37:37Z	44	0	diffusers	[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]	unconditional-image-generation	2024-02-29T03:37:11Z	--- license: mit tags: - pytorch - diffusers - unconditional-image-generation - diffusion-models-class --- # Model Card for Unit 1 of the [Diffusion Models Class 🧨](https://github.com/huggingface/diffusion-models-class) This model is a diffusion model for unconditional image generation of cute 🦋. ## Usage ```python from diffusers import DDPMPipeline pipeline = DDPMPipeline.from_pretrained('yjchenbe/sd-class-butterflies-32') image = pipeline().images[0] image ```
lunarsylph/gemmacell_v6	lunarsylph	2024-02-29T03:20:30Z	114	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T03:08:26Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
danwils/Alasv2-Seallm-7B-v2	danwils	2024-02-29T03:17:10Z	5	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-29T03:08:50Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
rasyosef/bert-tiny-domain-adapted-imdb	rasyosef	2024-02-29T03:00:57Z	118	0	transformers	[ "transformers", "tensorboard", "safetensors", "bert", "fill-mask", "generated_from_trainer", "en", "dataset:imdb", "base_model:prajjwal1/bert-tiny", "base_model:finetune:prajjwal1/bert-tiny", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2024-02-29T02:32:37Z	--- license: mit base_model: prajjwal1/bert-tiny tags: - generated_from_trainer model-index: - name: bert-tiny-domain-adapted-imdb results: [] datasets: - imdb language: - en metrics: - perplexity pipeline_tag: fill-mask widget: - text: This is a great [MASK]. example_title: Example --- # bert-tiny-domain-adapted-imdb This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the [imdb](https://huggingface.co/datasets/imdb) dataset. It achieves the following results on the evaluation set: - Loss: 3.6873 - Perplexity: 39.94 ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 4.1563 \| 1.0 \| 782 \| 3.7462 \| \| 4.0555 \| 2.0 \| 1564 \| 3.6977 \| \| 4.0285 \| 3.0 \| 2346 \| 3.6963 \| ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
cogbuji/Mr-Grammatology-clinical-problems-Mistral-7B-0.5	cogbuji	2024-02-29T02:56:46Z	16	5	mlx	[ "mlx", "safetensors", "mistral", "medical", "health", "instruct", "finetune", "chatml", "text-generation", "conversational", "en", "base_model:teknium/OpenHermes-2.5-Mistral-7B", "base_model:finetune:teknium/OpenHermes-2.5-Mistral-7B", "license:mit", "region:us" ]	text-generation	2024-02-20T01:35:24Z	--- base_model: teknium/OpenHermes-2.5-Mistral-7B license: mit language: - en model_creator: Chime Ogbuji library_name: mlx model_name: Mr-Grammatology-clinical-problems-Mistral-7B-0.5 pipeline_tag: text-generation prompt_template: '<\|im_start\|>system {system_message}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ' tags: - mlx - medical - health - mistral - instruct - finetune - chatml --- # Mr-Grammatology-clinical-problems-Mistral-7B-0.5 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/651d96a3e8c4c2ebaafc1e7d/uyiryuBhU4y62f4CRxabO.png) The name of the model is a homage to Fela Kuti's song __Mr Grammarticalogy-Lisationalsim Is The Boss__ released on the B-side of his 1976 LP [Excuse O](https://www.discogs.com/release/3149841-Fela-And-The-Africa-70-Excuse-O). It is a 16/32 QLoRa all linear layers finetune of [teknium/OpenHermes-2.5-Mistral-7B](/teknium/OpenHermes-2.5-Mistral-7B) using [controlled natural language (CNL) phrases](https://github.com/chimezie/django-snomed-ct#controlled-natural-language) generated from the September 23rd release of [SNOMED CT United States Edition](https://www.snomed.org/snomed-ct/Use-SNOMED-CT). The general idea is described in [Domain-Specific Biomedical Ontologies, RALM, and Generative Medical Expert Systems](https://chimezie.medium.com/biomedical-ontology-retrieval-augmented-language-models-using-django-snomed-ct-and-ogbujipt-dfa0d0b150d8). It is an experimental model for non-production environments to test how generative AI systems can be trained for use in various medical informatics scenarios. The original model was converted to MLX format, quantized, and then subject to continued pretraining using all the active domain-expert text definitions available in SNOMED-CT at a constant learning rate of 1e-5 using [mlx_lm's LoRa finetuning functionality](https://github.com/ml-explore/mlx-examples/blob/main/llms/mlx_lm/LORA.md) with 16 LoRa layers. It was then trained on a dataset of 336,762 records of medical terminology definition instructions generated from SNOMED-CT using a fork of [django-snomed-ct](https://github.com/chimezie/django-snomed-ct). These definition instructions were generated from the disorder, finding, morphological abnormality, and situation hierarchies in SNOMED-CT. This training step was done using [mlx-tuning-fork](https://github.com/chimezie/mlx-tuning-fork) through 42,096 training iterations, with a batch size of 8 at a time, using LoRa on all linear layers. There were 51,082 records of more granular definition instructions, part of which were incorporated into the training dataset. However, 40% were kept aside for validation. ## Use with mlx ```bash pip install mlx-lm ``` Download and convert. ```bash $ python -m mlx_lm.convert --hf-path cogbuji/Mr-Grammatology-clinical-problems-Mistral-7B-0.5 \ --mlx-path /path/to/mlx/model ``` Generate from prompts in commandline (see [Generate Text with LLMs and MLX](https://github.com/ml-explore/mlx-examples/tree/main/llms) for more options ) ```bash $ python -m mlx_lm.generate --prompt "How is Cardiomyopathy characterized in form?" \ --temp .4 -m 300 --model /path/to/mlx/model --seed 4 ``` ``` Prompt: <\|im_start\|>user How is Cardiomyopathy characterized in form?<\|im_end\|> <\|im_start\|>assistant Cardiomyopathy is characterized in form by a morphologically abnormal structure located in a myocardium structure ``` ## Example of use of 1-shot description prompting Using mlx-tuning-fork with OgbujiPts word looms to construct 1-shot example of description prompting. ```bash $ python -m mlx_tuning_fork.training -nt 1200 -t .4 --loom-file=sct_prompt.toml -f chatml config.yaml ``` ``` Prompt: <\|im_start\|>system Give detailed responses. Use critical thinking and think step-by-step. Don't make up answers if you don't know. Use SNOMED-CT definitions as much as possible, describing characterizations in form of morphological abnormalities involved in diagnoses (their signs), their etiology (causes/basis), their related findings. ## Question ## What are the signs and etiology of Skin ulcer due to diabetes mellitus? ## Answer ## SNOMED-CT defines Skin ulcer due to diabetes mellitus as characterized in form by an ulcer located in a skin structure. Ulcer is a mophologic abnormality. The cause or origin of a disorder is part of its etiology. Skin ulcer due to diabetes mellitus is caused by diabetes mellitus. So, the etiology of Skin ulcer due to diabetes mellitus is diabetes mellitus. Infected ulcer of skin is an infectious process characterized in form by an ulcer located in a skin structure. Since the signs of Skin ulcer due to diabetes mellitus is also an ulcer, Infected ulcer of skin is an example of a disorder with the same signs as Skin ulcer due to diabetes mellitus. <\|im_end\|> <\|im_start\|>user Take a deep breath and work on this problem step by step. ## Question ## The patient has Irritable bowel syndrome. Summarize the the biological processes and signs (characterizations in form) involved in the patient's diagnoses. Give examples of other disorders with the same signs and etiology. <\|im_end\|> <\|im_start\|>assistant Irritable bowel syndrome (SNOMED-CT definition: Irritable bowel syndrome) is a functional disorder of the gastrointestinal tract, characterized in form by abnormal bowel movements. It is a clinical diagnosis, and its signs and symptoms include abdominal pain, bloating, and altered bowel movements (diarrhea, constipation, or both). Etiology: Irritable bowel syndrome is believed to be caused by factors including abnormal gut motility, gastrointestinal dysrhythmias, and psychological factors. Signs: Examples of signs of the disorder include changes in stool consistency and abdominal pain. Irritable bowel syndrome is a functional bowel disorder, which is a category of gastrointestinal disorders with similar signs and symptoms. Examples of disorders with the same signs and etiology include: 1. Functional dyspepsia: It is characterized by an upper abdominal pain or discomfort and has a similar etiology as irritable bowel syndrome. It is a functional disorder of the stomach and small intestine, and its signs include epigastric pain and discomfort. 2. Chronic idiopathic constipation: It is characterized by chronic constipation and has a similar etiology as irritable bowel syndrome. It is a functional disorder of the colon ========== Prompt: 447.658 tokens-per-sec ```
CatBarks/t5_esSEC2_2_tokenizer	CatBarks	2024-02-29T02:52:04Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T02:52:02Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
CatBarks/t5_esSEC2_2	CatBarks	2024-02-29T02:52:02Z	48	0	transformers	[ "transformers", "safetensors", "t5", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	2024-02-29T02:49:29Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
fzzhang/mistral_gsm8k_s_prod_fullS	fzzhang	2024-02-29T02:40:11Z	0	0	peft	[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:mistralai/Mistral-7B-v0.1", "base_model:adapter:mistralai/Mistral-7B-v0.1", "license:apache-2.0", "region:us" ]	null	2024-02-28T19:11:32Z	--- license: apache-2.0 library_name: peft tags: - generated_from_trainer base_model: mistralai/Mistral-7B-v0.1 model-index: - name: mistral_gsm8k_s_prod_fullS results: [] --- <!-- 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. --> # mistral_gsm8k_s_prod_fullS This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) 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: 0.001 - train_batch_size: 4 - eval_batch_size: 8 - seed: 0 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results ### Framework versions - PEFT 0.7.2.dev0 - Transformers 4.37.0.dev0 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.0
Kquant03/Umbra-MoE-4x10.7-GGUF	Kquant03	2024-02-29T02:31:46Z	79	5	null	[ "gguf", "moe", "merge", "mergekit", "dataset:kodonho/SolarM-SakuraSolar-SLERP", "dataset:Sao10K/Sensualize-Solar-10.7B", "dataset:NousResearch/Nous-Hermes-2-SOLAR-10.7B", "dataset:fblgit/UNA-SOLAR-10.7B-Instruct-v1.0", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-01-21T10:04:26Z	--- license: apache-2.0 tags: - moe - merge - mergekit datasets: - kodonho/SolarM-SakuraSolar-SLERP - Sao10K/Sensualize-Solar-10.7B - NousResearch/Nous-Hermes-2-SOLAR-10.7B - fblgit/UNA-SOLAR-10.7B-Instruct-v1.0 --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/TN6IeT8hHjMCVljzVn2Fs.png) # Umbra-MoE-4x10.7 Umbra is an off shoot of the [Lumosia Series] with a Focus in General Knowledge and RP/ERP This model was built around the idea someone wanted a General Assiatant that could also tell Stories/RP/ERP when wanted. This is a very experimental model. It's a combination MoE of Solar models, the models selected are personal favorites. base context is 4k but it stays coherent up to 16k Please let me know how the model works for you. [Join our Discord!](https://discord.gg/ZgU79QDnE2) ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [Q2_K Tiny](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF/blob/main/ggml-model-q2_k.gguf) \| Q2_K \| 2 \| 12 GB\| 14 GB \| smallest, significant quality loss - not recommended for most purposes \| \| [Q3_K_M](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF/blob/main/ggml-model-q3_k_m.gguf) \| Q3_K_M \| 3 \| 15.7 GB\| 17.7 GB \| very small, high quality loss \| \| [Q4_0](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF/blob/main/ggml-model-q4_0.gguf) \| Q4_0 \| 4 \| 20.3 GB\| 22.3 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [Q4_K_M](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF/blob/main/ggml-model-q4_k_m.gguf) \| Q4_K_M \| 4 \| 20.4 GB\| 22.4 GB \| medium, balanced quality - recommended \| \| [Q5_0](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF/blob/main/ggml-model-q5_0.gguf) \| Q5_0 \| 5 \| 24.8 GB\| 26.8 GB \| legacy; large, balanced quality \| \| [Q5_K_M](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF/blob/main/ggml-model-q5_k_m.gguf) \| Q5_K_M \| 5 \| 24.9 GB\| 26.9 GB \| large, balanced quality - recommended \| \| [Q6 XL](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF/blob/main/ggml-model-q6_k.gguf) \| Q6_K \| 6 \| 29.6 GB\| 31.6 GB \| very large, extremely minor degradation \| \| [Q8 XXL](https://huggingface.co/Kquant03/Umbra-MoE-4x10.7-GGUF/blob/main/ggml-model-q8_0.gguf) \| Q8_0 \| 8 \| 38.4 GB\| 40.4 GB \| very large, extremely minor degradation - not recommended \| Template: ChatML ``` ### System: ### USER:{prompt} ### Assistant: ``` Settings: ``` Temp: 1.0 min-p: 0.02-0.1 ``` ## Evals: * Avg: 73.4 * ARC: 70.31 * HellaSwag: 87.81 * MMLU: 66.42 * T-QA: 67.82 * Winogrande: 83.27 * GSM8K: 64.75 ## Examples: ``` User: Tell me an interesting fact. Umbra: The Amazon Rainforest is home to an astounding variety of life forms. It encompasses over five million square kilometers across nine South American countries and holds approximately one-third of all known species on Earth. This biodiversity hotspot supports more than 390 billion individual trees representing 16,000 species. Over two million insect species live here alongside thousands of bird, mammal, amphibian, and reptile species. In this dense forest, indigenous communities have developed intricate knowledge systems that allow them to thrive sustainably within their surroundings. ``` ``` User: Tell me a story about a red haired fox Umbra: In the enchanted forest of Ardenwood, a vibrant world teeming with life and magic, lived a curious creature known as Vixie, whose russet fur glowed against the verdure that surrounded her. Her emerald eyes twinkled with mischief and wonder as she roamed the lush landscape, befriending all who crossed her path. One sunlit afternoon, Vixie found herself weaving amongst a sea of tall grasses swaying gently in the breeze. Ahead lay a shimmering riverbank, where a gathering of animals was assembled around a mystifying sight - a radiant stone pulsing with an ethereal glow. A majestic stag approached Vixie, his voice resonating with authority. He introduced himself as Elthon, leader of this assembly. They had gathered to seek guidance from the celestial gem, said to hold the secrets of the universe within its sparkling depths. Vixie, filled with curiosity, asked if she could partake in their quest for knowledge. Elthon agreed, and they each took turns gazing into the jewel. As Vixie's turn came, she felt a tingling sensation course through her body, her senses heightened as the stone revealed a vision before her. In the dreamlike tableau, Vixie saw herself standing atop a hill overlooking Ardenwood. She watched as the seasons changed, the land thrived, and creatures played out their destinies. It appeared the fates of these beings were intertwined, a tapestry woven together by love, friendship, sacrifice, and growth. When the trance subsided, Vixie returned to the present moment, feeling humbled and grateful. This revelation emboldened her desire to cherish those bonds she shared with others, knowing how vital they were to the beauty and harmony of the enchanted realm. From then on, Vixie continued her adventures with renewed purpose, nurturing friendships and embracing the mysteries of Ardenwood. ``` Umbra-MoE-4x10.7 is a Mixure of Experts (MoE) made with the following models using: * [kodonho/SolarM-SakuraSolar-SLERP](https://huggingface.co/kodonho/SolarM-SakuraSolar-SLERP) * [Sao10K/Sensualize-Solar-10.7B](https://huggingface.co/Sao10K/Sensualize-Solar-10.7B) * [NousResearch/Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B) * [fblgit/UNA-SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/fblgit/UNA-SOLAR-10.7B-Instruct-v1.0) ## 🧩 Configuration ``` base_model: kodonho/SolarM-SakuraSolar-SLERP gate_mode: hidden dtype: bfloat16 experts: - source_model: kodonho/SolarM-SakuraSolar-SLERP positive_prompts: - "versatile" - "helpful" - "factual" - "integrated" - "adaptive" - "comprehensive" - "balanced" negative_prompts: - "specialized" - "narrow" - "focused" - "limited" - "specific" - source_model: Sao10K/Sensualize-Solar-10.7B positive_prompts: - "creative" - "chat" - "discuss" - "culture" - "world" - "expressive" - "detailed" - "imaginative" - "engaging" negative_prompts: - "sorry" - "cannot" - "factual" - "concise" - "straightforward" - "objective" - "dry" - source_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B positive_prompts: - "analytical" - "accurate" - "logical" - "knowledgeable" - "precise" - "calculate" - "compute" - "solve" - "work" - "python" - "javascript" - "programming" - "algorithm" - "tell me" - "assistant" negative_prompts: - "creative" - "abstract" - "imaginative" - "artistic" - "emotional" - "mistake" - "inaccurate" - source_model: fblgit/UNA-SOLAR-10.7B-Instruct-v1.0 positive_prompts: - "instructive" - "clear" - "directive" - "helpful" - "informative" negative_prompts: - "exploratory" - "open-ended" - "narrative" - "speculative" - "artistic" ``` ## 💻 Usage ```python !pip install -qU transformers bitsandbytes accelerate from transformers import AutoTokenizer import transformers import torch model = "Steelskull/Umbra-MoE-4x10.7" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True}, ) messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}] prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```
Kquant03/NeuralTrix-7B-dpo-laser-GGUF	Kquant03	2024-02-29T02:28:26Z	6	2	null	[ "gguf", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-02-14T13:37:51Z	--- license: apache-2.0 language: - en --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/IclpTHDxA6a7xc7TZ5vth.png) # Made using Cultrix's Model, which can be found [here](https://huggingface.co/CultriX/NeuralTrix-7B-dpo). [Join our Discord!](https://discord.gg/ZgU79QDnE2) [BASE MODEL HERE](https://huggingface.co/Kquant03/NeuralTrix-7B-dpo-laser) NeuralTrix-7B-v1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B) * [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3) * [AiMavenAi/AiMaven-Prometheus](https://huggingface.co/AiMavenAi/AiMaven-Prometheus) It was then trained with DPO by Cultrix using: * https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1 I performed laser_snr_math on it afterwards to see if I could improve it. ## 🧩 Configuration ```yaml models: - model: mistralai/Mistral-7B-v0.1 # no parameters necessary for base model - model: mlabonne/OmniBeagle-7B parameters: density: 0.65 weight: 0.4 - model: flemmingmiguel/MBX-7B-v3 parameters: density: 0.6 weight: 0.35 - model: AiMavenAi/AiMaven-Prometheus parameters: density: 0.6 weight: 0.35 merge_method: dare_ties base_model: mistralai/Mistral-7B-v0.1 parameters: int8_mask: true dtype: float16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "CultriX/NeuralTrix-7B-v1" 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"]) ```
Dcolinmorgan/distaster-mlx-model	Dcolinmorgan	2024-02-29T02:26:01Z	113	0	transformers	[ "transformers", "safetensors", "bert", "text-classification", "dataset:Dcolinmorgan/disaster-tw", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-02-27T13:05:55Z	--- license: mit metrics: - accuracy pipeline_tag: text-classification datasets: - Dcolinmorgan/disaster-tw widget: - text: "Waves are crashing all around, the wind is growing stronger, lights are flashing." example_title: "Storm description without keyword" - text: "A cool breeze is passing through the meadow and over the brook tonight" example_title: "No emergency" - text: "Blood was scene at the corner of X and Y" example_title: "Emergency scene" - text: "Two men were seen at the corner of X and Y" example_title: "Normal scene" --- ## Model Name distaster inference from tweets trained locally on M1 max via mlx bert-base-uncased with labels tuned to 2 ### Training Description of the training process. ### Evaluation epoch and accuracy based. ### Weights & Biases This model was trained and evaluated using Weights & Biases. You can see the training and evaluation logs [here](https://api.wandb.ai/links/dcolinmorgan/tpeiht5r).
jq/nllb-1.3b-many-to-many-step800	jq	2024-02-29T02:21:17Z	149	0	transformers	[ "transformers", "safetensors", "m2m_100", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-29T02:16:59Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ICTNLP/Llama-2-7b-chat-TruthX	ICTNLP	2024-02-29T02:20:40Z	186	6	transformers	[ "transformers", "pytorch", "llama", "text-generation", "custom_code", "arxiv:2402.17811", "license:gpl-3.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-27T06:54:34Z	--- license: gpl-3.0 --- # TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space > [Shaolei Zhang](https://zhangshaolei1998.github.io/), [Tian Yu](https://tianyu0313.github.io/), [Yang Feng](https://people.ucas.edu.cn/~yangfeng?language=en)* Model for paper "[TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space](https://arxiv.org/pdf/2402.17811.pdf)". TruthX is an inference-time method to elicit the truthfulness of LLMs by editing their internal representations in truthful space, thereby mitigating the hallucinations of LLMs. On the [TruthfulQA benchmark](https://paperswithcode.com/sota/question-answering-on-truthfulqa), TruthX yields an average enhancement of 20% in truthfulness across 13 advanced LLMs. <div align="center"> <img src="./truthx_results.png" alt="img" width="100%" /> </div> <p align="center"> TruthfulQA MC1 accuracy of TruthX across 13 advanced LLMs </p> This repo provides Llama-2-7B-Chat-TruthX, a Llama-2-7B-Chat model with baked-in TruthX model. You can directly download this baked-in model and use it like standard Llama, no additional operations are required. ## Quick Starts Inference with Llama-2-7B-Chat-TruthX: ```python import torch from transformers import AutoTokenizer, AutoModelForCausalLM llama2chat_with_truthx = "ICTNLP/Llama-2-7b-chat-TruthX" tokenizer = AutoTokenizer.from_pretrained(llama2chat_with_truthx, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(llama2chat_with_truthx, trust_remote_code=True,torch_dtype=torch.float16).cuda() question = "What are the benefits of eating an apple a day?" encoded_inputs = tokenizer(question, return_tensors="pt")["input_ids"] outputs = model.generate(encoded_inputs.cuda())[0, encoded_inputs.shape[-1] :] outputs_text = tokenizer.decode(outputs, skip_special_tokens=True).strip() print(outputs_text) ``` Please refer to [GitHub repo](https://github.com/ictnlp/TruthX) and [our paper](https://arxiv.org/pdf/2402.17811.pdf) for more details. ## Licence Model weights and the inference code are released under The GNU General Public License v3.0 (GPLv3) ## Citation If this repository is useful for you, please cite as: ``` @misc{zhang2024truthx, title={TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space}, author={Shaolei Zhang and Tian Yu and Yang Feng}, year={2024}, eprint={2402.17811}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2402.17811} } ``` If you have any questions, feel free to contact `[email protected]`.
adjohn1313/wizard_sft_blackbox_rlhf_60k	adjohn1313	2024-02-29T02:14:23Z	76	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "awq", "region:us" ]	text-generation	2024-02-29T02:08:02Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
ultimecia/xlm-roberta-base-finetuned-panx-de	ultimecia	2024-02-29T02:14:20Z	115	0	transformers	[ "transformers", "tensorboard", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-02-29T02:02:06Z	--- license: mit base_model: xlm-roberta-base tags: - generated_from_trainer metrics: - f1 model-index: - name: xlm-roberta-base-finetuned-panx-de results: [] --- <!-- 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-de 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: 0.1353 - F1: 0.8480 ## 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: 96 - eval_batch_size: 96 - 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 \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| No log \| 1.0 \| 132 \| 0.1623 \| 0.8116 \| \| No log \| 2.0 \| 264 \| 0.1418 \| 0.8438 \| \| No log \| 3.0 \| 396 \| 0.1353 \| 0.8480 \| ### Framework versions - Transformers 4.38.1 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
Kquant03/Buttercup-4x7B-GGUF	Kquant03	2024-02-29T02:14:09Z	113	8	null	[ "gguf", "moe", "merge", "en", "arxiv:2101.03961", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-01-22T06:54:12Z	--- license: apache-2.0 language: - en tags: - moe - merge --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/qj_lv87mPw8t7KsNU07Uu.png) # "[We] are joined by the bonds of love. And you cannot track that, not with a thousand bloodhounds, and you cannot break it, not with a thousand swords." ## This is the repo for the GGUF files [BASE MODEL](https://huggingface.co/Kquant03/Buttercup-4x7B-bf16) [Join our Discord!](https://discord.gg/uT4CzytfYW) A frankenMoE not only using far better methodology and fundamental understanding of SMoE, but completely focused around intellectual roleplay. This model doesn't actually have redundancy like most MoE does...but if you encounter this, try to keep things fresh with the model by either introducing new concepts often, or through [drμgs](https://github.com/EGjoni/DRUGS). (no not that kind) The models that were implemented are as follows: - [mlabonne/Beagle14-7B](https://huggingface.co/mlabonne/Beagle14-7B) - base - [fblgit/una-cybertron-7b-v3-OMA](https://huggingface.co/fblgit/una-cybertron-7b-v3-OMA) - expert #1 - [rwitz/go-bruins-v2](https://huggingface.co/rwitz/go-bruins-v2) - expert #2 - [mlabonne/Beagle14-7B](https://huggingface.co/mlabonne/Beagle14-7B) - expert #3 - [mlabonne/Beagle14-7B](https://huggingface.co/mlabonne/Beagle14-7B) - expert #4 # Completely mogs mixtral instruct 0.1 across multiple benchmarks at half the size ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/GlhMcDiRhmUOsITmBplVT.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/cK0isGt1Nm2lEXZ9INrfu.png) ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [Q2_K Tiny](https://huggingface.co/Kquant03/Buttercup-4x7B-GGUF/blob/main/ggml-model-q2_k.gguf) \| Q2_K \| 2 \| 7.87 GB\| 9.87 GB \| smallest, significant quality loss - not recommended for most purposes \| \| [Q3_K_M](https://huggingface.co/Kquant03/Buttercup-4x7B-GGUF/blob/main/ggml-model-q3_k_m.gguf) \| Q3_K_M \| 3 \| 10.28 GB\| 12.28 GB \| very small, high quality loss \| \| [Q4_0](https://huggingface.co/Kquant03/Buttercup-4x7B-GGUF/blob/main/ggml-model-q4_0.gguf) \| Q4_0 \| 4 \| 13.3 GB\| 15.3 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [Q4_K_M](https://huggingface.co/Kquant03/Buttercup-4x7B-GGUF/blob/main/ggml-model-q4_k_m.gguf) \| Q4_K_M \| 4 \| 13.32 GB\| 15.32 GB \| medium, balanced quality - recommended \| \| [Q5_0](https://huggingface.co/Kquant03/Buttercup-4x7B-GGUF/blob/main/ggml-model-q5_0.gguf) \| Q5_0 \| 5 \| 16.24 GB\| 18.24 GB \| legacy; large, balanced quality \| \| [Q5_K_M](https://huggingface.co/Kquant03/Buttercup-4x7B-GGUF/blob/main/ggml-model-q5_k_m.gguf) \| Q5_K_M \| 5 \| ~16.24 GB\| ~18.24 GB \| large, balanced quality - recommended \| \| [Q6 XL](https://huggingface.co/Kquant03/Buttercup-4x7B-GGUF/blob/main/ggml-model-q6_k.gguf) \| Q6_K \| 6 \| 19.35 GB\| 21.35 GB \| very large, extremely minor degradation \| \| [Q8 XXL](https://huggingface.co/Kquant03/Buttercup-4x7B-GGUF/blob/main/ggml-model-q8_0.gguf) \| Q8_0 \| 8 \| 25.1 GB\| 27.1 GB \| very large, extremely minor degradation - not recommended \| # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)" ### (from the MistralAI papers...click the quoted question above to navigate to it directly.) The scale of a model is one of the most important axes for better model quality. Given a fixed computing budget, training a larger model for fewer steps is better than training a smaller model for more steps. Mixture of Experts enable models to be pretrained with far less compute, which means you can dramatically scale up the model or dataset size with the same compute budget as a dense model. In particular, a MoE model should achieve the same quality as its dense counterpart much faster during pretraining. So, what exactly is a MoE? In the context of transformer models, a MoE consists of two main elements: Sparse MoE layers are used instead of dense feed-forward network (FFN) layers. MoE layers have a certain number of “experts” (e.g. 32 in my "frankenMoE"), where each expert is a neural network. In practice, the experts are FFNs, but they can also be more complex networks or even a MoE itself, leading to hierarchical MoEs! A gate network or router, that determines which tokens are sent to which expert. For example, in the image below, the token “More” is sent to the second expert, and the token "Parameters” is sent to the first network. As we’ll explore later, we can send a token to more than one expert. How to route a token to an expert is one of the big decisions when working with MoEs - the router is composed of learned parameters and is pretrained at the same time as the rest of the network. At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/up_I0R2TQGjqTShZp_1Sz.png) Switch Layer MoE layer from the [Switch Transformers paper](https://arxiv.org/abs/2101.03961) So, to recap, in MoEs we replace every FFN layer of the transformer model with an MoE layer, which is composed of a gate network and a certain number of experts. Although MoEs provide benefits like efficient pretraining and faster inference compared to dense models, they also come with challenges: Training: MoEs enable significantly more compute-efficient pretraining, but they’ve historically struggled to generalize during fine-tuning, leading to overfitting. Inference: Although a MoE might have many parameters, only some of them are used during inference. This leads to much faster inference compared to a dense model with the same number of parameters. However, all parameters need to be loaded in RAM, so memory requirements are high. For example, [given a MoE like Mixtral 8x7B](https://huggingface.co/blog/moe), we’ll need to have enough VRAM to hold a dense 47B parameter model. Why 47B parameters and not 8 x 7B = 56B? That’s because in MoE models, only the FFN layers are treated as individual experts, and the rest of the model parameters are shared. At the same time, assuming just two experts are being used per token, the inference speed (FLOPs) is like using a 12B model (as opposed to a 14B model), because it computes 2x7B matrix multiplications, but with some layers shared (more on this soon). If all our tokens are sent to just a few popular experts, that will make training inefficient. In a normal MoE training, the gating network converges to mostly activate the same few experts. This self-reinforces as favored experts are trained quicker and hence selected more. To mitigate this, an auxiliary loss is added to encourage giving all experts equal importance. This loss ensures that all experts receive a roughly equal number of training examples. The following sections will also explore the concept of expert capacity, which introduces a threshold of how many tokens can be processed by an expert. In transformers, the auxiliary loss is exposed via the aux_loss parameter. ## "Wait...but you called this a frankenMoE?" The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously.
ch2vod/spamllama_labeler_12.8b	ch2vod	2024-02-29T02:08:41Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-02-29T02:08:31Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Kquant03/Buttercup-4x7B-V2-bf16	Kquant03	2024-02-29T02:08:04Z	8	5	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "merge", "en", "arxiv:2101.03961", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-15T19:15:45Z	--- license: apache-2.0 language: - en tags: - moe - merge --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/IxUHh1KtVmEgykXC6ya66.png) # "[We] are joined by the bonds of love. And you cannot track that, not with a thousand bloodhounds, and you cannot break it, not with a thousand swords." [GGUF FILES HERE](https://huggingface.co/Kquant03/Buttercup-V2-GGUF) [Join our Discord!](https://discord.gg/uT4CzytfYW) I will be lasering this model, so stay tuned. Hopefully this an improvement upon my [original model](https://huggingface.co/Kquant03/Buttercup-4x7B-bf16). The config looks like this...(detailed version is in the files and versions): - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - base - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - expert #1 - [cognitivecomputations/samantha-1.1-westlake-7b](https://huggingface.co/cognitivecomputations/samantha-1.1-westlake-7b) - expert #2 - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - expert #3 - [Kukedlc/Triunvirato-7b](https://huggingface.co/Kukedlc/Triunvirato-7b) - expert #4 # Huge improvement upon the base Buttercup model!!!! ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/f2kxGJNw2iVBExYHiydB0.png) # Laser version is rank 3 in the world for roleplay. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/w4-E6jF1nwd_HAO96Ldko.png) # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)" ### (from the MistralAI papers...click the quoted question above to navigate to it directly.) The scale of a model is one of the most important axes for better model quality. Given a fixed computing budget, training a larger model for fewer steps is better than training a smaller model for more steps. Mixture of Experts enable models to be pretrained with far less compute, which means you can dramatically scale up the model or dataset size with the same compute budget as a dense model. In particular, a MoE model should achieve the same quality as its dense counterpart much faster during pretraining. So, what exactly is a MoE? In the context of transformer models, a MoE consists of two main elements: Sparse MoE layers are used instead of dense feed-forward network (FFN) layers. MoE layers have a certain number of “experts” (e.g. 32 in my "frankenMoE"), where each expert is a neural network. In practice, the experts are FFNs, but they can also be more complex networks or even a MoE itself, leading to hierarchical MoEs! A gate network or router, that determines which tokens are sent to which expert. For example, in the image below, the token “More” is sent to the second expert, and the token "Parameters” is sent to the first network. As we’ll explore later, we can send a token to more than one expert. How to route a token to an expert is one of the big decisions when working with MoEs - the router is composed of learned parameters and is pretrained at the same time as the rest of the network. At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/up_I0R2TQGjqTShZp_1Sz.png) Switch Layer MoE layer from the [Switch Transformers paper](https://arxiv.org/abs/2101.03961) So, to recap, in MoEs we replace every FFN layer of the transformer model with an MoE layer, which is composed of a gate network and a certain number of experts. Although MoEs provide benefits like efficient pretraining and faster inference compared to dense models, they also come with challenges: Training: MoEs enable significantly more compute-efficient pretraining, but they’ve historically struggled to generalize during fine-tuning, leading to overfitting. Inference: Although a MoE might have many parameters, only some of them are used during inference. This leads to much faster inference compared to a dense model with the same number of parameters. However, all parameters need to be loaded in RAM, so memory requirements are high. For example, [given a MoE like Mixtral 8x7B](https://huggingface.co/blog/moe), we’ll need to have enough VRAM to hold a dense 47B parameter model. Why 47B parameters and not 8 x 7B = 56B? That’s because in MoE models, only the FFN layers are treated as individual experts, and the rest of the model parameters are shared. At the same time, assuming just two experts are being used per token, the inference speed (FLOPs) is like using a 12B model (as opposed to a 14B model), because it computes 2x7B matrix multiplications, but with some layers shared (more on this soon). If all our tokens are sent to just a few popular experts, that will make training inefficient. In a normal MoE training, the gating network converges to mostly activate the same few experts. This self-reinforces as favored experts are trained quicker and hence selected more. To mitigate this, an auxiliary loss is added to encourage giving all experts equal importance. This loss ensures that all experts receive a roughly equal number of training examples. The following sections will also explore the concept of expert capacity, which introduces a threshold of how many tokens can be processed by an expert. In transformers, the auxiliary loss is exposed via the aux_loss parameter. ## "Wait...but you called this a frankenMoE?" The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously.
Kquant03/NurseButtercup-4x7B-bf16	Kquant03	2024-02-29T02:01:18Z	5	1	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "merge", "en", "arxiv:2101.03961", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-26T04:36:53Z	--- license: apache-2.0 language: - en tags: - moe - merge --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/IJUYoGvKtUF8O0as3hLMM.png) # "[We] are joined by the bonds of love. And you cannot track that, not with a thousand bloodhounds, and you cannot break it, not with a thousand swords." [GGUF FILES HERE](https://huggingface.co/Kquant03/NurseButtercup-4x7B-GGUF) [Join our Discord!](https://discord.gg/uT4CzytfYW) Going to try a laser scan of this model with Fernando from Cognitive Computations. It is a FrankenMoE. The config looks like this...(detailed version is in the files and versions): - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - base - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - expert #1 - [cognitivecomputations/samantha-1.1-westlake-7b-laser](https://huggingface.co/cognitivecomputations/samantha-1.1-westlake-7b-laser) - expert #2 - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - expert #3 - [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) - expert #4 # Will upload to eval eventually. # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)" ### (from the MistralAI papers...click the quoted question above to navigate to it directly.) The scale of a model is one of the most important axes for better model quality. Given a fixed computing budget, training a larger model for fewer steps is better than training a smaller model for more steps. Mixture of Experts enable models to be pretrained with far less compute, which means you can dramatically scale up the model or dataset size with the same compute budget as a dense model. In particular, a MoE model should achieve the same quality as its dense counterpart much faster during pretraining. So, what exactly is a MoE? In the context of transformer models, a MoE consists of two main elements: Sparse MoE layers are used instead of dense feed-forward network (FFN) layers. MoE layers have a certain number of “experts” (e.g. 32 in my "frankenMoE"), where each expert is a neural network. In practice, the experts are FFNs, but they can also be more complex networks or even a MoE itself, leading to hierarchical MoEs! A gate network or router, that determines which tokens are sent to which expert. For example, in the image below, the token “More” is sent to the second expert, and the token "Parameters” is sent to the first network. As we’ll explore later, we can send a token to more than one expert. How to route a token to an expert is one of the big decisions when working with MoEs - the router is composed of learned parameters and is pretrained at the same time as the rest of the network. At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/up_I0R2TQGjqTShZp_1Sz.png) Switch Layer MoE layer from the [Switch Transformers paper](https://arxiv.org/abs/2101.03961) So, to recap, in MoEs we replace every FFN layer of the transformer model with an MoE layer, which is composed of a gate network and a certain number of experts. Although MoEs provide benefits like efficient pretraining and faster inference compared to dense models, they also come with challenges: Training: MoEs enable significantly more compute-efficient pretraining, but they’ve historically struggled to generalize during fine-tuning, leading to overfitting. Inference: Although a MoE might have many parameters, only some of them are used during inference. This leads to much faster inference compared to a dense model with the same number of parameters. However, all parameters need to be loaded in RAM, so memory requirements are high. For example, [given a MoE like Mixtral 8x7B](https://huggingface.co/blog/moe), we’ll need to have enough VRAM to hold a dense 47B parameter model. Why 47B parameters and not 8 x 7B = 56B? That’s because in MoE models, only the FFN layers are treated as individual experts, and the rest of the model parameters are shared. At the same time, assuming just two experts are being used per token, the inference speed (FLOPs) is like using a 12B model (as opposed to a 14B model), because it computes 2x7B matrix multiplications, but with some layers shared (more on this soon). If all our tokens are sent to just a few popular experts, that will make training inefficient. In a normal MoE training, the gating network converges to mostly activate the same few experts. This self-reinforces as favored experts are trained quicker and hence selected more. To mitigate this, an auxiliary loss is added to encourage giving all experts equal importance. This loss ensures that all experts receive a roughly equal number of training examples. The following sections will also explore the concept of expert capacity, which introduces a threshold of how many tokens can be processed by an expert. In transformers, the auxiliary loss is exposed via the aux_loss parameter. ## "Wait...but you called this a frankenMoE?" The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously.
Kquant03/NurseButtercup-4x7B-GGUF	Kquant03	2024-02-29T02:01:04Z	36	3	null	[ "gguf", "moe", "merge", "en", "arxiv:2101.03961", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-02-26T16:07:51Z	--- license: apache-2.0 language: - en tags: - moe - merge --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/IJUYoGvKtUF8O0as3hLMM.png) # "[We] are joined by the bonds of love. And you cannot track that, not with a thousand bloodhounds, and you cannot break it, not with a thousand swords." [BASE MODEL HERE](https://huggingface.co/Kquant03/NurseButtercup-4x7B-bf16) [Join our Discord!](https://discord.gg/uT4CzytfYW) Going to try a laser scan of this model with Fernando from Cognitive Computations. It is a FrankenMoE. The config looks like this...(detailed version is in the files and versions): - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - base - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - expert #1 - [cognitivecomputations/samantha-1.1-westlake-7b-laser](https://huggingface.co/cognitivecomputations/samantha-1.1-westlake-7b-laser) - expert #2 - [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo) - expert #3 - [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) - expert #4 # Will upload to eval eventually. # "[What is a Mixture of Experts (MoE)?](https://huggingface.co/blog/moe)" ### (from the MistralAI papers...click the quoted question above to navigate to it directly.) The scale of a model is one of the most important axes for better model quality. Given a fixed computing budget, training a larger model for fewer steps is better than training a smaller model for more steps. Mixture of Experts enable models to be pretrained with far less compute, which means you can dramatically scale up the model or dataset size with the same compute budget as a dense model. In particular, a MoE model should achieve the same quality as its dense counterpart much faster during pretraining. So, what exactly is a MoE? In the context of transformer models, a MoE consists of two main elements: Sparse MoE layers are used instead of dense feed-forward network (FFN) layers. MoE layers have a certain number of “experts” (e.g. 32 in my "frankenMoE"), where each expert is a neural network. In practice, the experts are FFNs, but they can also be more complex networks or even a MoE itself, leading to hierarchical MoEs! A gate network or router, that determines which tokens are sent to which expert. For example, in the image below, the token “More” is sent to the second expert, and the token "Parameters” is sent to the first network. As we’ll explore later, we can send a token to more than one expert. How to route a token to an expert is one of the big decisions when working with MoEs - the router is composed of learned parameters and is pretrained at the same time as the rest of the network. At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/up_I0R2TQGjqTShZp_1Sz.png) Switch Layer MoE layer from the [Switch Transformers paper](https://arxiv.org/abs/2101.03961) So, to recap, in MoEs we replace every FFN layer of the transformer model with an MoE layer, which is composed of a gate network and a certain number of experts. Although MoEs provide benefits like efficient pretraining and faster inference compared to dense models, they also come with challenges: Training: MoEs enable significantly more compute-efficient pretraining, but they’ve historically struggled to generalize during fine-tuning, leading to overfitting. Inference: Although a MoE might have many parameters, only some of them are used during inference. This leads to much faster inference compared to a dense model with the same number of parameters. However, all parameters need to be loaded in RAM, so memory requirements are high. For example, [given a MoE like Mixtral 8x7B](https://huggingface.co/blog/moe), we’ll need to have enough VRAM to hold a dense 47B parameter model. Why 47B parameters and not 8 x 7B = 56B? That’s because in MoE models, only the FFN layers are treated as individual experts, and the rest of the model parameters are shared. At the same time, assuming just two experts are being used per token, the inference speed (FLOPs) is like using a 12B model (as opposed to a 14B model), because it computes 2x7B matrix multiplications, but with some layers shared (more on this soon). If all our tokens are sent to just a few popular experts, that will make training inefficient. In a normal MoE training, the gating network converges to mostly activate the same few experts. This self-reinforces as favored experts are trained quicker and hence selected more. To mitigate this, an auxiliary loss is added to encourage giving all experts equal importance. This loss ensures that all experts receive a roughly equal number of training examples. The following sections will also explore the concept of expert capacity, which introduces a threshold of how many tokens can be processed by an expert. In transformers, the auxiliary loss is exposed via the aux_loss parameter. ## "Wait...but you called this a frankenMoE?" The difference between MoE and "frankenMoE" lies in the fact that the router layer in a model like the one on this repo is not trained simultaneously.
intvy/setfit-absa-all-mpnet-base-v2-laptops-polarity	intvy	2024-02-29T01:59:11Z	4	0	setfit	[ "setfit", "safetensors", "mpnet", "absa", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:sentence-transformers/all-mpnet-base-v2", "base_model:finetune:sentence-transformers/all-mpnet-base-v2", "model-index", "region:us" ]	text-classification	2024-02-29T01:59:11Z	--- library_name: setfit tags: - setfit - absa - sentence-transformers - text-classification - generated_from_setfit_trainer metrics: - accuracy widget: - text: louder and the mouse didnt break:I wish the volume could be louder and the mouse didnt break after only a month. - text: + + (sales, service,:BEST BUY - 5 STARS + + + (sales, service, respect for old men who aren't familiar with the technology) DELL COMPUTERS - 3 stars DELL SUPPORT - owes a me a couple - text: back and my built-in webcam and built-:I got it back and my built-in webcam and built-in mic were shorting out anytime I touched the lid, (mind you this was my means of communication with my fiance who was deployed) but I suffered thru it and would constandly have to reset the computer to be able to use my cam and mic anytime they went out. - text: after i install Mozzilla firfox i love every:the only fact i dont like about apples is they generally use safari and i dont use safari but after i install Mozzilla firfox i love every single bit about it. - text: in webcam and built-in mic were shorting out:I got it back and my built-in webcam and built-in mic were shorting out anytime I touched the lid, (mind you this was my means of communication with my fiance who was deployed) but I suffered thru it and would constandly have to reset the computer to be able to use my cam and mic anytime they went out. pipeline_tag: text-classification inference: false base_model: sentence-transformers/all-mpnet-base-v2 model-index: - name: SetFit Polarity Model with sentence-transformers/all-mpnet-base-v2 results: - task: type: text-classification name: Text Classification dataset: name: tomaarsen/setfit-absa-semeval-laptops type: unknown split: test metrics: - type: accuracy value: 0.7007874015748031 name: Accuracy --- # SetFit Polarity Model with sentence-transformers/all-mpnet-base-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of classifying aspect polarities. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. This model was trained within the context of a larger system for ABSA, which looks like so: 1. Use a spaCy model to select possible aspect span candidates. 2. Use a SetFit model to filter these possible aspect span candidates. 3. Use this SetFit model to classify the filtered aspect span candidates. ## Model Details ### Model Description - Model Type: SetFit - Sentence Transformer body: [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) - Classification head: a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - spaCy Model: en_core_web_sm - SetFitABSA Aspect Model: [joshuasundance/setfit-absa-all-MiniLM-L6-v2-laptops-aspect](https://huggingface.co/joshuasundance/setfit-absa-all-MiniLM-L6-v2-laptops-aspect) - SetFitABSA Polarity Model: [joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity](https://huggingface.co/joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity) - Maximum Sequence Length: 384 tokens - Number of Classes: 4 classes <!-- - Training Dataset: [tomaarsen/setfit-absa-semeval-laptops](https://huggingface.co/datasets/tomaarsen/setfit-absa-semeval-laptops) --> <!-- - Language: Unknown --> <!-- - License: Unknown --> ### Model Sources - Repository: [SetFit on GitHub](https://github.com/huggingface/setfit) - Paper: [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - Blogpost: [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ### Model Labels \| Label \| Examples \| \|:---------\|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| neutral \| <ul><li>'skip taking the cord with me because:I charge it at night and skip taking the cord with me because of the good battery life.'</li><li>'The tech guy then said the:The tech guy then said the service center does not do 1-to-1 exchange and I have to direct my concern to the "sales" team, which is the retail shop which I bought my netbook from.'</li><li>'all dark, power light steady, hard:\xa0One night I turned the freaking thing off after using it, the next day I turn it on, no GUI, screen all dark, power light steady, hard drive light steady and not flashing as it usually does.'</li></ul> \| \| positive \| <ul><li>'of the good battery life.:I charge it at night and skip taking the cord with me because of the good battery life.'</li><li>'is of high quality, has a:it is of high quality, has a killer GUI, is extremely stable, is highly expandable, is bundled with lots of very good applications, is easy to use, and is absolutely gorgeous.'</li><li>'has a killer GUI, is extremely:it is of high quality, has a killer GUI, is extremely stable, is highly expandable, is bundled with lots of very good applications, is easy to use, and is absolutely gorgeous.'</li></ul> \| \| negative \| <ul><li>'then said the service center does not do:The tech guy then said the service center does not do 1-to-1 exchange and I have to direct my concern to the "sales" team, which is the retail shop which I bought my netbook from.'</li><li>'concern to the "sales" team, which is:The tech guy then said the service center does not do 1-to-1 exchange and I have to direct my concern to the "sales" team, which is the retail shop which I bought my netbook from.'</li><li>'on, no GUI, screen all:\xa0One night I turned the freaking thing off after using it, the next day I turn it on, no GUI, screen all dark, power light steady, hard drive light steady and not flashing as it usually does.'</li></ul> \| \| conflict \| <ul><li>'-No backlit keyboard, but not:-No backlit keyboard, but not an issue for me.'</li><li>"to replace the battery once, but:I did have to replace the battery once, but that was only a couple months ago and it's been working perfect ever since."</li></ul> \| ## Evaluation ### Metrics \| Label \| Accuracy \| \|:--------\|:---------\| \| all \| 0.7008 \| ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import AbsaModel # Download from the 🤗 Hub model = AbsaModel.from_pretrained( "joshuasundance/setfit-absa-all-MiniLM-L6-v2-laptops-aspect", "joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity", spacy_model="en_core_web_sm", ) # Run inference preds = model("This laptop meets every expectation and Windows 7 is great!") ``` <!-- ### Downstream Use List how someone could finetune this model on their own dataset. --> <!-- ### Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. --> <!-- ## Bias, Risks and Limitations What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. --> <!-- ### Recommendations What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. --> ## Training Details ### Training Set Metrics \| Training set \| Min \| Median \| Max \| \|:-------------\|:----\|:--------\|:----\| \| Word count \| 3 \| 25.5873 \| 48 \| \| Label \| Training Sample Count \| \|:---------\|:----------------------\| \| conflict \| 2 \| \| negative \| 45 \| \| neutral \| 30 \| \| positive \| 49 \| ### Training Hyperparameters - batch_size: (128, 128) - num_epochs: (5, 5) - max_steps: -1 - sampling_strategy: oversampling - body_learning_rate: (2e-05, 1e-05) - head_learning_rate: 0.01 - loss: CosineSimilarityLoss - distance_metric: cosine_distance - margin: 0.25 - end_to_end: False - use_amp: True - warmup_proportion: 0.1 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: True ### Training Results \| Epoch \| Step \| Training Loss \| Validation Loss \| \|:----------:\|:------:\|:-------------:\|:---------------:\| \| 0.0120 \| 1 \| 0.2721 \| - \| \| 0.6024 \| 50 \| 0.0894 \| 0.2059 \| \| 1.2048 \| 100 \| 0.0014 \| 0.2309 \| \| 1.8072 \| 150 \| 0.0006 \| 0.2359 \| \| 2.4096 \| 200 \| 0.0005 \| 0.2373 \| \| 3.0120 \| 250 \| 0.0004 \| 0.2364 \| \| 3.6145 \| 300 \| 0.0003 \| 0.2371 \| * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.11.7 - SetFit: 1.0.3 - Sentence Transformers: 2.3.0 - spaCy: 3.7.2 - Transformers: 4.37.2 - PyTorch: 2.1.2+cu118 - Datasets: 2.16.1 - Tokenizers: 0.15.1 ## Citation ### BibTeX ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ``` <!-- ## Glossary Clearly define terms in order to be accessible across audiences. --> <!-- ## Model Card Authors Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. --> <!-- ## Model Card Contact Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->
intvy/setfit-absa-all-MiniLM-L6-v2-laptops-aspect	intvy	2024-02-29T01:58:44Z	6	0	setfit	[ "setfit", "safetensors", "bert", "absa", "sentence-transformers", "text-classification", "generated_from_setfit_trainer", "arxiv:2209.11055", "base_model:sentence-transformers/all-MiniLM-L6-v2", "base_model:finetune:sentence-transformers/all-MiniLM-L6-v2", "model-index", "region:us" ]	text-classification	2024-02-29T01:58:44Z	--- library_name: setfit tags: - setfit - absa - sentence-transformers - text-classification - generated_from_setfit_trainer metrics: - accuracy widget: - text: camera:It has no camera but, I can always buy and install one easy. - text: Acer:Acer was no help and Garmin could not determine the problem(after spending about 2 hours with me), so I returned it and purchased a Toshiba R700 that seems even nicer and I was able to load all of my software with no problem. - text: memory:I've been impressed with the battery life and the performance for such a small amount of memory. - text: speed:Yes, a Mac is much more money than the average laptop out there, but there is no comparison in style, speed and just cool factor. - text: fiance:I got it back and my built-in webcam and built-in mic were shorting out anytime I touched the lid, (mind you this was my means of communication with my fiance who was deployed) but I suffered thru it and would constandly have to reset the computer to be able to use my cam and mic anytime they went out. pipeline_tag: text-classification inference: false base_model: sentence-transformers/all-MiniLM-L6-v2 model-index: - name: SetFit Aspect Model with sentence-transformers/all-MiniLM-L6-v2 results: - task: type: text-classification name: Text Classification dataset: name: tomaarsen/setfit-absa-semeval-laptops type: unknown split: test metrics: - type: accuracy value: 0.8239700374531835 name: Accuracy --- # SetFit Aspect Model with sentence-transformers/all-MiniLM-L6-v2 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification. In particular, this model is in charge of filtering aspect span candidates. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. This model was trained within the context of a larger system for ABSA, which looks like so: 1. Use a spaCy model to select possible aspect span candidates. 2. Use this SetFit model to filter these possible aspect span candidates. 3. Use a SetFit model to classify the filtered aspect span candidates. ## Model Details ### Model Description - Model Type: SetFit - Sentence Transformer body: [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) - Classification head: a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - spaCy Model: en_core_web_sm - SetFitABSA Aspect Model: [joshuasundance/setfit-absa-all-MiniLM-L6-v2-laptops-aspect](https://huggingface.co/joshuasundance/setfit-absa-all-MiniLM-L6-v2-laptops-aspect) - SetFitABSA Polarity Model: [joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity](https://huggingface.co/joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity) - Maximum Sequence Length: 256 tokens - Number of Classes: 2 classes <!-- - Training Dataset: [tomaarsen/setfit-absa-semeval-laptops](https://huggingface.co/datasets/tomaarsen/setfit-absa-semeval-laptops) --> <!-- - Language: Unknown --> <!-- - License: Unknown --> ### Model Sources - Repository: [SetFit on GitHub](https://github.com/huggingface/setfit) - Paper: [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055) - Blogpost: [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit) ### Model Labels \| Label \| Examples \| \|:----------\|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\| \| aspect \| <ul><li>'cord:I charge it at night and skip taking the cord with me because of the good battery life.'</li><li>'battery life:I charge it at night and skip taking the cord with me because of the good battery life.'</li><li>'service center:The tech guy then said the service center does not do 1-to-1 exchange and I have to direct my concern to the "sales" team, which is the retail shop which I bought my netbook from.'</li></ul> \| \| no aspect \| <ul><li>'night:I charge it at night and skip taking the cord with me because of the good battery life.'</li><li>'skip:I charge it at night and skip taking the cord with me because of the good battery life.'</li><li>'exchange:The tech guy then said the service center does not do 1-to-1 exchange and I have to direct my concern to the "sales" team, which is the retail shop which I bought my netbook from.'</li></ul> \| ## Evaluation ### Metrics \| Label \| Accuracy \| \|:--------\|:---------\| \| all \| 0.8240 \| ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import AbsaModel # Download from the 🤗 Hub model = AbsaModel.from_pretrained( "joshuasundance/setfit-absa-all-MiniLM-L6-v2-laptops-aspect", "joshuasundance/setfit-absa-all-mpnet-base-v2-laptops-polarity", spacy_model="en_core_web_sm", ) # Run inference preds = model("This laptop meets every expectation and Windows 7 is great!") ``` <!-- ### Downstream Use List how someone could finetune this model on their own dataset. --> <!-- ### Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. --> <!-- ## Bias, Risks and Limitations What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. --> <!-- ### Recommendations What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. --> ## Training Details ### Training Set Metrics \| Training set \| Min \| Median \| Max \| \|:-------------\|:----\|:--------\|:----\| \| Word count \| 2 \| 21.1510 \| 42 \| \| Label \| Training Sample Count \| \|:----------\|:----------------------\| \| no aspect \| 119 \| \| aspect \| 126 \| ### Training Hyperparameters - batch_size: (128, 128) - num_epochs: (5, 5) - max_steps: -1 - sampling_strategy: oversampling - body_learning_rate: (2e-05, 1e-05) - head_learning_rate: 0.01 - loss: CosineSimilarityLoss - distance_metric: cosine_distance - margin: 0.25 - end_to_end: False - use_amp: True - warmup_proportion: 0.1 - seed: 42 - eval_max_steps: -1 - load_best_model_at_end: True ### Training Results \| Epoch \| Step \| Training Loss \| Validation Loss \| \|:----------:\|:-------:\|:-------------:\|:---------------:\| \| 0.0042 \| 1 \| 0.3776 \| - \| \| 0.2110 \| 50 \| 0.2644 \| 0.2622 \| \| 0.4219 \| 100 \| 0.2248 \| 0.2437 \| \| 0.6329 \| 150 \| 0.0059 \| 0.2238 \| \| 0.8439 \| 200 \| 0.0017 \| 0.2326 \| \| 1.0549 \| 250 \| 0.0012 \| 0.2382 \| \| 1.2658 \| 300 \| 0.0008 \| 0.2455 \| \| 1.4768 \| 350 \| 0.0006 \| 0.2328 \| \| 1.6878 \| 400 \| 0.0005 \| 0.243 \| * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.11.7 - SetFit: 1.0.3 - Sentence Transformers: 2.3.0 - spaCy: 3.7.2 - Transformers: 4.37.2 - PyTorch: 2.1.2+cu118 - Datasets: 2.16.1 - Tokenizers: 0.15.1 ## Citation ### BibTeX ```bibtex @article{https://doi.org/10.48550/arxiv.2209.11055, doi = {10.48550/ARXIV.2209.11055}, url = {https://arxiv.org/abs/2209.11055}, author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren}, keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {Efficient Few-Shot Learning Without Prompts}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} } ``` <!-- ## Glossary Clearly define terms in order to be accessible across audiences. --> <!-- ## Model Card Authors Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. --> <!-- ## Model Card Contact Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->
roseruski/autotrain-xp6fd-5n2o9	roseruski	2024-02-28T23:58:05Z	119	0	transformers	[ "transformers", "safetensors", "distilbert", "text-classification", "autotrain", "dataset:autotrain-xp6fd-5n2o9/autotrain-data", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-02-28T23:57:30Z	--- tags: - autotrain - text-classification widget: - text: "I love AutoTrain" datasets: - autotrain-xp6fd-5n2o9/autotrain-data --- # Model Trained Using AutoTrain - Problem type: Text Classification ## Validation Metrics loss: 0.047194674611091614 f1: 0.962457337883959 precision: 0.9791666666666666 recall: 0.9463087248322147 auc: 0.9930245807106035 accuracy: 0.9901345291479821
Lienid/nous-twelve	Lienid	2024-02-28T21:05:01Z	4	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-28T17:16:27Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Mantis-VL/mfuyu_v2_8192_720p-5500	Mantis-VL	2024-02-28T21:04:16Z	5	0	transformers	[ "transformers", "safetensors", "fuyu", "text-generation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-02-28T20:59:03Z	--- tags: - generated_from_trainer model-index: - name: mfuyu_v2_8192_720p-5500 results: [] --- <!-- 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. --> # mfuyu_v2_8192_720p-5500 This model was trained from scratch 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: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Framework versions - Transformers 4.37.0 - Pytorch 2.1.2 - Datasets 2.17.1 - Tokenizers 0.15.0
MayaDG/autotrain-abquo-3fhoy	MayaDG	2024-02-28T21:00:13Z	194	0	transformers	[ "transformers", "safetensors", "vit", "image-classification", "autotrain", "dataset:autotrain-abquo-3fhoy/autotrain-data", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2024-02-28T20:59:39Z	--- tags: - autotrain - image-classification widget: - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg example_title: Tiger - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg example_title: Teapot - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg example_title: Palace datasets: - autotrain-abquo-3fhoy/autotrain-data --- # Model Trained Using AutoTrain - Problem type: Image Classification ## Validation Metricsg loss: 0.21081779897212982 f1: 0.9487179487179487 precision: 0.9487179487179487 recall: 0.9487179487179487 auc: 0.9721767594108021 accuracy: 0.936
Mantis-VL/mfuyu_v2_3072_480p-7000	Mantis-VL	2024-02-28T20:59:04Z	6	0	transformers	[ "transformers", "safetensors", "fuyu", "text-generation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-02-28T20:51:15Z	--- tags: - generated_from_trainer model-index: - name: mfuyu_v2_3072_480p-7000 results: [] --- <!-- 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. --> # mfuyu_v2_3072_480p-7000
tanatapanun/fine-tuned-FLAN-T5-20-epochs-wanglab-512-output	tanatapanun	2024-02-28T20:56:35Z	108	0	transformers	[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2024-02-28T19:22:00Z	--- tags: - generated_from_trainer metrics: - rouge model-index: - name: fine-tuned-FLAN-T5-20-epochs-wanglab-512-output results: [] --- <!-- 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. --> # fine-tuned-FLAN-T5-20-epochs-wanglab-512-output This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. It achieves the following results on the evaluation set: - Loss: 6.0705 - Rouge1: 0.1508 - Rouge2: 0.0272 - Rougel: 0.1374 - Rougelsum: 0.1351 - Bertscore F1: 0.8553 - Bleurt Score: -1.2097 - Gen Len: 14.69 ## 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: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Bertscore F1 \| Bleurt Score \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\|:------:\|:------:\|:---------:\|:------------:\|:------------:\|:-------:\| \| No log \| 1.0 \| 301 \| 11.0933 \| 0.065 \| 0.0148 \| 0.0596 \| 0.0595 \| 0.7859 \| -1.4402 \| 18.92 \| \| 20.9249 \| 2.0 \| 602 \| 9.2324 \| 0.0604 \| 0.0154 \| 0.0556 \| 0.0554 \| 0.7869 \| -1.3807 \| 17.42 \| \| 20.9249 \| 3.0 \| 903 \| 7.6254 \| 0.0681 \| 0.0192 \| 0.0632 \| 0.0627 \| 0.7978 \| -1.4375 \| 18.42 \| \| 11.3584 \| 4.0 \| 1204 \| 6.7112 \| 0.0614 \| 0.0073 \| 0.0578 \| 0.0582 \| 0.8076 \| -1.3157 \| 14.34 \| \| 8.9106 \| 5.0 \| 1505 \| 6.6742 \| 0.0701 \| 0.0204 \| 0.0638 \| 0.0635 \| 0.7968 \| -1.3894 \| 17.29 \| \| 8.9106 \| 6.0 \| 1806 \| 5.9658 \| 0.0836 \| 0.0145 \| 0.074 \| 0.0742 \| 0.818 \| -1.3081 \| 13.76 \| \| 7.8674 \| 7.0 \| 2107 \| 5.7095 \| 0.113 \| 0.025 \| 0.1061 \| 0.1078 \| 0.8433 \| -1.4119 \| 13.71 \| \| 7.8674 \| 8.0 \| 2408 \| 5.6269 \| 0.0987 \| 0.0147 \| 0.0933 \| 0.0939 \| 0.8201 \| -1.2529 \| 15.32 \| \| 6.7786 \| 9.0 \| 2709 \| 5.5192 \| 0.1133 \| 0.0203 \| 0.1038 \| 0.1051 \| 0.8484 \| -1.3751 \| 13.75 \| \| 6.3646 \| 10.0 \| 3010 \| 5.4626 \| 0.1347 \| 0.0276 \| 0.122 \| 0.1236 \| 0.8501 \| -1.278 \| 13.16 \| \| 6.3646 \| 11.0 \| 3311 \| 5.4467 \| 0.103 \| 0.0172 \| 0.0951 \| 0.0943 \| 0.8263 \| -1.3587 \| 15.48 \| \| 5.6998 \| 12.0 \| 3612 \| 5.4587 \| 0.126 \| 0.0326 \| 0.1191 \| 0.1183 \| 0.8474 \| -1.2782 \| 15.86 \| \| 5.6998 \| 13.0 \| 3913 \| 5.4846 \| 0.1523 \| 0.0325 \| 0.1407 \| 0.1408 \| 0.8528 \| -1.2406 \| 14.82 \| \| 5.2971 \| 14.0 \| 4214 \| 5.6166 \| 0.1363 \| 0.0275 \| 0.1279 \| 0.1247 \| 0.8512 \| -1.2827 \| 14.7 \| \| 4.9391 \| 15.0 \| 4515 \| 5.6821 \| 0.1479 \| 0.0238 \| 0.136 \| 0.1342 \| 0.8545 \| -1.2217 \| 14.72 \| \| 4.9391 \| 16.0 \| 4816 \| 5.7849 \| 0.1577 \| 0.0307 \| 0.1455 \| 0.1445 \| 0.8566 \| -1.1756 \| 15.25 \| \| 4.6035 \| 17.0 \| 5117 \| 5.8945 \| 0.1313 \| 0.0234 \| 0.1214 \| 0.1199 \| 0.8525 \| -1.2609 \| 14.67 \| \| 4.6035 \| 18.0 \| 5418 \| 5.9956 \| 0.1506 \| 0.0315 \| 0.1367 \| 0.1348 \| 0.8542 \| -1.2107 \| 14.61 \| \| 4.3893 \| 19.0 \| 5719 \| 6.0337 \| 0.1449 \| 0.0294 \| 0.1337 \| 0.1317 \| 0.8553 \| -1.2173 \| 14.49 \| \| 4.245 \| 20.0 \| 6020 \| 6.0705 \| 0.1508 \| 0.0272 \| 0.1374 \| 0.1351 \| 0.8553 \| -1.2097 \| 14.69 \| ### Framework versions - Transformers 4.37.2 - Pytorch 2.1.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2
KevStrider/ppo-LunarLander-v2	KevStrider	2024-02-28T20:55:19Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-02-28T20:55:00Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 253.05 +/- 51.82 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 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 ... ```
CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo-gguf	CorticalStack	2024-02-28T20:48:23Z	2	1	null	[ "gguf", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-02-28T19:58:22Z	--- license: apache-2.0 --- <img src="neurotic-crown-clown-tak-stack.png" alt="Neurotic crown clown tak stack logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/> # CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo A collection of GGUF quantised versions of [CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo](https://huggingface.co/CorticalStack/neurotic-crown-clown-7b-tak-stack-dpo). The main branch model is quantised using GGUF format Q4_K_M. GGUF is a format that replaces GGML, which is no longer supported by llama.cpp. An incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
ankhamun/IxI000x800000_000x800IxI	ankhamun	2024-02-28T20:48:09Z	114	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-02-28T20:46:03Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

Subsets and Splits