Split (1)

train · 847k 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 18:27:39	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 500 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 18:23:41	card stringlengths 11 1.01M
akansha2k2/Burger_sandwich_pizza	akansha2k2	2024-05-14T14:05:50Z	196	0	transformers	[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "pytorch", "huggingpics", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	image-classification	2024-05-14T14:05:42Z	--- tags: - image-classification - pytorch - huggingpics metrics: - accuracy model-index: - name: Burger_sandwich_pizza results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.8656716346740723 --- # Burger_sandwich_pizza Autogenerated by HuggingPics🤗🖼️ Create your own image classifier for anything by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb). Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics). ## Example Images #### Burger ![Burger](images/Burger.jpg) #### pizza ![pizza](images/pizza.jpg) #### sandwich ![sandwich](images/sandwich.jpg)
tomaszki/llama-21-b	tomaszki	2024-05-14T14:00:54Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T13:58:18Z	--- 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/llama-21-a	tomaszki	2024-05-14T13:57:27Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T13:53:57Z	--- 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]
casque/0509_clear_see_through_v1	casque	2024-05-14T13:57:21Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2024-05-14T13:53:21Z	--- license: creativeml-openrail-m ---
MLP-Lemma/Lemma-Llama-DS-ckpt3.5k	MLP-Lemma	2024-05-14T13:53:32Z	4	0	transformers	[ "transformers", "safetensors", "llama", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]	null	2024-05-14T13:26:04Z	--- 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]
lmstudio-community/codegemma-1.1-7b-it-GGUF	lmstudio-community	2024-05-14T13:49:54Z	714	5	transformers	[ "transformers", "gguf", "text-generation", "base_model:google/codegemma-1.1-7b-it", "base_model:quantized:google/codegemma-1.1-7b-it", "license:gemma", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	text-generation	2024-05-04T22:25:17Z	--- library_name: transformers extra_gated_heading: Access CodeGemma on Hugging Face extra_gated_prompt: >- To access CodeGemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately. extra_gated_button_content: Acknowledge license pipeline_tag: text-generation widget: - text: > <start_of_turn>user Write a Python function to calculate the nth fibonacci number.<end_of_turn> <start_of_turn>model inference: parameters: max_new_tokens: 200 license: gemma license_link: https://ai.google.dev/gemma/terms quantized_by: bartowski base_model: google/codegemma-1.1-7b-it lm_studio: param_count: 8b use_case: coding release_date: 30-04-2024 model_creator: google prompt_template: Google Gemma Instruct system_prompt: none base_model: gemma original_repo: google/codegemma-1.1-7b-it --- ## 💫 Community Model> CodeGemma 1.1 7b Instruct by Google 👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC). Model creator: [Google](https://huggingface.co/google)<br> Original model: [google/codegemma-1.1-7b-it](https://huggingface.co/google/codegemma-1.1-7b-it)<br> GGUF quantization: provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b2777](https://github.com/ggerganov/llama.cpp/releases/tag/b2777)<br> ## Model Summary: CodeGemma 1.1 7b Instruct is an iteration on the initial CodeGemma release. It should come with minor improvements to code generation.<br> This model is meant to be used as a coding companion or for code generation.<br> ## Prompt Template: Choose the 'Google Gemma Instruct' preset in your LM Studio. Under the hood, the model will see a prompt that's formatted like so: ``` <start_of_turn>user {prompt}<end_of_turn> <start_of_turn>model ``` ## Technical Details CodeGemma is based on the Gemma 7b model with additional training on web documents, mathematics, and code, with a mixture of 80% code and 20% natural language. The code used is based on publicly avaialble code repositories. The instruct version was further trained on mathematical datasets in an attempt to improve its mathematical reasoning capabilities, as well as synthetic code generation combined with a second LLM for evaluation and reinforcement feedback. Additional details can be found on Google's official report PDF [here](https://storage.googleapis.com/deepmind-media/gemma/codegemma_report.pdf) ## Special thanks 🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible. 🙏 Special thanks to [Kalomaze](https://github.com/kalomaze) for his dataset (linked [here](https://github.com/ggerganov/llama.cpp/discussions/5263)) that was used for calculating the imatrix for these quants, which improves the overall quality! ## Disclaimers LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.
Manpa/crypto-metamath	Manpa	2024-05-14T13:49:08Z	4	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T13:45:17Z	--- 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]
kyl23/hw3_RTE_lora_1e-4_r16	kyl23	2024-05-14T13:47:56Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-14T13:47:51Z	--- 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]
NoteDance/Swin	NoteDance	2024-05-14T13:45:44Z	0	0	tf	[ "tf", "Note", "swin", "vision", "image-classification", "dataset:imagenet-1k", "dataset:imagenet-21k", "license:apache-2.0", "region:us" ]	image-classification	2024-05-14T13:42:11Z	--- license: apache-2.0 datasets: - imagenet-1k - imagenet-21k library_name: tf pipeline_tag: image-classification tags: - Note - swin - vision --- This model is built by Note, Note can be found [here](https://github.com/NoteDance/Note). The model can be found [here](https://github.com/NoteDance/Note/blob/Note-7.0/Note/neuralnetwork/tf/SwinTransformerV2.py). The tutorial can be found [here](https://github.com/NoteDance/Note-documentation/tree/tf-7.0).
SidXXD/attn_maps-color_sandesh-dog-clean	SidXXD	2024-05-14T13:39:24Z	0	0	diffusers	[ "diffusers", "tensorboard", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "custom-diffusion", "base_model:CompVis/stable-diffusion-v1-4", "base_model:adapter:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2024-05-14T13:28:56Z	--- license: creativeml-openrail-m base_model: CompVis/stable-diffusion-v1-4 instance_prompt: photo of a <new1> dog tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - custom-diffusion inference: true --- # Custom Diffusion - SidXXD/attn_maps-color_sandesh-dog-clean These are Custom Diffusion adaption weights for CompVis/stable-diffusion-v1-4. The weights were trained on photo of a <new1> dog using [Custom Diffusion](https://www.cs.cmu.edu/~custom-diffusion). You can find some example images in the following. For more details on the training, please follow [this link](https://github.com/huggingface/diffusers/blob/main/examples/custom_diffusion).
kasrahabib/all-MiniLM-L6-v2-finetuned-iso29148-f_nf_req-embdr	kasrahabib	2024-05-14T13:35:10Z	62	0	transformers	[ "transformers", "tf", "tensorboard", "bert", "text-classification", "generated_from_keras_callback", "base_model:sentence-transformers/all-MiniLM-L6-v2", "base_model:finetune:sentence-transformers/all-MiniLM-L6-v2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-05-14T13:26:31Z	--- license: apache-2.0 base_model: sentence-transformers/all-MiniLM-L6-v2 tags: - generated_from_keras_callback model-index: - name: kasrahabib/all-MiniLM-L6-v2-finetuned-iso29148-f_nf_req-embdr results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # kasrahabib/all-MiniLM-L6-v2-finetuned-iso29148-f_nf_req-embdr This model is a fine-tuned version of [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0009 - Validation Loss: 0.6623 - Epoch: 29 ## 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: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4710, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Epoch \| \|:----------:\|:---------------:\|:-----:\| \| 0.5280 \| 0.3710 \| 0 \| \| 0.3075 \| 0.3428 \| 1 \| \| 0.2140 \| 0.3139 \| 2 \| \| 0.1252 \| 0.3637 \| 3 \| \| 0.0794 \| 0.3695 \| 4 \| \| 0.0506 \| 0.4162 \| 5 \| \| 0.0384 \| 0.4577 \| 6 \| \| 0.0253 \| 0.4791 \| 7 \| \| 0.0190 \| 0.5735 \| 8 \| \| 0.0119 \| 0.5711 \| 9 \| \| 0.0141 \| 0.5977 \| 10 \| \| 0.0131 \| 0.5945 \| 11 \| \| 0.0060 \| 0.6052 \| 12 \| \| 0.0098 \| 0.6270 \| 13 \| \| 0.0080 \| 0.6484 \| 14 \| \| 0.0098 \| 0.6139 \| 15 \| \| 0.0064 \| 0.6103 \| 16 \| \| 0.0067 \| 0.6232 \| 17 \| \| 0.0078 \| 0.6205 \| 18 \| \| 0.0067 \| 0.6126 \| 19 \| \| 0.0039 \| 0.6108 \| 20 \| \| 0.0039 \| 0.6407 \| 21 \| \| 0.0052 \| 0.6501 \| 22 \| \| 0.0043 \| 0.6523 \| 23 \| \| 0.0048 \| 0.6800 \| 24 \| \| 0.0071 \| 0.6644 \| 25 \| \| 0.0014 \| 0.6600 \| 26 \| \| 0.0026 \| 0.6578 \| 27 \| \| 0.0010 \| 0.6613 \| 28 \| \| 0.0009 \| 0.6623 \| 29 \| ### Framework versions - Transformers 4.40.1 - TensorFlow 2.15.0 - Datasets 2.19.1 - Tokenizers 0.19.1
Kayyyy27/CustomModel_twitter	Kayyyy27	2024-05-14T13:32:11Z	119	0	transformers	[ "transformers", "safetensors", "distilbert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-05-14T13:31:51Z	--- 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]
fine-tuned/jina-embeddings-v2-base-en-14052024-afuz-webapp	fine-tuned	2024-05-14T13:25:33Z	5	0	sentence-transformers	[ "sentence-transformers", "safetensors", "bert", "feature-extraction", "sentence-similarity", "mteb", "Fantasy", "Novels", "Books", "Fiction", "Literature", "custom_code", "en", "dataset:fine-tuned/jina-embeddings-v2-base-en-14052024-afuz-webapp", "dataset:allenai/c4", "license:apache-2.0", "autotrain_compatible", "text-embeddings-inference", "endpoints_compatible", "region:us" ]	feature-extraction	2024-05-14T13:25:16Z	--- license: apache-2.0 datasets: - fine-tuned/jina-embeddings-v2-base-en-14052024-afuz-webapp - allenai/c4 language: - en pipeline_tag: feature-extraction tags: - sentence-transformers - feature-extraction - sentence-similarity - mteb - Fantasy - Novels - Books - Fiction - Literature --- This model is a fine-tuned version of [jinaai/jina-embeddings-v2-base-en](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) designed for the following use case: genre-specific search for fantasy novels ## How to Use This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started: ```python from sentence_transformers import SentenceTransformer from sentence_transformers.util import cos_sim model = SentenceTransformer( 'fine-tuned/jina-embeddings-v2-base-en-14052024-afuz-webapp', trust_remote_code=True ) embeddings = model.encode([ 'first text to embed', 'second text to embed' ]) print(cos_sim(embeddings[0], embeddings[1])) ```
ANGJustinl/Microsoft_Design_ArtStyle	ANGJustinl	2024-05-14T13:24:23Z	0	0	diffusers	[ "diffusers", "text-to-image", "stable-diffusion", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2024-05-14T13:24:22Z	--- tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora widget: - text: >- text:"Microsoft Design", A blue and purple color scheme is used in this image with a focus on the blue and pink hues. The image features a series of blue and violet waves which are arranged in a way that creates a visually appealing pattern. The colors are vibrant and eye-catching making the image an interesting design element., masterpiece, best quality, detailed parameters: negative_prompt: >- bad anatomy, worst quality, low quality, normal quality, watermark, blurry, output: url: images/Upscale_2024-05-14-205452_0.png - text: >- text:"Microsoft Design", A blue and purple color scheme is used in this image with a focus on the blue and pink hues. The image features a series of blue and violet waves which are arranged in a way that creates a visually appealing pattern. The colors are vibrant and eye-catching making the image an interesting design element., masterpiece, best quality, detailed parameters: negative_prompt: >- bad anatomy, worst quality, low quality, normal quality, watermark, blurry, output: url: images/Upscale_2024-05-14-205434_0.png - text: >- text:"Microsoft Design", A blue and purple color scheme is used in this image with a focus on the blue and pink hues. The image features a series of blue and violet waves which are arranged in a way that creates a visually appealing pattern. The colors are vibrant and eye-catching making the image an interesting design element., masterpiece, best quality, detailed parameters: negative_prompt: >- bad anatomy, worst quality, low quality, normal quality, watermark, blurry, output: url: images/Upscale_2024-05-14-205416_0.png - text: >- text:"Microsoft Design", A blue and purple color scheme is used in this image with a focus on the blue and pink hues. The image features a series of blue and violet waves which are arranged in a way that creates a visually appealing pattern. The colors are vibrant and eye-catching making the image an interesting design element., masterpiece, best quality, detailed parameters: negative_prompt: >- bad anatomy, worst quality, low quality, normal quality, watermark, blurry, output: url: images/Upscale_2024-05-14-205355_0.png - text: >- text:"Microsoft Design", A black and white image of a pink and purple design with a black background., masterpiece, best quality, detailed parameters: negative_prompt: >- bad anatomy, worst quality, low quality, normal quality, watermark, blurry, output: url: images/Upscale_2024-05-14-204426_0.png base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: null license: creativeml-openrail-m --- # Microsoft Design ArtStyle <Gallery /> ## Model description Same name on civitai ## Download model Weights for this model are available in Safetensors format. [Download](/ANGJustinl/Microsoft_Design_ArtStyle/tree/main) them in the Files & versions tab.
Manpa/crypto-mistral7b-metamath	Manpa	2024-05-14T13:23:04Z	4	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T13:19:08Z	--- 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]
MoMonir/codegemma-1.1-7b-it-GGUF	MoMonir	2024-05-14T13:20:48Z	6	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "text-generation", "license:gemma", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2024-05-14T12:35:46Z	--- license: gemma library_name: transformers tags: - llama-cpp - gguf-my-repo extra_gated_heading: Access CodeGemma on Hugging Face extra_gated_prompt: To access CodeGemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately. extra_gated_button_content: Acknowledge license pipeline_tag: text-generation widget: - text: '<start_of_turn>user Write a Python function to calculate the nth fibonacci number.<end_of_turn> <start_of_turn>model ' inference: parameters: max_new_tokens: 200 license_link: https://ai.google.dev/gemma/terms --- # MoMonir/codegemma-1.1-7b-it-GGUF This model was converted to GGUF format from [`google/codegemma-1.1-7b-it`](https://huggingface.co/google/codegemma-1.1-7b-it) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/google/codegemma-1.1-7b-it) for more details on the model. <!-- README_GGUF.md-about-gguf start --> ### About GGUF ([TheBloke](https://huggingface.co/TheBloke) Description) GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. <!-- README_GGUF.md-about-gguf end --> ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo MoMonir/codegemma-1.1-7b-it-GGUF --model codegemma-1.1-7b-it.Q4_K_M.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo MoMonir/codegemma-1.1-7b-it-GGUF --model codegemma-1.1-7b-it.Q4_K_M.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m codegemma-1.1-7b-it.Q4_K_M.gguf -n 128 ```
kspl/depression-falcon-7b	kspl	2024-05-14T13:20:41Z	0	0	null	[ "safetensors", "license:apache-2.0", "region:us" ]	null	2024-05-13T10:51:05Z	--- license: apache-2.0 ---
quangtqv/cross_encoder_tool_learning_best_model_14_5_2024	quangtqv	2024-05-14T13:20:04Z	115	0	transformers	[ "transformers", "safetensors", "xlm-roberta", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-05-14T13:19:31Z	--- 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]
Rishwonth/aa_model	Rishwonth	2024-05-14T13:18:34Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "base_model:finetune:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-05-14T13:18:19Z	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl base_model: unsloth/llama-3-8b-bnb-4bit --- # Uploaded model - Developed by: Rishwonth - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Ankesh1234/gemma1_fine	Ankesh1234	2024-05-14T13:18:22Z	77	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-05-14T12:33:38Z	--- license: apache-2.0 ---
kasrahabib/roberta-base-finetuned-iso29148-f_nf_req-embdr	kasrahabib	2024-05-14T13:11:11Z	62	0	transformers	[ "transformers", "tf", "tensorboard", "roberta", "text-classification", "generated_from_keras_callback", "base_model:FacebookAI/roberta-base", "base_model:finetune:FacebookAI/roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-05-14T12:49:04Z	--- license: mit base_model: FacebookAI/roberta-base tags: - generated_from_keras_callback model-index: - name: kasrahabib/roberta-base-finetuned-iso29148-f_nf_req-cls results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # kasrahabib/roberta-base-finetuned-iso29148-f_nf_req-cls This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0019 - Validation Loss: 0.6444 - Epoch: 29 ## 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: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4710, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results \| Train Loss \| Validation Loss \| Epoch \| \|:----------:\|:---------------:\|:-----:\| \| 0.4775 \| 0.3493 \| 0 \| \| 0.2723 \| 0.3205 \| 1 \| \| 0.1702 \| 0.3163 \| 2 \| \| 0.0925 \| 0.3759 \| 3 \| \| 0.0803 \| 0.4358 \| 4 \| \| 0.0444 \| 0.5255 \| 5 \| \| 0.0227 \| 0.5733 \| 6 \| \| 0.0342 \| 0.5173 \| 7 \| \| 0.0231 \| 0.5098 \| 8 \| \| 0.0144 \| 0.5852 \| 9 \| \| 0.0067 \| 0.6479 \| 10 \| \| 0.0039 \| 0.7709 \| 11 \| \| 0.0222 \| 0.5779 \| 12 \| \| 0.0144 \| 0.6940 \| 13 \| \| 0.0213 \| 0.5848 \| 14 \| \| 0.0047 \| 0.6554 \| 15 \| \| 0.0036 \| 0.6801 \| 16 \| \| 0.0011 \| 0.7073 \| 17 \| \| 0.0082 \| 0.7724 \| 18 \| \| 0.0084 \| 0.6025 \| 19 \| \| 0.0009 \| 0.6345 \| 20 \| \| 0.0034 \| 0.6718 \| 21 \| \| 0.0032 \| 0.6396 \| 22 \| \| 0.0030 \| 0.6050 \| 23 \| \| 0.0005 \| 0.6186 \| 24 \| \| 0.0006 \| 0.6282 \| 25 \| \| 0.0005 \| 0.6337 \| 26 \| \| 0.0004 \| 0.6417 \| 27 \| \| 0.0003 \| 0.6447 \| 28 \| \| 0.0019 \| 0.6444 \| 29 \| ### Framework versions - Transformers 4.40.1 - TensorFlow 2.15.0 - Datasets 2.19.1 - Tokenizers 0.19.1
CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF	CISCai	2024-05-14T13:08:59Z	33	4	null	[ "gguf", "text-generation", "en", "base_model:AetherResearch/Cerebrum-1.0-8x7b", "base_model:quantized:AetherResearch/Cerebrum-1.0-8x7b", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2024-03-20T15:54:27Z	--- base_model: AetherResearch/Cerebrum-1.0-8x7b license: apache-2.0 language: - en pipeline_tag: text-generation model_creator: Aether AI model_name: Cerebrum-1.0-8x7b model_type: mixtral quantized_by: CISC --- # Cerebrum-1.0-8x7B - SOTA GGUF - Model creator: [Aether AI](https://huggingface.co/AetherResearch) - Original model: [Cerebrum 1.0 8x7B](https://huggingface.co/AetherResearch/Cerebrum-1.0-8x7b) <!-- description start --> ## Description This repo contains State Of The Art quantized GGUF format model files for [Cerebrum 1.0 8x7B](https://huggingface.co/AetherResearch/Cerebrum-1.0-8x7b). Quantization was done with an importance matrix that was trained for ~250K tokens (64 batches of 4096 tokens) of [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) and [wiki.train.raw](https://raw.githubusercontent.com/pytorch/examples/main/word_language_model/data/wikitext-2/train.txt) concatenated. <!-- description end --> <!-- prompt-template start --> ## Prompt template: Cerebrum ``` <s>A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions. User: Are you conscious? AI: ``` <!-- prompt-template end --> <!-- compatibility_gguf start --> ## Compatibility These quantised GGUFv3 files are compatible with llama.cpp from February 27th 2024 onwards, as of commit [0becb22](https://github.com/ggerganov/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307) They are also compatible with many third party UIs and libraries provided they are built using a recent llama.cpp. ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_IQ1_S - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.56 bits per weight (bpw) * GGML_TYPE_IQ2_XXS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.06 bpw * GGML_TYPE_IQ2_XS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.31 bpw * GGML_TYPE_IQ2_S - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.5 bpw * GGML_TYPE_IQ2_M - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.7 bpw * GGML_TYPE_IQ3_XXS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.06 bpw * GGML_TYPE_IQ3_XS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.3 bpw * GGML_TYPE_IQ3_S - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.44 bpw * GGML_TYPE_IQ3_M - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.66 bpw * GGML_TYPE_IQ4_XS - 4-bit quantization in super-blocks with an importance matrix applied, effectively using 4.25 bpw Refer to the Provided Files table below to see what files use which methods, and how. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-provided-files start --> ## Provided files \| Name \| Quant method \| Bits \| Size \| Max RAM required \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [Cerebrum-1.0-8x7b.IQ1_S.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ1_S.gguf) \| IQ1_S \| 1 \| 9.2 GB\| 9.7 GB \| smallest, significant quality loss - TBD: Waiting for [this issue](https://github.com/ggerganov/llama.cpp/issues/5996) to be resolved \| \| [Cerebrum-1.0-8x7b.IQ2_XXS.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ2_XXS.gguf) \| IQ2_XXS \| 2 \| 12.0 GB\| 12.5 GB \| very small, high quality loss \| \| [Cerebrum-1.0-8x7b.IQ2_XS.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ2_XS.gguf) \| IQ2_XS \| 2 \| 13.4 GB\| 13.9 GB \| very small, high quality loss \| \| [Cerebrum-1.0-8x7b.IQ2_S.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ2_S.gguf) \| IQ2_S \| 2 \| 13.6 GB\| 14.1 GB \| small, substantial quality loss \| \| [Cerebrum-1.0-8x7b.IQ2_M.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ2_M.gguf) \| IQ2_M \| 2 \| 15.0 GB\| 15.5 GB \| small, greater quality loss \| \| [Cerebrum-1.0-8x7b.IQ3_XXS.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ3_XXS.gguf) \| IQ3_XXS \| 3 \| 17.3 GB\| 17.8 GB \| very small, high quality loss \| \| [Cerebrum-1.0-8x7b.IQ3_XS.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ3_XS.gguf) \| IQ3_XS \| 3 \| 18.4 GB\| 18.9 GB \| small, substantial quality loss \| \| [Cerebrum-1.0-8x7b.IQ3_S.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ3_S.gguf) \| IQ3_S \| 3 \| 19.5 GB\| 20.0 GB \| small, greater quality loss \| \| [Cerebrum-1.0-8x7b.IQ3_M.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ3_M.gguf) \| IQ3_M \| 3 \| 20.5 GB\| 21.0 GB \| medium, balanced quality - recommended \| \| [Cerebrum-1.0-8x7b.IQ4_XS.gguf](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.IQ4_XS.gguf) \| IQ4_XS \| 4 \| 24.0 GB\| 24.5 GB \| small, substantial quality loss \| Generated importance matrix file: [Cerebrum-1.0-8x7b.imatrix.dat](https://huggingface.co/CISCai/Cerebrum-1.0-8x7b-SOTA-GGUF/blob/main/Cerebrum-1.0-8x7b.imatrix.dat) Note: the above RAM figures assume no GPU offloading with 4K context. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. <!-- README_GGUF.md-provided-files end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [0becb22](https://github.com/ggerganov/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307) or later. ```shell ./main -ngl 33 -m Cerebrum-1.0-8x7b.IQ2_XS.gguf --override-kv llama.expert_used_count=int:3 --color -c 16384 --temp 0.7 --repeat-penalty 1.0 -n -1 -p "A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions.\nUser: {prompt}\nAI:" ``` Change `-ngl 33` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 16384` to the desired sequence length. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` If you are low on V/RAM try quantizing the K-cache with `-ctk q8_0` or even `-ctk q4_0` for big memory savings (depending on context size). There is a similar option for V-cache (`-ctv`), however that is [not working yet](https://github.com/ggerganov/llama.cpp/issues/4425). For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) module. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://llama-cpp-python.readthedocs.io/en/latest/). #### First install the package Run one of the following commands, according to your system: ```shell # Prebuilt wheel with basic CPU support pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu # Prebuilt wheel with NVidia CUDA acceleration pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121 (or cu122 etc.) # Prebuilt wheel with Metal GPU acceleration pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/metal # Build base version with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUDA=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # Or with Vulkan acceleration CMAKE_ARGS="-DLLAMA_VULKAN=on" pip install llama-cpp-python # Or with Kompute acceleration CMAKE_ARGS="-DLLAMA_KOMPUTE=on" pip install llama-cpp-python # Or with SYCL acceleration CMAKE_ARGS="-DLLAMA_SYCL=on -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_CUDA=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Chat Completion API llm = Llama(model_path="./Cerebrum-1.0-8x7b.IQ3_M.gguf", n_gpu_layers=33, n_ctx=16384) print(llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] )) ``` <!-- README_GGUF.md-how-to-run end --> <!-- original-model-card start --> # Original model card: Aether AI's Cerebrum-1.0-8x7B ## Introduction Cerebrum 8x7b is a large language model (LLM) created specifically for reasoning tasks. It is based on the Mixtral 8x7b model. Similar to its smaller version, [Cerebrum 7b](https://huggingface.co/AetherResearch/Cerebrum-1.0-7b), it is fine-tuned on a small custom dataset of native chain of thought data and further improved with targeted RLHF (tRLHF), a novel technique for sample-efficient LLM alignment. Unlike numerous other recent fine-tuning approaches, our training pipeline includes under 5000 training prompts and even fewer labeled datapoints for tRLHF. Native chain of thought approach means that Cerebrum is trained to devise a tactical plan before tackling problems that require thinking. For brainstorming, knowledge intensive, and creative tasks Cerebrum will typically omit unnecessarily verbose considerations. Cerebrum 8x7b offers competitive performance to Gemini 1.0 Pro and GPT-3.5 Turbo on a range of tasks that require reasoning. ## Benchmarking An overview of Cerebrum 8x7b performance compared to Gemini 1.0 Pro, GPT-3.5 and Mixtral 8x7b on selected benchmarks: <img src="/AetherResearch/Cerebrum-1.0-8x7b/resolve/main/benchmarking.png" alt="benchmarking_chart" width="750"/> <img src="/AetherResearch/Cerebrum-1.0-8x7b/resolve/main/benchmarking_table.png" alt="benchmarking_table" width="750"/> Evaluation details: 1) ARC-C: all models evaluated zero-shot. Gemini 1.0 Pro and GPT-3.5 (gpt-3.5-turbo-0125) evaluated via API, reported numbers taken for Mixtral 8x7b. 2) HumanEval: all models evaluated zero-shot, reported numbers used. 3) GSM8k: Cerebrum, GPT-3.5, and Mixtral 8x7b evaluated with maj@8, Gemini evaluated with maj@32. GPT-3.5 (gpt-3.5-turbo-0125) evaluated via API, reported numbers taken for Gemini 1.0 Pro and Mixtral 8x7b. 4) MATH: Cerebrum evaluated 0-shot. GPT-3.5 and Gemini evaluated 4-shot, Mixtral 8x7b maj@4. Reported numbers used. ## Usage For optimal performance, Cerebrum should be prompted with an Alpaca-style template that requests the description of the "thought process". Here is what a conversation should look like from the model's point of view: ``` <s>A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions. User: Are you conscious? AI: ``` This prompt is also available as a chat template. Here is how you could use it: ``` messages = [ {'role': 'user', 'content': 'What is self-consistency decoding?'}, {'role': 'assistant', 'content': 'Self-consistency decoding is a technique used in natural language processing to improve the performance of language models. It works by generating multiple outputs for a given input and then selecting the most consistent output based on a set of criteria.'}, {'role': 'user', 'content': 'Why does self-consistency work?'} ] input = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors='pt') with torch.no_grad(): out = model.generate(input_ids=input, max_new_tokens=100, do_sample=False) ``` The model ends its turn by generating the EOS token. Importantly, this token should be removed from the model answer in a multi-turn dialogue. Cerebrum can be operated at very low temperatures (and specifically temperature 0), which improves performance on tasks that require precise answers. The alignment should be sufficient to avoid repetitions in most cases without a repetition penalty. ## Examples Some of the model output examples: The model is trained to first "think aloud about the solution", before solving the problem itself: ~~~~ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions. User: Find the longest increasing subarray of the given array. The function signature should be def longest_increasing_subarray(vals: List[int]). Write the code in Python. AI: To find the longest increasing subarray of the given array, we could start by considering the first element of the array as the start of the subarray. Then, we could iterate through the remaining elements of the array and check if each element is greater than the last element of the current subarray. If it is, we could add it to the subarray. If it is not, we could save the length of the current subarray and start a new subarray with the current element. We could repeat this process until we reach the end of the array. Then, we could return the longest subarray found. Here is an example: ```python def longest_increasing_subarray(vals: List[int]): if len(vals) == 0: return [] longest_subarray = [vals[0]] current_subarray = [vals[0]] for i in range(1, len(vals)): if vals[i] > current_subarray[-1]: current_subarray.append(vals[i]) else: if len(current_subarray) > len(longest_subarray): longest_subarray = current_subarray current_subarray = [vals[i]] if len(current_subarray) > len(longest_subarray): longest_subarray = current_subarray return longest_subarray ``` ~~~~ Usual unprompted chain of thought example for mathematical problem solving: ~~~~ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions. User: Out of six apples three are bad. What is the probability that at least one apple will be bad when selecting two apples out of them? AI: To find the probability that at least one apple will be bad when selecting two apples out of them, we need to consider the possible outcomes of the selection. There are two cases: either one of the selected apples is bad, or both of them are bad. The probability that one of the selected apples is bad is equal to the probability that the first apple is bad and the second apple is good, plus the probability that the first apple is good and the second apple is bad. Since three out of six apples are bad, the probability that the first apple is bad is $3/6 = 1/2$. The probability that the second apple is good, given that the first apple is bad, is equal to $3/5$, since there are three good apples left out of five remaining apples. Therefore, the probability that the first apple is bad and the second apple is good is $1/2 \cdot 3/5 = 3/10$. Similarly, the probability that the first apple is good and the second apple is bad is also $3/10$. Therefore, the probability that one of the selected apples is bad is $3/10 + 3/10 = 6/10 = 3/5$. The probability that both of the selected apples are bad is equal to the probability that the first apple is bad and the second apple is bad. Since there are three bad apples out of six, the probability that the first apple is bad is $3/6 = 1/2$. The probability that the second apple is bad, given that the first apple is bad, is equal to $2/5$, since there are two bad apples left out of five remaining apples. Therefore, the probability that both of the selected apples are bad is $1/2 \cdot 2/5 = 2/10 = 1/5$. To find the probability that at least one apple will be bad, we add the probabilities of the two cases: the probability that one of the selected apples is bad and the probability that both of the selected apples are bad. Therefore, the probability that at least one apple will be bad is $3/5 + 1/5 = 4/5$. The answer is 4/5. ~~~~ Similar example for a simple physical task: ~~~~ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions. User: The apple falls from a tree of height 10m. When will it reach the earth if there is no air resistance? AI: To find out when the apple will reach the earth, we can use the equation of motion for a freely falling object. The equation of motion for a freely falling object is $s = ut + \frac{1}{2}at^2$, where $s$ is the displacement, $u$ is the initial velocity, $a$ is the acceleration due to gravity, and $t$ is the time taken. In this case, the initial velocity of the apple is 0, and the acceleration due to gravity is 9.8 m/s^2. Therefore, we can write the equation of motion as $s = \frac{1}{2}at^2$. Substituting the values, we get $10 = \frac{1}{2} \cdot 9.8 \cdot t^2$. Solving for $t$, we get $t = \sqrt{\frac{20}{9.8}} = \sqrt{2.04} = 1.43$ seconds. Therefore, the apple will reach the earth in 1.43 seconds. The answer is 1.43 seconds. ~~~~ Simple calculus problem, note that the model quietly corrects itself after proposing factoring out of $n$ from the numerator, which is inefficient in this case. ~~~~ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions. User: What is $\lim_{n \to \infty} \frac{(n + 3) \cdot \sqrt{n}}{(n/2 - 1)^2}$? AI: To find the limit of $\frac{(n + 3) \cdot \sqrt{n}}{(n/2 - 1)^2}$ as $n$ approaches infinity, we can start by simplifying the expression. We can factor out $n$ from the numerator and write $(n + 3) \cdot \sqrt{n} = n \cdot \sqrt{n} + 3 \cdot \sqrt{n}$. We can also write $(n/2 - 1)^2 = n^2/4 - n + 1$. Therefore, we can write the limit as $\lim_{n \to \infty} \frac{n \cdot \sqrt{n} + 3 \cdot \sqrt{n}}{n^2/4 - n + 1}$. Now, we can consider the behavior of each term in the numerator and denominator as $n$ approaches infinity. As $n$ approaches infinity, $n \cdot \sqrt{n}$ will grow much faster than $3 \cdot \sqrt{n}$, so we can ignore the $3 \cdot \sqrt{n}$ term in the numerator. Similarly, as $n$ approaches infinity, $n^2/4$ will grow much faster than $n$ and $1$, so we can ignore the $n$ and $1$ terms in the denominator. Therefore, we can write the limit as $\lim_{n \to \infty} \frac{n \cdot \sqrt{n}}{n^2/4} = \lim_{n \to \infty} \frac{4 \cdot n \cdot \sqrt{n}}{n^2} = \lim_{n \to \infty} \frac{4 \cdot \sqrt{n}}{n} = \lim_{n \to \infty} \frac{4}{\sqrt{n}} = 0$. Therefore, the limit of $\frac{(n + 3) \cdot \sqrt{n}}{(n/2 - 1)^2}$ as $n$ approaches infinity is 0. The answer is 0. ~~~~ Example of a simple proof. The model "forgets" to prove that the matrix $B^T A B$ is symmetric. This is quite common - in fact, GPT-4 fails in a similar fashion. ~~~~ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions. User: If $A$ is positive semi-definite, is $B^TAB$ positive semi-definite? AI: To determine whether $B^TAB$ is positive semi-definite, we need to consider the properties of $A$ and $B$. Since $A$ is positive semi-definite, we know that for any vector $x$, $x^TAx \geq 0$. To show that $B^TAB$ is positive semi-definite, we need to show that for any vector $y$, $y^TB^TABy \geq 0$. We can write $y^TB^TABy$ as $(By)^TA(By)$. Since $A$ is positive semi-definite, we know that $(By)^TA(By) \geq 0$. Therefore, $y^TB^TABy \geq 0$ for any vector $y$, which means that $B^TAB$ is positive semi-definite. The answer is yes. ~~~~ Typical reaction of a model to some hallucination-inducing prompt. Instead of simply claiming that it does not know the painter George Ellster, it tries to help the user find a painter with a similar name: ~~~~ A chat between a user and a thinking artificial intelligence assistant. The assistant describes its thought process and gives helpful and detailed answers to the user's questions. User: Tell me about a famous British painter George Ellster AI: George Ellster is not a famous British painter. However, there are a few notable British painters with similar names: George Elgar Hicks (1824-1914) was a Victorian-era painter known for his genre scenes and portraits. George Frederic Watts (1817-1904) was a Victorian-era painter and sculptor known for his allegorical and symbolic works. George Stubbs (1724-1806) was an 18th-century painter known for his equestrian and animal paintings. George Romney (1734-1802) was an 18th-century painter known for his portraits and historical scenes. These are just a few examples of notable British painters with similar names to George Ellster. ~~~~
hotkeyswap/v1-airouting	hotkeyswap	2024-05-14T13:07:19Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-06T10:06:09Z	--- 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]
llxlb/lora_model_test1	llxlb	2024-05-14T12:56:35Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "base_model:finetune:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-05-14T12:56:23Z	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl base_model: unsloth/llama-3-8b-bnb-4bit --- # Uploaded model - Developed by: llxlb - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Wacim-octo/corgy_factory_LoRA	Wacim-octo	2024-05-14T12:55:49Z	0	0	diffusers	[ "diffusers", "text-to-image", "diffusers-training", "dora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:finetune:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]	text-to-image	2024-05-14T12:46:55Z	--- license: openrail++ library_name: diffusers tags: - text-to-image - diffusers-training - diffusers - dora - template:sd-lora - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - text-to-image - diffusers-training - diffusers - dora - template:sd-lora - stable-diffusion-xl - stable-diffusion-xl-diffusers base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: a photo of a factury widget: [] --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # SDXL LoRA DreamBooth - Wacim-octo/corgy_factory_LoRA <Gallery /> ## Model description These are Wacim-octo/corgy_factory_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use a photo of a factury to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](Wacim-octo/corgy_factory_LoRA/tree/main) them in the Files & versions tab. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
LuisCe/Kidney	LuisCe	2024-05-14T12:52:49Z	76	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "Resolución", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-05-14T12:46:32Z	--- library_name: transformers tags: - Resolución --- # 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]
dbaek111/Mistral-7B-v0.2-Elon_1000-instruct	dbaek111	2024-05-14T12:47:31Z	77	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "trl", "sft", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-05-14T12:44:01Z	--- library_name: transformers tags: - trl - sft --- # 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]
roshinishetty333/llama-2-7b-prefix-tuned	roshinishetty333	2024-05-14T12:46:02Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-12T20:21:12Z	--- 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]
IEETA/Multi-Head-CRF	IEETA	2024-05-14T12:45:00Z	0	0	null	[ "es", "dataset:IEETA/SPACCC-Spanish-NER", "license:mit", "region:us" ]	null	2024-05-10T14:29:08Z	--- license: mit datasets: - IEETA/SPACCC-Spanish-NER language: - es metrics: - f1 --- # Model Card for Biomedical Named Entity Recognition in Spanish Clinical Texts Our model focuses on Biomedical Named Entity Recognition (NER) in Spanish clinical texts, crucial for automated information extraction in medical research and treatment improvements. It proposes a novel approach using a Multi-Head Conditional Random Field (CRF) classifier to tackle multi-class NER tasks, overcoming challenges of overlapping entity instances. The classes it recognizes include symptoms, procedures, diseases, chemicals, and proteins. We provide 4 different models, available as branches of this repository. ## Model Details ### Model Description - Developed by: IEETA - Model type: Multi-Head-CRF, Roberta Base - Language(s) (NLP): Spanish - License: MIT - Finetuned from model: lcampillos/roberta-es-clinical-trials-ner ### Model Sources - Repository: [IEETA Multi-Head-CRF GitHub](https://github.com/ieeta-pt/Multi-Head-CRF) - Paper: Multi-head CRF classifier for biomedical multi-class Named Entity Recognition on Spanish clinical notes [Awaiting Publication] Authors: - Richard A A Jonker ([ORCID: 0000-0002-3806-6940](https://orcid.org/0000-0002-3806-6940)) - Tiago Almeida ([ORCID: 0000-0002-4258-3350](https://orcid.org/0000-0002-4258-3350)) - Rui Antunes ([ORCID: 0000-0003-3533-8872](https://orcid.org/0000-0003-3533-8872)) - João R Almeida ([ORCID: 0000-0003-0729-2264](https://orcid.org/0000-0003-0729-2264)) - Sérgio Matos ([ORCID: 0000-0003-1941-3983](https://orcid.org/0000-0003-1941-3983)) ## Uses Note we do not take any liability for the use of the model in any professional/medical domain. The model is intended for academic purposes only. It performs Named Entity Recognition over 5 classes namely: SYMPTOM PROCEDURE DISEASE PROTEIN CHEMICAL ## How to Get Started with the Model Please refer to our GitHub repository for more information on how to train the model and run inference: [IEETA Multi-Head-CRF GitHub](https://github.com/ieeta-pt/Multi-Head-CRF) ## Training Details ### Training Data The training data can be found on IEETA/SPACCC-Spanish-NER, which is further described on the dataset card. The dataset used consists of 4 seperate datasets: - [SympTEMIST](https://zenodo.org/records/10635215) - [MedProcNER](https://zenodo.org/records/8224056) - [DisTEMIST](https://zenodo.org/records/7614764) - [PharmaCoNER](https://zenodo.org/records/4270158) ### Speeds, Sizes, Times The models were trained using an Nvidia Quadro RTX 8000. The models for 5 classes took approximately 1 hour to train and occupy around 1GB of disk space. Additionally, this model shows linear complexity (+8 minutes) per entity class to classify. ### Testing Data, Factors & Metrics #### Testing Data The testing data can be found on IEETA/SPACCC-Spanish-NER, which is further described on the dataset card. #### Metrics The models were evaluated using the micro-averaged F1-score metric, the standard for entity recognition tasks. ### Results We provide 4 separate models with various hyperparameter changes: \| HLs per head \| Augmentation \| Percentage Tags \| Augmentation Probability \| F1 \| \|--------------\|--------------\|-----------------\|--------------------------\|--------\| \| 3 \| Random \| 0.25 \| 0.50 \| 78.73 \| \| 3 \| Unknown \| 0.50 \| 0.25 \| 78.50 \| \| 3 \| None \| - \| - \| 78.89 \| \| 1 \| Random \| 0.25 \| 0.50 \| 78.89 \| All models are trained with a context size of 32 tokens for 60 epochs. ## Citation BibTeX: [Awaiting Publication]
davideaguglia/ppo-LunarLander-v2-fromscratch	davideaguglia	2024-05-14T12:44:55Z	0	0	null	[ "tensorboard", "LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]	reinforcement-learning	2024-05-14T12:14:37Z	--- tags: - LunarLander-v2 - ppo - deep-reinforcement-learning - reinforcement-learning - custom-implementation - deep-rl-course model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: -80.26 +/- 45.16 name: mean_reward verified: false --- # PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. # Hyperparameters ```python {'exp_name': 'ppo' 'seed': 1 'torch_deterministic': True 'cuda': True 'track': False 'wandb_project_name': 'cleanRL' 'wandb_entity': None 'capture_video': False 'env_id': 'LunarLander-v2' 'total_timesteps': 1000000 'learning_rate': 0.00025 'num_envs': 4 'num_steps': 128 'anneal_lr': True 'gae': True 'gamma': 0.99 'gae_lambda': 0.95 'num_minibatches': 4 'update_epochs': 4 'norm_adv': True 'clip_coef': 0.2 'clip_vloss': True 'ent_coef': 0.01 'vf_coef': 0.5 'max_grad_norm': 0.5 'target_kl': None 'repo_id': 'davideaguglia/ppo-LunarLander-v2-fromscratch' 'batch_size': 512 'minibatch_size': 128} ```
mfuentelsaz/clasificador-muchocine	mfuentelsaz	2024-05-14T12:43:55Z	110	0	transformers	[ "transformers", "safetensors", "electra", "text-classification", "classification", "generated_from_trainer", "base_model:mrm8488/electricidad-base-discriminator", "base_model:finetune:mrm8488/electricidad-base-discriminator", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-05-09T08:32:58Z	--- base_model: mrm8488/electricidad-base-discriminator tags: - classification - generated_from_trainer metrics: - accuracy model-index: - name: clasificador-muchocine 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. --> # clasificador-muchocine This model is a fine-tuned version of [mrm8488/electricidad-base-discriminator](https://huggingface.co/mrm8488/electricidad-base-discriminator) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4057 - Accuracy: 0.4348 ## 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: 3.0 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 388 \| 1.3794 \| 0.3961 \| \| 1.3811 \| 2.0 \| 776 \| 1.2981 \| 0.4206 \| \| 1.0028 \| 3.0 \| 1164 \| 1.4057 \| 0.4348 \| ### Framework versions - Transformers 4.40.2 - Pytorch 2.2.1+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1
time-series-foundation-models/Lag-Llama	time-series-foundation-models	2024-05-14T12:41:49Z	0	216	null	[ "safetensors", "time series", "forecasting", "pretrained models", "foundation models", "time series foundation models", "time-series", "time-series-forecasting", "arxiv:2310.08278", "license:apache-2.0", "region:us" ]	time-series-forecasting	2024-02-07T10:33:56Z	--- license: apache-2.0 tags: - time series - forecasting - pretrained models - foundation models - time series foundation models - time-series pipeline_tag: time-series-forecasting --- # Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting ![lag-llama-architecture](images/lagllama.webp) Lag-Llama is the <b>first open-source foundation model for time series forecasting</b>! [[Tweet Thread](https://twitter.com/arjunashok37/status/1755261111233114165)] [[Model Weights](https://huggingface.co/time-series-foundation-models/Lag-Llama)] [[Colab Demo 1: Zero-Shot Forecasting](https://colab.research.google.com/drive/1DRAzLUPxsd-0r8b-o4nlyFXrjw_ZajJJ?usp=sharing)] [[Colab Demo 2: (Preliminary Finetuning)](https://colab.research.google.com/drive/1uvTmh-pe1zO5TeaaRVDdoEWJ5dFDI-pA?usp=sharing)] [[Paper](https://arxiv.org/abs/2310.08278)] [[Video](https://www.youtube.com/watch?v=Mf2FOzDPxck)] ____ <b>Updates</b>: * 16-Apr-2024: Released pretraining and finetuning scripts to replicate the experiments in the paper. See [Reproducing Experiments in the Paper](https://github.com/time-series-foundation-models/lag-llama?tab=readme-ov-file#reproducing-experiments-in-the-paper) for details. * 9-Apr-2024: We have released a 15-minute video 🎥 on Lag-Llama on [YouTube](https://www.youtube.com/watch?v=Mf2FOzDPxck). * 5-Apr-2024: Added a [section](https://colab.research.google.com/drive/1DRAzLUPxsd-0r8b-o4nlyFXrjw_ZajJJ?authuser=1#scrollTo=Mj9LXMpJ01d7&line=6&uniqifier=1) in Colab Demo 1 on the importance of tuning the context length for zero-shot forecasting. Added a [best practices section](https://github.com/time-series-foundation-models/lag-llama?tab=readme-ov-file#best-practices) in the README; added recommendations for finetuning. These recommendations will be demonstrated with an example in [Colab Demo 2](https://colab.research.google.com/drive/1uvTmh-pe1zO5TeaaRVDdoEWJ5dFDI-pA?usp=sharing) soon. * 4-Apr-2024: We have updated our requirements file with new versions of certain packages. Please update/recreate your environments if you have previously used the code locally. * 7-Mar-2024: We have released a preliminary [Colab Demo 2](https://colab.research.google.com/drive/1uvTmh-pe1zO5TeaaRVDdoEWJ5dFDI-pA?usp=sharing) for finetuning. Please note this is a preliminary tutorial. We recommend taking a look at the best practices if you are finetuning the model or using it for benchmarking. * 17-Feb-2024: We have released a new updated [Colab Demo 1](https://colab.research.google.com/drive/1DRAzLUPxsd-0r8b-o4nlyFXrjw_ZajJJ?usp=sharing) for zero-shot forecasting that shows how one can load time series of different formats. * 7-Feb-2024: We released Lag-Llama, with open-source model checkpoints and a Colab Demo for zero-shot forecasting. ____ Current Features: 💫 <b>Zero-shot forecasting</b> on a dataset of <b>any frequency</b> for <b>any prediction length</b>, using <a href="https://colab.research.google.com/drive/1DRAzLUPxsd-0r8b-o4nlyFXrjw_ZajJJ?usp=sharing" target="_blank">Colab Demo 1.</a><br/> 💫 <b>Finetuning</b> on a dataset using [Colab Demo 2](https://colab.research.google.com/drive/1uvTmh-pe1zO5TeaaRVDdoEWJ5dFDI-pA?usp=sharing). 💫 <b>Reproducing</b> experiments in the paper using the released scripts. See [Reproducing Experiments in the Paper](https://github.com/time-series-foundation-models/lag-llama?tab=readme-ov-file#reproducing-experiments-in-the-paper) for details. Note: Please see the [best practices section](https://github.com/time-series-foundation-models/lag-llama?tab=readme-ov-file#best-practices) when using the model for zero-shot prediction and finetuning. ____ ## Reproducing Experiments in the Paper To replicate the pretraining setup used in the paper, please see [the pretraining script](scripts/pretrain.sh). Once a model is pretrained, instructions to finetune it with the setup in the paper can be found in [the finetuning script](scripts/finetune.sh). ## Best Practices Here are some general tips in using Lag-Llama. <!-- We recommend reading the [paper](https://arxiv.org/abs/2310.08278) for all details about the model. --> ### General Information * Lag-Llama is a probabilistic forecasting model trained to output a probability distribution for each timestep to be predicted. For your own specific use-case, we would recommend benchmarking the zero-shot performance of the model on your data first, and then finetuning if necessary. As we show in our paper, Lag-Llama has strong zero-shot capabilities, but performs best when finetuned. The more data you finetune on, the better. For specific tips on applying on model zero-shot or on finetuning, please refer to the sections below. #### Zero-Shot Forecasting * Importantly, we recommend trying different context lengths (starting from $32$ which it was trained on) and identifying what works best for your data. As we show in [this section of the zero-shot forecasting demo](https://colab.research.google.com/drive/1DRAzLUPxsd-0r8b-o4nlyFXrjw_ZajJJ?authuser=1#scrollTo=Mj9LXMpJ01d7&line=6&uniqifier=1), the model's zero-shot performance improves as the context length is increased, until a certain context length which may be specific to your data. Further, we recommend enabling RoPE scaling for the model to work well with context lengths larger than what it was trained on. #### Fine-Tuning If you are trying to benchmark the performance of the model under finetuning, or trying to obtain maximum performance from the model: * We recommend tuning two important hyperparameters for each dataset that you finetune on: the context length (suggested values: $32$, $64$, $128$, $256$, $512$, $1024$) and the learning rate (suggested values: $10^{-2}$, $5 * 10^{-3}$, $10^{-3}$, $5 * 10^{-3}$, $1 * 10^{-4}$, $5 * 10^{-4}$). * We also highly recommend using a validation split of your dataset to early stop your model, with an early stopping patience of 50 epochs. ## Contact We are dedicated to ensuring the reproducility of our results, and would be happy to help clarify questions about benchmarking our model or about the experiments in the paper. The quickest way to reach us would be by email. Please email both: 1. [Arjun Ashok](https://ashok-arjun.github.io/) - arjun [dot] ashok [at] servicenow [dot] com 2. [Kashif Rasul](https://scholar.google.de/citations?user=cfIrwmAAAAAJ&hl=en) - kashif [dot] rasul [at] gmail [dot] com If you have questions about the model usage (or) code (or) have specific errors (eg. using it with your own dataset), it would be best to create an issue in the GitHub repository. ## Citing this work Please use the following Bibtex entry to cite Lag-Llama. ``` @misc{rasul2024lagllama, title={Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting}, author={Kashif Rasul and Arjun Ashok and Andrew Robert Williams and Hena Ghonia and Rishika Bhagwatkar and Arian Khorasani and Mohammad Javad Darvishi Bayazi and George Adamopoulos and Roland Riachi and Nadhir Hassen and Marin Biloš and Sahil Garg and Anderson Schneider and Nicolas Chapados and Alexandre Drouin and Valentina Zantedeschi and Yuriy Nevmyvaka and Irina Rish}, year={2024}, eprint={2310.08278}, archivePrefix={arXiv}, primaryClass={cs.LG} } ```
flaubert/flaubert_large_cased	flaubert	2024-05-14T12:38:43Z	4,538	3	transformers	[ "transformers", "pytorch", "safetensors", "flaubert", "fill-mask", "bert", "language-model", "flue", "french", "bert-large", "flaubert-large", "cased", "fr", "dataset:flaubert", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2022-03-02T23:29:05Z	--- language: fr license: mit datasets: - flaubert metrics: - flue tags: - bert - language-model - flaubert - flue - french - bert-large - flaubert-large - cased --- # FlauBERT: Unsupervised Language Model Pre-training for French FlauBERT is a French BERT trained on a very large and heterogeneous French corpus. Models of different sizes are trained using the new CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/eng/jean-zay/ ) supercomputer. Along with FlauBERT comes [FLUE](https://github.com/getalp/Flaubert/tree/master/flue): an evaluation setup for French NLP systems similar to the popular GLUE benchmark. The goal is to enable further reproducible experiments in the future and to share models and progress on the French language.For more details please refer to the [official website](https://github.com/getalp/Flaubert). ## FlauBERT models \| Model name \| Number of layers \| Attention Heads \| Embedding Dimension \| Total Parameters \| \| :------: \| :---: \| :---: \| :---: \| :---: \| \| `flaubert-small-cased` \| 6 \| 8 \| 512 \| 54 M \| \| `flaubert-base-uncased` \| 12 \| 12 \| 768 \| 137 M \| \| `flaubert-base-cased` \| 12 \| 12 \| 768 \| 138 M \| \| `flaubert-large-cased` \| 24 \| 16 \| 1024 \| 373 M \| Note: `flaubert-small-cased` is partially trained so performance is not guaranteed. Consider using it for debugging purpose only. ## Using FlauBERT with Hugging Face's Transformers ```python import torch from transformers import FlaubertModel, FlaubertTokenizer # Choose among ['flaubert/flaubert_small_cased', 'flaubert/flaubert_base_uncased', # 'flaubert/flaubert_base_cased', 'flaubert/flaubert_large_cased'] modelname = 'flaubert/flaubert_base_cased' # Load pretrained model and tokenizer flaubert, log = FlaubertModel.from_pretrained(modelname, output_loading_info=True) flaubert_tokenizer = FlaubertTokenizer.from_pretrained(modelname, do_lowercase=False) # do_lowercase=False if using cased models, True if using uncased ones sentence = "Le chat mange une pomme." token_ids = torch.tensor([flaubert_tokenizer.encode(sentence)]) last_layer = flaubert(token_ids)[0] print(last_layer.shape) # torch.Size([1, 8, 768]) -> (batch size x number of tokens x embedding dimension) # The BERT [CLS] token correspond to the first hidden state of the last layer cls_embedding = last_layer[:, 0, :] ``` Notes: if your `transformers` version is <=2.10.0, `modelname` should take one of the following values: ``` ['flaubert-small-cased', 'flaubert-base-uncased', 'flaubert-base-cased', 'flaubert-large-cased'] ``` ## References If you use FlauBERT or the FLUE Benchmark for your scientific publication, or if you find the resources in this repository useful, please cite one of the following papers: [LREC paper](http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.302.pdf) ``` @InProceedings{le2020flaubert, author = {Le, Hang and Vial, Lo\"{i}c and Frej, Jibril and Segonne, Vincent and Coavoux, Maximin and Lecouteux, Benjamin and Allauzen, Alexandre and Crabb\'{e}, Beno\^{i}t and Besacier, Laurent and Schwab, Didier}, title = {FlauBERT: Unsupervised Language Model Pre-training for French}, booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference}, month = {May}, year = {2020}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {2479--2490}, url = {https://www.aclweb.org/anthology/2020.lrec-1.302} } ``` [TALN paper](https://hal.archives-ouvertes.fr/hal-02784776/) ``` @inproceedings{le2020flaubert, title = {FlauBERT: des mod{\`e}les de langue contextualis{\'e}s pr{\'e}-entra{\^\i}n{\'e}s pour le fran{\c{c}}ais}, author = {Le, Hang and Vial, Lo{\"\i}c and Frej, Jibril and Segonne, Vincent and Coavoux, Maximin and Lecouteux, Benjamin and Allauzen, Alexandre and Crabb{\'e}, Beno{\^\i}t and Besacier, Laurent and Schwab, Didier}, booktitle = {Actes de la 6e conf{\'e}rence conjointe Journ{\'e}es d'{\'E}tudes sur la Parole (JEP, 31e {\'e}dition), Traitement Automatique des Langues Naturelles (TALN, 27e {\'e}dition), Rencontre des {\'E}tudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (R{\'E}CITAL, 22e {\'e}dition). Volume 2: Traitement Automatique des Langues Naturelles}, pages = {268--278}, year = {2020}, organization = {ATALA} } ```
flaubert/flaubert_base_cased	flaubert	2024-05-14T12:38:22Z	5,735	8	transformers	[ "transformers", "pytorch", "safetensors", "flaubert", "fill-mask", "bert", "language-model", "flue", "french", "bert-base", "flaubert-base", "cased", "fr", "dataset:flaubert", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2022-03-02T23:29:05Z	--- language: fr license: mit datasets: - flaubert metrics: - flue tags: - bert - language-model - flaubert - flue - french - bert-base - flaubert-base - cased --- # FlauBERT: Unsupervised Language Model Pre-training for French FlauBERT is a French BERT trained on a very large and heterogeneous French corpus. Models of different sizes are trained using the new CNRS (French National Centre for Scientific Research) [Jean Zay](http://www.idris.fr/eng/jean-zay/ ) supercomputer. Along with FlauBERT comes [FLUE](https://github.com/getalp/Flaubert/tree/master/flue): an evaluation setup for French NLP systems similar to the popular GLUE benchmark. The goal is to enable further reproducible experiments in the future and to share models and progress on the French language.For more details please refer to the [official website](https://github.com/getalp/Flaubert). ## FlauBERT models \| Model name \| Number of layers \| Attention Heads \| Embedding Dimension \| Total Parameters \| \| :------: \| :---: \| :---: \| :---: \| :---: \| \| `flaubert-small-cased` \| 6 \| 8 \| 512 \| 54 M \| \| `flaubert-base-uncased` \| 12 \| 12 \| 768 \| 137 M \| \| `flaubert-base-cased` \| 12 \| 12 \| 768 \| 138 M \| \| `flaubert-large-cased` \| 24 \| 16 \| 1024 \| 373 M \| Note: `flaubert-small-cased` is partially trained so performance is not guaranteed. Consider using it for debugging purpose only. ## Using FlauBERT with Hugging Face's Transformers ```python import torch from transformers import FlaubertModel, FlaubertTokenizer # Choose among ['flaubert/flaubert_small_cased', 'flaubert/flaubert_base_uncased', # 'flaubert/flaubert_base_cased', 'flaubert/flaubert_large_cased'] modelname = 'flaubert/flaubert_base_cased' # Load pretrained model and tokenizer flaubert, log = FlaubertModel.from_pretrained(modelname, output_loading_info=True) flaubert_tokenizer = FlaubertTokenizer.from_pretrained(modelname, do_lowercase=False) # do_lowercase=False if using cased models, True if using uncased ones sentence = "Le chat mange une pomme." token_ids = torch.tensor([flaubert_tokenizer.encode(sentence)]) last_layer = flaubert(token_ids)[0] print(last_layer.shape) # torch.Size([1, 8, 768]) -> (batch size x number of tokens x embedding dimension) # The BERT [CLS] token correspond to the first hidden state of the last layer cls_embedding = last_layer[:, 0, :] ``` Notes: if your `transformers` version is <=2.10.0, `modelname` should take one of the following values: ``` ['flaubert-small-cased', 'flaubert-base-uncased', 'flaubert-base-cased', 'flaubert-large-cased'] ``` ## References If you use FlauBERT or the FLUE Benchmark for your scientific publication, or if you find the resources in this repository useful, please cite one of the following papers: [LREC paper](http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.302.pdf) ``` @InProceedings{le2020flaubert, author = {Le, Hang and Vial, Lo\"{i}c and Frej, Jibril and Segonne, Vincent and Coavoux, Maximin and Lecouteux, Benjamin and Allauzen, Alexandre and Crabb\'{e}, Beno\^{i}t and Besacier, Laurent and Schwab, Didier}, title = {FlauBERT: Unsupervised Language Model Pre-training for French}, booktitle = {Proceedings of The 12th Language Resources and Evaluation Conference}, month = {May}, year = {2020}, address = {Marseille, France}, publisher = {European Language Resources Association}, pages = {2479--2490}, url = {https://www.aclweb.org/anthology/2020.lrec-1.302} } ``` [TALN paper](https://hal.archives-ouvertes.fr/hal-02784776/) ``` @inproceedings{le2020flaubert, title = {FlauBERT: des mod{\`e}les de langue contextualis{\'e}s pr{\'e}-entra{\^\i}n{\'e}s pour le fran{\c{c}}ais}, author = {Le, Hang and Vial, Lo{\"\i}c and Frej, Jibril and Segonne, Vincent and Coavoux, Maximin and Lecouteux, Benjamin and Allauzen, Alexandre and Crabb{\'e}, Beno{\^\i}t and Besacier, Laurent and Schwab, Didier}, booktitle = {Actes de la 6e conf{\'e}rence conjointe Journ{\'e}es d'{\'E}tudes sur la Parole (JEP, 31e {\'e}dition), Traitement Automatique des Langues Naturelles (TALN, 27e {\'e}dition), Rencontre des {\'E}tudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (R{\'E}CITAL, 22e {\'e}dition). Volume 2: Traitement Automatique des Langues Naturelles}, pages = {268--278}, year = {2020}, organization = {ATALA} } ```
MoMonir/granite-8b-code-instruct-GGUF	MoMonir	2024-05-14T12:30:48Z	21	0	transformers	[ "transformers", "gguf", "code", "granite", "llama-cpp", "gguf-my-repo", "text-generation", "dataset:bigcode/commitpackft", "dataset:TIGER-Lab/MathInstruct", "dataset:meta-math/MetaMathQA", "dataset:glaiveai/glaive-code-assistant-v3", "dataset:glaive-function-calling-v2", "dataset:bugdaryan/sql-create-context-instruction", "dataset:garage-bAInd/Open-Platypus", "dataset:nvidia/HelpSteer", "base_model:ibm-granite/granite-8b-code-base-4k", "base_model:quantized:ibm-granite/granite-8b-code-base-4k", "license:apache-2.0", "model-index", "region:us", "conversational" ]	text-generation	2024-05-14T12:14:08Z	--- license: apache-2.0 library_name: transformers tags: - code - granite - llama-cpp - gguf-my-repo base_model: ibm-granite/granite-8b-code-base datasets: - bigcode/commitpackft - TIGER-Lab/MathInstruct - meta-math/MetaMathQA - glaiveai/glaive-code-assistant-v3 - glaive-function-calling-v2 - bugdaryan/sql-create-context-instruction - garage-bAInd/Open-Platypus - nvidia/HelpSteer metrics: - code_eval pipeline_tag: text-generation inference: false model-index: - name: granite-8b-code-instruct results: - task: type: text-generation dataset: name: HumanEvalSynthesis(Python) type: bigcode/humanevalpack metrics: - type: pass@1 value: 57.9 name: pass@1 - type: pass@1 value: 52.4 name: pass@1 - type: pass@1 value: 58.5 name: pass@1 - type: pass@1 value: 43.3 name: pass@1 - type: pass@1 value: 48.2 name: pass@1 - type: pass@1 value: 37.2 name: pass@1 - type: pass@1 value: 53.0 name: pass@1 - type: pass@1 value: 42.7 name: pass@1 - type: pass@1 value: 52.4 name: pass@1 - type: pass@1 value: 36.6 name: pass@1 - type: pass@1 value: 43.9 name: pass@1 - type: pass@1 value: 16.5 name: pass@1 - type: pass@1 value: 39.6 name: pass@1 - type: pass@1 value: 40.9 name: pass@1 - type: pass@1 value: 48.2 name: pass@1 - type: pass@1 value: 41.5 name: pass@1 - type: pass@1 value: 39.0 name: pass@1 - type: pass@1 value: 32.9 name: pass@1 --- # MoMonir/granite-8b-code-instruct-GGUF This model was converted to GGUF format from [`ibm-granite/granite-8b-code-instruct`](https://huggingface.co/ibm-granite/granite-8b-code-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/ibm-granite/granite-8b-code-instruct) for more details on the model. <!-- README_GGUF.md-about-gguf start --> ### About GGUF ([TheBloke](https://huggingface.co/TheBloke) Description) GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. <!-- README_GGUF.md-about-gguf end --> ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo MoMonir/granite-8b-code-instruct-GGUF --model granite-8b-code-instruct.Q4_K_M.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo MoMonir/granite-8b-code-instruct-GGUF --model granite-8b-code-instruct.Q4_K_M.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m granite-8b-code-instruct.Q4_K_M.gguf -n 128 ```
Reihaneh/wav2vec2_fy_nl_with_lid_22	Reihaneh	2024-05-14T12:27:14Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-14T12:27:13Z	--- 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]
roofdancer/thesis-bart-finetuned-on-transformed	roofdancer	2024-05-14T12:22:11Z	121	0	transformers	[ "transformers", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:sshleifer/distilbart-cnn-6-6", "base_model:finetune:sshleifer/distilbart-cnn-6-6", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-05-14T09:17:21Z	--- license: apache-2.0 base_model: sshleifer/distilbart-cnn-6-6 tags: - generated_from_trainer metrics: - rouge model-index: - name: thesis-bart-finetuned-on-transformed 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. --> # thesis-bart-finetuned-on-transformed This model is a fine-tuned version of [sshleifer/distilbart-cnn-6-6](https://huggingface.co/sshleifer/distilbart-cnn-6-6) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.7334 - Rouge1: 39.6832 - Rouge2: 13.5041 - Rougel: 21.0331 - Rougelsum: 35.5827 - Gen Len: 141.1176 ## 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: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rouge1 \| Rouge2 \| Rougel \| Rougelsum \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:-------:\|:-------:\|:-------:\|:---------:\|:--------:\| \| 2.829 \| 1.0 \| 2811 \| 2.7334 \| 39.6832 \| 13.5041 \| 21.0331 \| 35.5827 \| 141.1176 \| ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2
Mag0g/Ezekiel27_3	Mag0g	2024-05-14T12:19:18Z	128	0	transformers	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T12:18:12Z	--- 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]
avaimon/mt5-summarizer-2	avaimon	2024-05-14T12:19:17Z	64	0	transformers	[ "transformers", "tf", "mt5", "text2text-generation", "generated_from_keras_callback", "base_model:google/mt5-small", "base_model:finetune:google/mt5-small", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-05-14T09:44:40Z	--- license: apache-2.0 base_model: google/mt5-small tags: - generated_from_keras_callback model-index: - name: avaimon/mt5-summarizer-2 results: [] --- <!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # avaimon/mt5-summarizer-2 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 3.3832 - Validation Loss: 2.5500 - Epoch: 2 ## 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: - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5.6e-05, 'decay_steps': 15000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: mixed_float16 ### Training results \| Train Loss \| Validation Loss \| Epoch \| \|:----------:\|:---------------:\|:-----:\| \| 5.0111 \| 2.6779 \| 0 \| \| 3.6902 \| 2.5984 \| 1 \| \| 3.3832 \| 2.5500 \| 2 \| ### Framework versions - Transformers 4.40.2 - TensorFlow 2.15.0 - Datasets 2.19.1 - Tokenizers 0.19.1
Ayush-1722/Meta-Llama-3-8B-Instruct-Summarize-v0.1-16K-LoRANET-Merged	Ayush-1722	2024-05-14T12:17:54Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "facebook", "meta", "pytorch", "llama-3", "conversational", "en", "license:llama3", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T12:03:58Z	--- language: - en license: llama3 tags: - facebook - meta - pytorch - llama - llama-3 pipeline_tag: text-generation extra_gated_prompt: "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version\ \ Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for\ \ use, reproduction, distribution and modification of the Llama Materials set forth\ \ herein.\n\"Documentation\" means the specifications, manuals and documentation\ \ accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\ \"Licensee\" or \"you\" means you, or your employer or any other person or entity\ \ (if you are entering into this Agreement on such person or entity’s behalf), of\ \ the age required under applicable laws, rules or regulations to provide legal\ \ consent and that has legal authority to bind your employer or such other person\ \ or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama\ \ 3\" means the foundational large language models and software and algorithms,\ \ including machine-learning model code, trained model weights, inference-enabling\ \ code, training-enabling code, fine-tuning enabling code and other elements of\ \ the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\ \"Llama Materials\" means, collectively, Meta’s proprietary Meta Llama 3 and Documentation\ \ (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"\ we\" means Meta Platforms Ireland Limited (if you are located in or, if you are\ \ an entity, your principal place of business is in the EEA or Switzerland) and\ \ Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n\ \ \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted\ \ a non-exclusive, worldwide, non-transferable and royalty-free limited license\ \ under Meta’s intellectual property or other rights owned by Meta embodied in the\ \ Llama Materials to use, reproduce, distribute, copy, create derivative works of,\ \ and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni.\ \ If you distribute or make available the Llama Materials (or any derivative works\ \ thereof), or a product or service that uses any of them, including another AI\ \ model, you shall (A) provide a copy of this Agreement with any such Llama Materials;\ \ and (B) prominently display “Built with Meta Llama 3” on a related website, user\ \ interface, blogpost, about page, or product documentation. If you use the Llama\ \ Materials to create, train, fine tune, or otherwise improve an AI model, which\ \ is distributed or made available, you shall also include “Llama 3” at the beginning\ \ of any such AI model name.\nii. If you receive Llama Materials, or any derivative\ \ works thereof, from a Licensee as part of an integrated end user product, then\ \ Section 2 of this Agreement will not apply to you.\niii. You must retain in all\ \ copies of the Llama Materials that you distribute the following attribution notice\ \ within a “Notice” text file distributed as a part of such copies: “Meta Llama\ \ 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms,\ \ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\ \ applicable laws and regulations (including trade compliance laws and regulations)\ \ and adhere to the Acceptable Use Policy for the Llama Materials (available at\ \ https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference\ \ into this Agreement.\nv. You will not use the Llama Materials or any output or\ \ results of the Llama Materials to improve any other large language model (excluding\ \ Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If,\ \ on the Meta Llama 3 version release date, the monthly active users of the products\ \ or services made available by or for Licensee, or Licensee’s affiliates, is greater\ \ than 700 million monthly active users in the preceding calendar month, you must\ \ request a license from Meta, which Meta may grant to you in its sole discretion,\ \ and you are not authorized to exercise any of the rights under this Agreement\ \ unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer\ \ of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT\ \ AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF\ \ ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,\ \ INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY,\ \ OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING\ \ THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME\ \ ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n\ 4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER\ \ ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,\ \ OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT,\ \ SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META\ \ OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n\ 5. Intellectual Property.\na. No trademark licenses are granted under this Agreement,\ \ and in connection with the Llama Materials, neither Meta nor Licensee may use\ \ any name or mark owned by or associated with the other or any of its affiliates,\ \ except as required for reasonable and customary use in describing and redistributing\ \ the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you\ \ a license to use “Llama 3” (the “Mark”) solely as required to comply with the\ \ last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently\ \ accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All\ \ goodwill arising out of your use of the Mark will inure to the benefit of Meta.\n\ b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for\ \ Meta, with respect to any derivative works and modifications of the Llama Materials\ \ that are made by you, as between you and Meta, you are and will be the owner of\ \ such derivative works and modifications.\nc. If you institute litigation or other\ \ proceedings against Meta or any entity (including a cross-claim or counterclaim\ \ in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results,\ \ or any portion of any of the foregoing, constitutes infringement of intellectual\ \ property or other rights owned or licensable by you, then any licenses granted\ \ to you under this Agreement shall terminate as of the date such litigation or\ \ claim is filed or instituted. You will indemnify and hold harmless Meta from and\ \ against any claim by any third party arising out of or related to your use or\ \ distribution of the Llama Materials.\n6. Term and Termination. The term of this\ \ Agreement will commence upon your acceptance of this Agreement or access to the\ \ Llama Materials and will continue in full force and effect until terminated in\ \ accordance with the terms and conditions herein. Meta may terminate this Agreement\ \ if you are in breach of any term or condition of this Agreement. Upon termination\ \ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\ \ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\ \ and Jurisdiction. This Agreement will be governed and construed under the laws\ \ of the State of California without regard to choice of law principles, and the\ \ UN Convention on Contracts for the International Sale of Goods does not apply\ \ to this Agreement. The courts of California shall have exclusive jurisdiction\ \ of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use\ \ Policy\nMeta is committed to promoting safe and fair use of its tools and features,\ \ including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable\ \ Use Policy (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n\ #### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly.\ \ You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate\ \ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\ \ contribute to, encourage, plan, incite, or further illegal or unlawful activity\ \ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\ \ or harm to children, including the solicitation, creation, acquisition, or dissemination\ \ of child exploitative content or failure to report Child Sexual Abuse Material\n\ \ 3. Human trafficking, exploitation, and sexual violence\n 4. The\ \ illegal distribution of information or materials to minors, including obscene\ \ materials, or failure to employ legally required age-gating in connection with\ \ such information or materials.\n 5. Sexual solicitation\n 6. Any\ \ other criminal activity\n 2. Engage in, promote, incite, or facilitate the\ \ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\ \ 3. Engage in, promote, incite, or facilitate discrimination or other unlawful\ \ or harmful conduct in the provision of employment, employment benefits, credit,\ \ housing, other economic benefits, or other essential goods and services\n 4.\ \ Engage in the unauthorized or unlicensed practice of any profession including,\ \ but not limited to, financial, legal, medical/health, or related professional\ \ practices\n 5. Collect, process, disclose, generate, or infer health, demographic,\ \ or other sensitive personal or private information about individuals without rights\ \ and consents required by applicable laws\n 6. Engage in or facilitate any action\ \ or generate any content that infringes, misappropriates, or otherwise violates\ \ any third-party rights, including the outputs or results of any products or services\ \ using the Llama Materials\n 7. Create, generate, or facilitate the creation\ \ of malicious code, malware, computer viruses or do anything else that could disable,\ \ overburden, interfere with or impair the proper working, integrity, operation\ \ or appearance of a website or computer system\n2. Engage in, promote, incite,\ \ facilitate, or assist in the planning or development of activities that present\ \ a risk of death or bodily harm to individuals, including use of Meta Llama 3 related\ \ to the following:\n 1. Military, warfare, nuclear industries or applications,\ \ espionage, use for materials or activities that are subject to the International\ \ Traffic Arms Regulations (ITAR) maintained by the United States Department of\ \ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\ \ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\ \ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\ \ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\ \ content intended to incite or promote violence, abuse, or any infliction of bodily\ \ harm to an individual\n3. Intentionally deceive or mislead others, including use\ \ of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering\ \ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\ \ or furthering defamatory content, including the creation of defamatory statements,\ \ images, or other content\n 3. Generating, promoting, or further distributing\ \ spam\n 4. Impersonating another individual without consent, authorization,\ \ or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are\ \ human-generated\n 6. Generating or facilitating false online engagement, including\ \ fake reviews and other means of fake online engagement\n4. Fail to appropriately\ \ disclose to end users any known dangers of your AI system\nPlease report any violation\ \ of this Policy, software “bug,” or other problems that could lead to a violation\ \ of this Policy through one of the following means:\n * Reporting issues with\ \ the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n\ \ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\ \ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\ \ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]" extra_gated_fields: First Name: text Last Name: text Date of birth: date_picker Country: country Affiliation: text geo: ip_location ? By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy : checkbox extra_gated_description: The information you provide will be collected, stored, processed and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/). extra_gated_button_content: Submit widget: - example_title: Hello messages: - role: user content: Hey my name is Julien! How are you? - example_title: Winter holidays messages: - role: system content: You are a helpful and honest assistant. Please, respond concisely and truthfully. - role: user content: Can you recommend a good destination for Winter holidays? - example_title: Programming assistant messages: - role: system content: You are a helpful and honest code and programming assistant. Please, respond concisely and truthfully. - role: user content: Write a function that computes the nth fibonacci number. inference: parameters: max_new_tokens: 300 stop: - <\|end_of_text\|> - <\|eot_id\|> --- ## Model Details Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes. The Llama 3 instruction tuned models are optimized for dialogue use cases and outperform many of the available open source chat models on common industry benchmarks. Further, in developing these models, we took great care to optimize helpfulness and safety. Model developers Meta Variations Llama 3 comes in two sizes — 8B and 70B parameters — in pre-trained and instruction tuned variants. Input Models input text only. Output Models generate text and code only. Model Architecture Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. <table> <tr> <td> </td> <td><strong>Training Data</strong> </td> <td><strong>Params</strong> </td> <td><strong>Context length</strong> </td> <td><strong>GQA</strong> </td> <td><strong>Token count</strong> </td> <td><strong>Knowledge cutoff</strong> </td> </tr> <tr> <td rowspan="2" >Llama 3 </td> <td rowspan="2" >A new mix of publicly available online data. </td> <td>8B </td> <td>8k </td> <td>Yes </td> <td rowspan="2" >15T+ </td> <td>March, 2023 </td> </tr> <tr> <td>70B </td> <td>8k </td> <td>Yes </td> <td>December, 2023 </td> </tr> </table> Llama 3 family of models. Token counts refer to pretraining data only. Both the 8 and 70B versions use Grouped-Query Attention (GQA) for improved inference scalability. Model Release Date April 18, 2024. Status This is a static model trained on an offline dataset. Future versions of the tuned models will be released as we improve model safety with community feedback. License A custom commercial license is available at: [https://llama.meta.com/llama3/license](https://llama.meta.com/llama3/license) Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama3). For more technical information about generation parameters and recipes for how to use Llama 3 in applications, please go [here](https://github.com/meta-llama/llama-recipes). ## Intended Use Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction tuned models are intended for assistant-like chat, whereas pretrained models can be adapted for a variety of natural language generation tasks. Out-of-scope Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3 Community License. Use in languages other than English. Note: Developers may fine-tune Llama 3 models for languages beyond English provided they comply with the Llama 3 Community License and the Acceptable Use Policy. ## How to use This repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original `llama3` codebase. ### Use with transformers You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both. #### Transformers pipeline ```python import transformers import torch model_id = "meta-llama/Meta-Llama-3-8B-Instruct" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto", ) messages = [ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, {"role": "user", "content": "Who are you?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` #### Transformers AutoModelForCausalLM ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_id = "meta-llama/Meta-Llama-3-8B-Instruct" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto", ) messages = [ {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, {"role": "user", "content": "Who are you?"}, ] input_ids = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" ).to(model.device) terminators = [ tokenizer.eos_token_id, tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = model.generate( input_ids, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.6, top_p=0.9, ) response = outputs[0][input_ids.shape[-1]:] print(tokenizer.decode(response, skip_special_tokens=True)) ``` ### Use with `llama3` Please, follow the instructions in the [repository](https://github.com/meta-llama/llama3) To download Original checkpoints, see the example command below leveraging `huggingface-cli`: ``` huggingface-cli download meta-llama/Meta-Llama-3-8B-Instruct --include "original/" --local-dir Meta-Llama-3-8B-Instruct ``` For Hugging Face support, we recommend using transformers or TGI, but a similar command works. ## Hardware and Software Training Factors* We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute. Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program. <table> <tr> <td> </td> <td><strong>Time (GPU hours)</strong> </td> <td><strong>Power Consumption (W)</strong> </td> <td><strong>Carbon Emitted(tCO2eq)</strong> </td> </tr> <tr> <td>Llama 3 8B </td> <td>1.3M </td> <td>700 </td> <td>390 </td> </tr> <tr> <td>Llama 3 70B </td> <td>6.4M </td> <td>700 </td> <td>1900 </td> </tr> <tr> <td>Total </td> <td>7.7M </td> <td> </td> <td>2290 </td> </tr> </table> CO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others. ## Training Data Overview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data. Data Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively. ## Benchmarks In this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see [here](https://github.com/meta-llama/llama3/blob/main/eval_methodology.md). ### Base pretrained models <table> <tr> <td><strong>Category</strong> </td> <td><strong>Benchmark</strong> </td> <td><strong>Llama 3 8B</strong> </td> <td><strong>Llama2 7B</strong> </td> <td><strong>Llama2 13B</strong> </td> <td><strong>Llama 3 70B</strong> </td> <td><strong>Llama2 70B</strong> </td> </tr> <tr> <td rowspan="6" >General </td> <td>MMLU (5-shot) </td> <td>66.6 </td> <td>45.7 </td> <td>53.8 </td> <td>79.5 </td> <td>69.7 </td> </tr> <tr> <td>AGIEval English (3-5 shot) </td> <td>45.9 </td> <td>28.8 </td> <td>38.7 </td> <td>63.0 </td> <td>54.8 </td> </tr> <tr> <td>CommonSenseQA (7-shot) </td> <td>72.6 </td> <td>57.6 </td> <td>67.6 </td> <td>83.8 </td> <td>78.7 </td> </tr> <tr> <td>Winogrande (5-shot) </td> <td>76.1 </td> <td>73.3 </td> <td>75.4 </td> <td>83.1 </td> <td>81.8 </td> </tr> <tr> <td>BIG-Bench Hard (3-shot, CoT) </td> <td>61.1 </td> <td>38.1 </td> <td>47.0 </td> <td>81.3 </td> <td>65.7 </td> </tr> <tr> <td>ARC-Challenge (25-shot) </td> <td>78.6 </td> <td>53.7 </td> <td>67.6 </td> <td>93.0 </td> <td>85.3 </td> </tr> <tr> <td>Knowledge reasoning </td> <td>TriviaQA-Wiki (5-shot) </td> <td>78.5 </td> <td>72.1 </td> <td>79.6 </td> <td>89.7 </td> <td>87.5 </td> </tr> <tr> <td rowspan="4" >Reading comprehension </td> <td>SQuAD (1-shot) </td> <td>76.4 </td> <td>72.2 </td> <td>72.1 </td> <td>85.6 </td> <td>82.6 </td> </tr> <tr> <td>QuAC (1-shot, F1) </td> <td>44.4 </td> <td>39.6 </td> <td>44.9 </td> <td>51.1 </td> <td>49.4 </td> </tr> <tr> <td>BoolQ (0-shot) </td> <td>75.7 </td> <td>65.5 </td> <td>66.9 </td> <td>79.0 </td> <td>73.1 </td> </tr> <tr> <td>DROP (3-shot, F1) </td> <td>58.4 </td> <td>37.9 </td> <td>49.8 </td> <td>79.7 </td> <td>70.2 </td> </tr> </table> ### Instruction tuned models <table> <tr> <td><strong>Benchmark</strong> </td> <td><strong>Llama 3 8B</strong> </td> <td><strong>Llama 2 7B</strong> </td> <td><strong>Llama 2 13B</strong> </td> <td><strong>Llama 3 70B</strong> </td> <td><strong>Llama 2 70B</strong> </td> </tr> <tr> <td>MMLU (5-shot) </td> <td>68.4 </td> <td>34.1 </td> <td>47.8 </td> <td>82.0 </td> <td>52.9 </td> </tr> <tr> <td>GPQA (0-shot) </td> <td>34.2 </td> <td>21.7 </td> <td>22.3 </td> <td>39.5 </td> <td>21.0 </td> </tr> <tr> <td>HumanEval (0-shot) </td> <td>62.2 </td> <td>7.9 </td> <td>14.0 </td> <td>81.7 </td> <td>25.6 </td> </tr> <tr> <td>GSM-8K (8-shot, CoT) </td> <td>79.6 </td> <td>25.7 </td> <td>77.4 </td> <td>93.0 </td> <td>57.5 </td> </tr> <tr> <td>MATH (4-shot, CoT) </td> <td>30.0 </td> <td>3.8 </td> <td>6.7 </td> <td>50.4 </td> <td>11.6 </td> </tr> </table> ### Responsibility & Safety We believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community. Foundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications. Rather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience. As part of the Llama 3 release, we updated our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including [Meta Llama Guard 2](https://llama.meta.com/purple-llama/) and [Code Shield](https://llama.meta.com/purple-llama/) safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a [reference implementation](https://github.com/meta-llama/llama-recipes/tree/main/recipes/responsible_ai) to get you started. #### Llama 3-Instruct As outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case. <span style="text-decoration:underline;">Safety</span> For our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable. <span style="text-decoration:underline;">Refusals</span> In addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2. We built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date. #### Responsible release In addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision. Misuse If you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy/](https://llama.meta.com/llama3/use-policy/). #### Critical risks <span style="text-decoration:underline;">CBRNE</span> (Chemical, Biological, Radiological, Nuclear, and high yield Explosives) We have conducted a two fold assessment of the safety of the model in this area: * Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks. * Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model). ### <span style="text-decoration:underline;">Cyber Security </span> We have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of [equivalent coding capability](https://huggingface.co/spaces/facebook/CyberSecEval). ### <span style="text-decoration:underline;">Child Safety</span> Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences. ### Community Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama). Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community. ## Ethical Considerations and Limitations The core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress. But Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating [Purple Llama](https://github.com/facebookresearch/PurpleLlama) solutions into your workflows and specifically [Llama Guard](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety. Please see the Responsible Use Guide available at [http://llama.meta.com/responsible-use-guide](http://llama.meta.com/responsible-use-guide) ## Citation instructions @article{llama3modelcard, title={Llama 3 Model Card}, author={AI@Meta}, year={2024}, url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md} } ## Contributors Aaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos
ravi6389/twitter_sentiment	ravi6389	2024-05-14T12:13:25Z	0	0	null	[ "license:other", "region:us" ]	null	2024-05-14T08:45:54Z	--- license: other license_name: other license_link: LICENSE ---
Sajjo/w2v-bert-2.0-unified_v2	Sajjo	2024-05-14T12:10:55Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-14T12:09:11Z	--- 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]
openbmb/Eurus-RM-7b	openbmb	2024-05-14T12:09:46Z	605	27	transformers	[ "transformers", "safetensors", "mistral", "feature-extraction", "reward_model", "text-classification", "custom_code", "dataset:openbmb/UltraFeedback", "dataset:openbmb/UltraInteract_pair", "dataset:openbmb/UltraSafety", "arxiv:2404.02078", "license:apache-2.0", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-classification	2024-04-02T08:36:55Z	--- license: apache-2.0 datasets: - openbmb/UltraFeedback - openbmb/UltraInteract_pair - openbmb/UltraSafety tags: - reward_model pipeline_tag: text-classification --- # Links - 📜 [Paper](https://arxiv.org/abs/2404.02078) - 🤗 [Eurus Collection](https://huggingface.co/collections/openbmb/eurus-660bc40bec5376b3adc9d1c5) - 🤗 UltraInteract - [SFT](https://huggingface.co/datasets/openbmb/UltraInteract_sft) - [Preference Learning](https://huggingface.co/datasets/openbmb/UltraInteract_pair) - [GitHub Repo](https://github.com/OpenBMB/Eurus) # Introduction Eurus-RM-7B is trained on a mixture of [UltraInteract](https://huggingface.co/datasets/openbmb/UltraInteract), [UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback), and [UltraSafety](https://huggingface.co/datasets/openbmb/UltraSafety), with a specifically designed reward modeling objective for reasoning to directly increase. - EURUS-RM-7B stands out as the best 7B RM overall and achieves similar or better performance than much larger baselines. Particularly, it outperforms GPT-4 in certain tasks. - Our training objective is beneficial in improving RM performance on hard problems and reasoning. - ULTRAINTERACT is compatible with other datasets like UltraFeedback and UltraSafety, and mixing these datasets can balance different RM abilities. - EURUS-RM-7B improves LLMs’ reasoning performance by a large margin through reranking. ## Usage ```python from transformers import AutoTokenizer, AutoModel import torch def test(model_path): dataset = [ # cases in webgpt; we use the same template as Mistral-Instruct-v0.2 { "chosen": "[INST] Sural relates to which part of the body? [/INST] The sural region is the muscular swelling of the back of the leg below the knee, formed chiefly by the bellies of the gastrocnemius and soleus muscles [1,2].", "rejected": "[INST] Sural relates to which part of the body? [/INST] The Sural nerve runs down the side of the leg near the small saphenous vein, then passes forward below the lateral malleolus and continues on the outside of the foot as the lateral dorsal cutaneous nerve, which then communicates with the intermediate dorsal cutaneous nerve, which branches off to the side of the foot. [1]", } ] tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModel.from_pretrained(model_path, trust_remote_code=True) with torch.no_grad(): for example in dataset: inputs = tokenizer(example["chosen"], return_tensors="pt") chosen_reward = model(inputs).item() inputs = tokenizer(example["rejected"], return_tensors="pt") rejected_reward = model(inputs).item() print(chosen_reward - rejected_reward) test("openbmb/Eurus-RM-7b") # Output: 47.4404296875 ``` ## Evaluation - Eurus-RM-7B stands out as the best 7B RM overall and achieves similar or better performance than much larger baselines. Particularly, it outperforms GPT-4 in certain tasks. - Our training objective is beneficial in improving RM performance on hard problems and reasoning. - ULTRAINTERACT is compatible with other datasets like UltraFeedback and UltraSafety, and mixing these datasets can balance different RM abilities. - Eurus-RM-7B improves LLMs’ reasoning performance by a large margin through reranking. <img src="./figures/rm_exp.png" alt="stats" style="zoom: 40%;" /> ## Citation ``` @misc{yuan2024advancing, title={Advancing LLM Reasoning Generalists with Preference Trees}, author={Lifan Yuan and Ganqu Cui and Hanbin Wang and Ning Ding and Xingyao Wang and Jia Deng and Boji Shan and Huimin Chen and Ruobing Xie and Yankai Lin and Zhenghao Liu and Bowen Zhou and Hao Peng and Zhiyuan Liu and Maosong Sun}, year={2024}, eprint={2404.02078}, archivePrefix={arXiv}, } ```
ludocomito/Minerva-MoE-2x3B	ludocomito	2024-05-14T12:05:44Z	2,817	0	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "moe", "frankenmoe", "merge", "mergekit", "lazymergekit", "DeepMount00/Minerva-3B-base-RAG", "FairMind/Minerva-3B-Instruct-v1.0", "base_model:DeepMount00/Minerva-3B-base-RAG", "base_model:merge:DeepMount00/Minerva-3B-base-RAG", "base_model:FairMind/Minerva-3B-Instruct-v1.0", "base_model:merge:FairMind/Minerva-3B-Instruct-v1.0", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-13T17:22:01Z	--- license: apache-2.0 tags: - moe - frankenmoe - merge - mergekit - lazymergekit - DeepMount00/Minerva-3B-base-RAG - FairMind/Minerva-3B-Instruct-v1.0 base_model: - DeepMount00/Minerva-3B-base-RAG - FairMind/Minerva-3B-Instruct-v1.0 --- # Minerva-MoE-3x3B Minerva-MoE-3x3B is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [DeepMount00/Minerva-3B-base-RAG](https://huggingface.co/DeepMount00/Minerva-3B-base-RAG) * [FairMind/Minerva-3B-Instruct-v1.0](https://huggingface.co/FairMind/Minerva-3B-Instruct-v1.0) ## Evaluation arc_it acc_norm: 31.91 hellaswag_it acc_norm: 52.20 mmmlu_it: 25.72 ## 🧩 Configuration ```yaml base_model: sapienzanlp/Minerva-3B-base-v1.0 experts: - source_model: DeepMount00/Minerva-3B-base-RAG positive_prompts: - "rispondi a domande" - "cosa è" - "chi è" - "dove è" - "come si" - "spiegami" - "definisci" - source_model: FairMind/Minerva-3B-Instruct-v1.0 positive_prompts: - "istruzione" - "input" - "risposta" - "scrivi" - "sequenza" - "istruzioni" dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers bitsandbytes accelerate from transformers import AutoTokenizer import transformers import torch model = "ludocomito/Minerva-MoE-3x3B" 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"]) ```
lmms-lab/llava-next-110b	lmms-lab	2024-05-14T12:05:00Z	41	21	transformers	[ "transformers", "safetensors", "llava", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-05-06T06:17:11Z	--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # LLaVA Model Card ## Model Details Model type: LLaVA is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture. Base LLM: Qwen/Qwen1.5-110B-Chat ### Model Description Repository: https://github.com/LLaVA-VL/LLaVA-NeXT Primary intended uses: The primary use of LLaVA is research on large multimodal models and chatbots. This is only for research exploration, and prohibited for commercial usage. Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence. ### License Notices This project utilizes certain datasets and checkpoints that are subject to their respective original licenses. Users must comply with all terms and conditions of these original licenses, including but not limited to the OpenAI Terms of Use for the dataset and the specific licenses for base language models for checkpoints trained using the dataset (e.g. Llama-1/2 community license for LLaMA-2 and Vicuna-v1.5, [Tongyi Qianwen LICENSE AGREEMENT](https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT) and [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](https://llama.meta.com/llama3/license/)). This project does not impose any additional constraints beyond those stipulated in the original licenses. Furthermore, users are reminded to ensure that their use of the dataset and checkpoints is in compliance with all applicable laws and regulations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Procedure We conducted the training on LLaVA-1.6's codebase with adding support of Llama-3 and Qwen model. ### Training Hyperparameters ```shell LLM_VERSION="Qwen/Qwen1.5-110B-Chat" LLM_VERSION_CLEAN="${LLM_VERSION//\//_}" VISION_MODEL_VERSION="openai/clip-vit-large-patch14-336" VISION_MODEL_VERSION_CLEAN="${VISION_MODEL_VERSION//\//_}" PROMPT_VERSION=plain PRETRAIN_DATA_VERSION="blip558k" ############### Pretrain ################ BASE_RUN_NAME="llavanext-${LLM_VERSION_CLEAN}-${VISION_MODEL_VERSION_CLEAN}-pretrain_${PRETRAIN_DATA_VERSION}_plain" echo "BASE_RUN_NAME: ${BASE_RUN_NAME}" PROMPT_VERSION="qwen_1_5" MID_RUN_NAME="llavanext-${LLM_VERSION_CLEAN}-${VISION_MODEL_VERSION_CLEAN}-pretrain_${PRETRAIN_DATA_VERSION}_plain-ft_la1_6mix_d32k" echo "MID_RUN_NAME: ${MID_RUN_NAME}" torchrun # with necessary torchrun information for distributed training\ llava/train/train_mem.py \ --deepspeed scripts/zero3.json \ --model_name_or_path $LLM_VERSION \ --version $PROMPT_VERSION \ --data_path="/path/to/data/llava_instruct/llava1_6mix.json" \ --image_folder /path/to/data/llava_data \ --pretrain_mm_mlp_adapter="./checkpoints/projectors/${BASE_RUN_NAME}/mm_projector.bin" \ --mm_tunable_parts="mm_vision_tower,mm_mlp_adapter,mm_language_model" \ --mm_vision_tower_lr=2e-6 \ --vision_tower ${VISION_MODEL_VERSION} \ --mm_projector_type mlp2x_gelu \ --mm_vision_select_layer -2 \ --mm_use_im_start_end False \ --mm_use_im_patch_token False \ --group_by_modality_length True \ --image_aspect_ratio anyres \ --image_grid_pinpoints "[(336, 672), (672, 336), (672, 672), (1008, 336), (336, 1008)]" \ --mm_patch_merge_type spatial_unpad \ --bf16 True \ --run_name $MID_RUN_NAME \ --output_dir ./checkpoints/$MID_RUN_NAME \ --num_train_epochs 1 \ --per_device_train_batch_size 1 \ --per_device_eval_batch_size 4 \ --gradient_accumulation_steps 1 \ --evaluation_strategy "no" \ --save_strategy "steps" \ --save_steps 3000 \ --save_total_limit 1 \ --learning_rate 1e-5 \ --weight_decay 0. \ --warmup_ratio 0.03 \ --lr_scheduler_type "cosine" \ --logging_steps 1 \ --tf32 True \ --model_max_length 32768 \ --gradient_checkpointing True \ --dataloader_num_workers 8 \ --lazy_preprocess True \ --report_to wandb \ --torch_compile True \ --torch_compile_backend "inductor" --dataloader_drop_last True ``` ### Training Data - 558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP. - 158K GPT-generated multimodal instruction-following data. - 500K academic-task-oriented VQA data mixture. - 50K GPT-4V data mixture. - 40K ShareGPT data. - 20K COCO Caption data. #### Speeds, Sizes, Times [optional] The training cost is ~18-20 hours on 16 x 8 NVIDIA H800-SXM4-80GB (may vary due to hardware differences). [More Information Needed] ## Evaluation The evaluation is conducted with the support of [`lmms-eval`](https://github.com/EvolvingLMMs-Lab/lmms-eval)
stablediffusionapi/xsmergerealisticdyai	stablediffusionapi	2024-05-14T11:58:04Z	29	0	diffusers	[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2024-05-14T11:56:56Z	--- license: creativeml-openrail-m tags: - modelslab.com - stable-diffusion-api - text-to-image - ultra-realistic pinned: true --- # API Inference ![generated from modelslab.com](https://cdn2.stablediffusionapi.com/generations/bf190b5a-fe19-437c-ba05-82f29cb1f7ad-0.png) ## Get API Key Get API key from [ModelsLab API](http://modelslab.com), No Payment needed. Replace Key in below code, change model_id to "xsmergerealisticdyai" Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://modelslab.com/docs) Try model for free: [Generate Images](https://modelslab.com/models/xsmergerealisticdyai) Model link: [View model](https://modelslab.com/models/xsmergerealisticdyai) View all models: [View Models](https://modelslab.com/models) import requests import json url = "https://modelslab.com/api/v6/images/text2img" payload = json.dumps({ "key": "your_api_key", "model_id": "xsmergerealisticdyai", "prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": "no", "enhance_prompt": "yes", "seed": None, "guidance_scale": 7.5, "multi_lingual": "no", "panorama": "no", "self_attention": "no", "upscale": "no", "embeddings": "embeddings_model_id", "lora": "lora_model_id", "webhook": None, "track_id": None }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) print(response.text) > Use this coupon code to get 25% off DMGG0RBN
Arshik/testing	Arshik	2024-05-14T11:56:49Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-14T11:56:48Z	--- 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]
mradermacher/Alphacode-MALI-11B-GGUF	mradermacher	2024-05-14T11:54:37Z	44	0	transformers	[ "transformers", "gguf", "merge", "ko", "base_model:Alphacode-AI/Alphacode-MALI-11B", "base_model:quantized:Alphacode-AI/Alphacode-MALI-11B", "license:cc-by-4.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-05-14T11:16:25Z	--- base_model: Alphacode-AI/Alphacode-MALI-11B language: - ko library_name: transformers license: cc-by-4.0 quantized_by: mradermacher tags: - merge --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> static quants of https://huggingface.co/Alphacode-AI/Alphacode-MALI-11B <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q2_K.gguf) \| Q2_K \| 4.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.IQ3_XS.gguf) \| IQ3_XS \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q3_K_S.gguf) \| Q3_K_S \| 4.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.IQ3_S.gguf) \| IQ3_S \| 4.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.IQ3_M.gguf) \| IQ3_M \| 4.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q3_K_M.gguf) \| Q3_K_M \| 5.3 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q3_K_L.gguf) \| Q3_K_L \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.IQ4_XS.gguf) \| IQ4_XS \| 5.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q4_K_S.gguf) \| Q4_K_S \| 6.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q4_K_M.gguf) \| Q4_K_M \| 6.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q5_K_S.gguf) \| Q5_K_S \| 7.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q5_K_M.gguf) \| Q5_K_M \| 7.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q6_K.gguf) \| Q6_K \| 8.9 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Alphacode-MALI-11B-GGUF/resolve/main/Alphacode-MALI-11B.Q8_0.gguf) \| Q8_0 \| 11.5 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
avinashnraj/tinyllama-colorist-v0	avinashnraj	2024-05-14T11:51:59Z	144	1	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T11:50:39Z	--- 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]
mradermacher/pali-8B-moe-GGUF	mradermacher	2024-05-14T11:51:07Z	3	0	transformers	[ "transformers", "gguf", "en", "endpoints_compatible", "region:us" ]	null	2024-05-14T10:21:33Z	--- base_model: DataGuard/pali-8B-moe language: - en library_name: transformers quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> static quants of https://huggingface.co/DataGuard/pali-8B-moe <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q2_K.gguf) \| Q2_K \| 8.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.IQ3_XS.gguf) \| IQ3_XS \| 10.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q3_K_S.gguf) \| Q3_K_S \| 10.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.IQ3_S.gguf) \| IQ3_S \| 10.6 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.IQ3_M.gguf) \| IQ3_M \| 10.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q3_K_M.gguf) \| Q3_K_M \| 11.7 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q3_K_L.gguf) \| Q3_K_L \| 12.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.IQ4_XS.gguf) \| IQ4_XS \| 13.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q4_K_S.gguf) \| Q4_K_S \| 13.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q4_K_M.gguf) \| Q4_K_M \| 14.7 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q5_K_S.gguf) \| Q5_K_S \| 16.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q5_K_M.gguf) \| Q5_K_M \| 17.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q6_K.gguf) \| Q6_K \| 19.9 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/pali-8B-moe-GGUF/resolve/main/pali-8B-moe.Q8_0.gguf) \| Q8_0 \| 25.8 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
justinhl/hybrid-qa1	justinhl	2024-05-14T11:49:47Z	34	0	transformers	[ "transformers", "safetensors", "phi3", "text-generation", "question-answering", "custom_code", "arxiv:1910.09700", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	question-answering	2024-05-13T07:19:41Z	--- library_name: transformers pipeline_tag: question-answering license: mit --- # 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]
FO-UA/adapt-llm-fraud	FO-UA	2024-05-14T11:47:45Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2024-05-14T11:47:45Z	--- license: apache-2.0 ---
darshit0503/openorca_constitution_7b_chat_uncensored_FT_GGUF	darshit0503	2024-05-14T11:47:22Z	9	1	transformers	[ "transformers", "gguf", "mistral", "text-generation-inference", "unsloth", "en", "base_model:Open-Orca/Mistral-7B-OpenOrca", "base_model:quantized:Open-Orca/Mistral-7B-OpenOrca", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2024-05-14T11:45:06Z	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - mistral - gguf base_model: Open-Orca/Mistral-7B-OpenOrca --- # Uploaded model - Developed by: darshit0503 - License: apache-2.0 - Finetuned from model : Open-Orca/Mistral-7B-OpenOrca This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Whiskas0663/dqn-SpaceInvadersNoFrameskip-v4	Whiskas0663	2024-05-14T11:44:57Z	0	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2024-05-14T11:44:16Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 672.50 +/- 308.55 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Whiskas0663 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Whiskas0663 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Whiskas0663 ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
1024m/EXALT-1A-GEMMA-5A-16bit	1024m	2024-05-14T11:41:41Z	4	0	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/gemma-7b-bnb-4bit", "base_model:finetune:unsloth/gemma-7b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T11:37:15Z	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - gemma - trl - sft base_model: unsloth/gemma-7b-bnb-4bit --- # Uploaded model - Developed by: 1024m - License: apache-2.0 - Finetuned from model : unsloth/gemma-7b-bnb-4bit This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
1024m/EXALT-1A-LLAMA3-5B-Lora	1024m	2024-05-14T11:41:08Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "base_model:finetune:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-05-14T09:00:04Z	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl base_model: unsloth/llama-3-8b-bnb-4bit --- # Uploaded model - Developed by: 1024m - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
neopolita/meta-llama-3-8b-gguf	neopolita	2024-05-14T11:40:37Z	85	0	null	[ "gguf", "endpoints_compatible", "region:us" ]	null	2024-04-18T19:03:31Z	--- {} --- # GGUF quants for [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) using [llama.cpp](https://github.com/ggerganov/llama.cpp) Terms of Use: Please check the [original model](https://huggingface.co/meta-llama/Meta-Llama-3-8B) <picture> <img alt="cthulhu" src="https://huggingface.co/neopolita/common/resolve/main/profile.png"> </picture> ## Quants * `q2_k`: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors. * `q3_k_s`: Uses Q3_K for all tensors * `q3_k_m`: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K * `q3_k_l`: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K * `q4_0`: Original quant method, 4-bit. * `q4_1`: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. * `q4_k_s`: Uses Q4_K for all tensors * `q4_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K * `q5_0`: Higher accuracy, higher resource usage and slower inference. * `q5_1`: Even higher accuracy, resource usage and slower inference. * `q5_k_s`: Uses Q5_K for all tensors * `q5_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K * `q6_k`: Uses Q8_K for all tensors * `q8_0`: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.
Vipinap/RAFT-llama3-8b-v1	Vipinap	2024-05-14T11:40:33Z	78	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-05-14T11:25:02Z	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl base_model: raft_llama3_8b_ft_stable --- # Uploaded model - Developed by: Vipinap - License: apache-2.0 - Finetuned from model : raft_llama3_8b_ft_stable This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
sasa3396/distilbert-base-uncased-finetuned-squad	sasa3396	2024-05-14T11:36:36Z	113	0	transformers	[ "transformers", "pytorch", "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	2024-05-14T11:04:20Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer model-index: - name: distilbert-base-uncased-finetuned-squad 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-base-uncased-finetuned-squad 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: 1 - eval_batch_size: 1 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Framework versions - Transformers 4.34.0 - Pytorch 2.1.0+cu118 - Datasets 2.18.0 - Tokenizers 0.14.1
kyl23/hw3_WNLI_bitfit_1e-4	kyl23	2024-05-14T11:32:16Z	180	0	transformers	[ "transformers", "safetensors", "roberta", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-05-14T11:31:51Z	--- 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]
abc88767/2c50	abc88767	2024-05-14T11:30:53Z	128	0	transformers	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T11:29:20Z	--- 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]
Litzy619/G0513HMA6H	Litzy619	2024-05-14T11:28:19Z	0	0	null	[ "safetensors", "generated_from_trainer", "base_model:google/gemma-2b", "base_model:finetune:google/gemma-2b", "license:gemma", "region:us" ]	null	2024-05-14T05:56:23Z	--- license: gemma base_model: google/gemma-2b tags: - generated_from_trainer model-index: - name: G0513HMA6H 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. --> # G0513HMA6H This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1240 ## 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: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 3.161 \| 0.09 \| 10 \| 2.8226 \| \| 2.4808 \| 0.18 \| 20 \| 1.9257 \| \| 1.4989 \| 0.27 \| 30 \| 0.9749 \| \| 0.6093 \| 0.36 \| 40 \| 0.2572 \| \| 0.1925 \| 0.45 \| 50 \| 0.1591 \| \| 0.1558 \| 0.54 \| 60 \| 0.1523 \| \| 0.1517 \| 0.63 \| 70 \| 0.1497 \| \| 0.1503 \| 0.73 \| 80 \| 0.1487 \| \| 0.1422 \| 0.82 \| 90 \| 0.1499 \| \| 0.1459 \| 0.91 \| 100 \| 0.1487 \| \| 0.1494 \| 1.0 \| 110 \| 0.1495 \| \| 0.1438 \| 1.09 \| 120 \| 0.1499 \| \| 0.1458 \| 1.18 \| 130 \| 0.1472 \| \| 0.1465 \| 1.27 \| 140 \| 0.1463 \| \| 0.1483 \| 1.36 \| 150 \| 0.1464 \| \| 0.1426 \| 1.45 \| 160 \| 0.1480 \| \| 0.1433 \| 1.54 \| 170 \| 0.1450 \| \| 0.1443 \| 1.63 \| 180 \| 0.1440 \| \| 0.1455 \| 1.72 \| 190 \| 0.1495 \| \| 0.1437 \| 1.81 \| 200 \| 0.1439 \| \| 0.1433 \| 1.9 \| 210 \| 0.1398 \| \| 0.1408 \| 1.99 \| 220 \| 0.1387 \| \| 0.1348 \| 2.08 \| 230 \| 0.1340 \| \| 0.1311 \| 2.18 \| 240 \| 0.1334 \| \| 0.1303 \| 2.27 \| 250 \| 0.1297 \| \| 0.1319 \| 2.36 \| 260 \| 0.1285 \| \| 0.1297 \| 2.45 \| 270 \| 0.1291 \| \| 0.129 \| 2.54 \| 280 \| 0.1270 \| \| 0.1247 \| 2.63 \| 290 \| 0.1252 \| \| 0.1251 \| 2.72 \| 300 \| 0.1242 \| \| 0.1299 \| 2.81 \| 310 \| 0.1239 \| \| 0.1271 \| 2.9 \| 320 \| 0.1240 \| \| 0.1269 \| 2.99 \| 330 \| 0.1240 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.0
irenicquasar/llama3-8B-dpo-bnb-4bit	irenicquasar	2024-05-14T11:20:05Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "base_model:finetune:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-05-14T11:19:57Z	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl base_model: unsloth/llama-3-8b-bnb-4bit --- # Uploaded model - Developed by: irenicquasar - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
GodsonNtungi/swahili_llm_v892	GodsonNtungi	2024-05-14T11:19:59Z	4	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "base_model:finetune:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T11:16:34Z	--- language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl - sft base_model: unsloth/llama-3-8b-Instruct-bnb-4bit --- # Uploaded model - Developed by: GodsonNtungi - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF	mradermacher	2024-05-14T11:19:43Z	3	0	transformers	[ "transformers", "gguf", "en", "base_model:chihoonlee10/T3Q-ko-solar-dpo-v8.0", "base_model:quantized:chihoonlee10/T3Q-ko-solar-dpo-v8.0", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-05-14T10:41:05Z	--- base_model: chihoonlee10/T3Q-ko-solar-dpo-v8.0 language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> static quants of https://huggingface.co/chihoonlee10/T3Q-ko-solar-dpo-v8.0 <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q2_K.gguf) \| Q2_K \| 4.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.IQ3_XS.gguf) \| IQ3_XS \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q3_K_S.gguf) \| Q3_K_S \| 4.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.IQ3_S.gguf) \| IQ3_S \| 4.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.IQ3_M.gguf) \| IQ3_M \| 4.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q3_K_M.gguf) \| Q3_K_M \| 5.3 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q3_K_L.gguf) \| Q3_K_L \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.IQ4_XS.gguf) \| IQ4_XS \| 5.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q4_K_S.gguf) \| Q4_K_S \| 6.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q4_K_M.gguf) \| Q4_K_M \| 6.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q5_K_S.gguf) \| Q5_K_S \| 7.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q5_K_M.gguf) \| Q5_K_M \| 7.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q6_K.gguf) \| Q6_K \| 8.9 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-ko-solar-dpo-v8.0-GGUF/resolve/main/T3Q-ko-solar-dpo-v8.0.Q8_0.gguf) \| Q8_0 \| 11.5 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
SaidiSouhaieb/5e65445f4cdd6508ff3ea928e41632ca488866a0	SaidiSouhaieb	2024-05-14T11:16:47Z	146	0	transformers	[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2024-05-14T11:11:31Z	--- 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]
second-state/StarCoder2-15B-Instruct-v0.1-GGUF	second-state	2024-05-14T11:05:09Z	50	0	transformers	[ "transformers", "gguf", "starcoder2", "text-generation", "code", "base_model:bigcode/starcoder2-15b-instruct-v0.1", "base_model:quantized:bigcode/starcoder2-15b-instruct-v0.1", "license:bigcode-openrail-m", "autotrain_compatible", "region:us", "conversational" ]	text-generation	2024-05-14T08:32:33Z	--- base_model: bigcode/starcoder2-15b-instruct-v0.1 inference: false license: bigcode-openrail-m library_name: transformers model_creator: bigcode model_name: StarCoder2-15B-Instruct-v0.1 pipeline_tag: text-generation quantized_by: Second State Inc. tags: - code --- <!-- header start --> <!-- 200823 --> <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <hr style="margin-top: 1.0em; margin-bottom: 1.0em;"> <!-- header end --> # StarCoder2-15B-Instruct-v0.1-GGUF ## Original Model [bigcode/starcoder2-15b-instruct-v0.1](https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1) ## Run with LlamaEdge - LlamaEdge version: coming soon - Context size: `6144` ## Quantized GGUF Models \| Name \| Quant method \| Bits \| Size \| Use case \| \| ---- \| ---- \| ---- \| ---- \| ----- \| \| [starcoder2-15b-instruct-v0.1-Q2_K.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q2_K.gguf) \| Q2_K \| 2 \| 6.19 GB\| smallest, significant quality loss - not recommended for most purposes \| \| [starcoder2-15b-instruct-v0.1-Q3_K_L.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_L.gguf) \| Q3_K_L \| 3 \| 8.97 GB\| small, substantial quality loss \| \| [starcoder2-15b-instruct-v0.1-Q3_K_M.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_M.gguf) \| Q3_K_M \| 3 \| 8.1 GB\| very small, high quality loss \| \| [starcoder2-15b-instruct-v0.1-Q3_K_S.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q3_K_S.gguf) \| Q3_K_S \| 3 \| 6.99 GB\| very small, high quality loss \| \| [starcoder2-15b-instruct-v0.1-Q4_0.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q4_0.gguf) \| Q4_0 \| 4 \| 9.07 GB\| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [starcoder2-15b-instruct-v0.1-Q4_K_M.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q4_K_M.gguf) \| Q4_K_M \| 4 \| 9.86 GB\| medium, balanced quality - recommended \| \| [starcoder2-15b-instruct-v0.1-Q4_K_S.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q4_K_S.gguf) \| Q4_K_S \| 4 \| 9.26 GB\| small, greater quality loss \| \| [starcoder2-15b-instruct-v0.1-Q5_0.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q5_0.gguf) \| Q5_0 \| 5 \| 11 GB\| legacy; medium, balanced quality - prefer using Q4_K_M \| \| [starcoder2-15b-instruct-v0.1-Q5_K_M.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q5_K_M.gguf) \| Q5_K_M \| 5 \| 11.4 GB\| large, very low quality loss - recommended \| \| [starcoder2-15b-instruct-v0.1-Q5_K_S.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q5_K_S.gguf) \| Q5_K_S \| 5 \| 11 GB\| large, low quality loss - recommended \| \| [starcoder2-15b-instruct-v0.1-Q6_K.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q6_K.gguf) \| Q6_K \| 6 \| 13.1 GB\| very large, extremely low quality loss \| \| [starcoder2-15b-instruct-v0.1-Q8_0.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-Q8_0.gguf) \| Q8_0 \| 8 \| 17 GB\| very large, extremely low quality loss - not recommended \| \| [starcoder2-15b-instruct-v0.1-f16.gguf](https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF/blob/main/starcoder2-15b-instruct-v0.1-f16.gguf) \| f16 \| 16 \| 31.9 GB\| \| Quantized with llama.cpp b2824
mradermacher/Prob-Gen-70B-GGUF	mradermacher	2024-05-14T11:01:46Z	17	0	transformers	[ "transformers", "gguf", "en", "base_model:DukeNLP/Prob-Gen-70B", "base_model:quantized:DukeNLP/Prob-Gen-70B", "endpoints_compatible", "region:us" ]	null	2024-05-14T06:45:22Z	--- base_model: DukeNLP/Prob-Gen-70B language: - en library_name: transformers quantized_by: mradermacher tags: [] --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> static quants of https://huggingface.co/DukeNLP/Prob-Gen-70B <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q2_K.gguf) \| Q2_K \| 26.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.IQ3_XS.gguf) \| IQ3_XS \| 29.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.IQ3_S.gguf) \| IQ3_S \| 31.0 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q3_K_S.gguf) \| Q3_K_S \| 31.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.IQ3_M.gguf) \| IQ3_M \| 32.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q3_K_M.gguf) \| Q3_K_M \| 34.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q3_K_L.gguf) \| Q3_K_L \| 37.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.IQ4_XS.gguf) \| IQ4_XS \| 38.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q4_K_S.gguf) \| Q4_K_S \| 40.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q4_K_M.gguf) \| Q4_K_M \| 42.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q5_K_S.gguf) \| Q5_K_S \| 48.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q5_K_M.gguf) \| Q5_K_M \| 50.0 \| \| \| [PART 1](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q6_K.gguf.part2of2) \| Q6_K \| 58.0 \| very good quality \| \| [PART 1](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Prob-Gen-70B-GGUF/resolve/main/Prob-Gen-70B.Q8_0.gguf.part2of2) \| Q8_0 \| 75.1 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
Litzy619/G0513HMA11H	Litzy619	2024-05-14T11:00:50Z	0	0	null	[ "safetensors", "generated_from_trainer", "base_model:google/gemma-2b", "base_model:finetune:google/gemma-2b", "license:gemma", "region:us" ]	null	2024-05-14T10:13:52Z	--- license: gemma base_model: google/gemma-2b tags: - generated_from_trainer model-index: - name: G0513HMA11H 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. --> # G0513HMA11H This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1235 ## 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: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 100 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 3.1913 \| 0.09 \| 10 \| 2.9118 \| \| 2.6582 \| 0.18 \| 20 \| 2.2403 \| \| 1.8555 \| 0.27 \| 30 \| 1.4009 \| \| 1.0564 \| 0.36 \| 40 \| 0.6458 \| \| 0.3947 \| 0.45 \| 50 \| 0.2176 \| \| 0.1854 \| 0.54 \| 60 \| 0.1585 \| \| 0.1558 \| 0.63 \| 70 \| 0.1516 \| \| 0.1551 \| 0.73 \| 80 \| 0.1501 \| \| 0.1434 \| 0.82 \| 90 \| 0.1503 \| \| 0.1462 \| 0.91 \| 100 \| 0.1500 \| \| 0.1504 \| 1.0 \| 110 \| 0.1489 \| \| 0.1444 \| 1.09 \| 120 \| 0.1481 \| \| 0.1457 \| 1.18 \| 130 \| 0.1485 \| \| 0.1463 \| 1.27 \| 140 \| 0.1464 \| \| 0.1476 \| 1.36 \| 150 \| 0.1457 \| \| 0.1417 \| 1.45 \| 160 \| 0.1480 \| \| 0.1429 \| 1.54 \| 170 \| 0.1450 \| \| 0.1455 \| 1.63 \| 180 \| 0.1444 \| \| 0.1449 \| 1.72 \| 190 \| 0.1470 \| \| 0.1414 \| 1.81 \| 200 \| 0.1397 \| \| 0.1405 \| 1.9 \| 210 \| 0.1387 \| \| 0.1378 \| 1.99 \| 220 \| 0.1337 \| \| 0.1306 \| 2.08 \| 230 \| 0.1303 \| \| 0.1297 \| 2.18 \| 240 \| 0.1304 \| \| 0.1288 \| 2.27 \| 250 \| 0.1310 \| \| 0.1297 \| 2.36 \| 260 \| 0.1269 \| \| 0.1277 \| 2.45 \| 270 \| 0.1271 \| \| 0.1242 \| 2.54 \| 280 \| 0.1270 \| \| 0.1229 \| 2.63 \| 290 \| 0.1256 \| \| 0.1226 \| 2.72 \| 300 \| 0.1239 \| \| 0.1249 \| 2.81 \| 310 \| 0.1236 \| \| 0.1237 \| 2.9 \| 320 \| 0.1235 \| \| 0.1249 \| 2.99 \| 330 \| 0.1235 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.0
neopolita/yi-1.5-6b-gguf	neopolita	2024-05-14T10:57:34Z	15	0	null	[ "gguf", "endpoints_compatible", "region:us" ]	null	2024-05-14T10:34:26Z	--- {} --- # GGUF quants for [01-ai/Yi-1.5-6B](https://huggingface.co/01-ai/Yi-1.5-6B) using [llama.cpp](https://github.com/ggerganov/llama.cpp) Terms of Use: Please check the [original model](https://huggingface.co/01-ai/Yi-1.5-6B) <picture> <img alt="cthulhu" src="https://huggingface.co/neopolita/common/resolve/main/profile.png"> </picture> ## Quants * `q2_k`: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors. * `q3_k_s`: Uses Q3_K for all tensors * `q3_k_m`: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K * `q3_k_l`: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K * `q4_0`: Original quant method, 4-bit. * `q4_1`: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. * `q4_k_s`: Uses Q4_K for all tensors * `q4_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K * `q5_0`: Higher accuracy, higher resource usage and slower inference. * `q5_1`: Even higher accuracy, resource usage and slower inference. * `q5_k_s`: Uses Q5_K for all tensors * `q5_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K * `q6_k`: Uses Q8_K for all tensors * `q8_0`: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.
abhishek/autotrain-obj-det-cppe5-1	abhishek	2024-05-14T10:56:38Z	196	2	transformers	[ "transformers", "tensorboard", "safetensors", "detr", "object-detection", "autotrain", "vision", "dataset:cppe-5", "endpoints_compatible", "region:us" ]	object-detection	2024-05-14T09:36:39Z	--- tags: - autotrain - object-detection - vision 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: - cppe-5 --- # Model Trained Using AutoTrain - Problem type: Object Detection ## Validation Metrics loss: 0.8912756443023682 map: 0.4887 map_50: 0.8353 map_75: 0.473 map_small: 0.4091 map_medium: 0.3492 map_large: 0.679 mar_1: 0.3601 mar_10: 0.6056 mar_100: 0.6186 mar_small: 0.4686 mar_medium: 0.4922 mar_large: 0.7882 map_Coverall: 0.7 mar_100_Coverall: 0.7689 map_Face_Shield: 0.5987 mar_100_Face_Shield: 0.7294 map_Gloves: 0.3918 mar_100_Gloves: 0.523 map_Goggles: 0.3115 mar_100_Goggles: 0.5312 map_Mask: 0.4418 mar_100_Mask: 0.5404
readomni/dao-9b	readomni	2024-05-14T10:54:53Z	74	17	transformers	[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "conversational", "base_model:01-ai/Yi-1.5-9B", "base_model:finetune:01-ai/Yi-1.5-9B", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-13T11:20:45Z	--- license: apache-2.0 base_model: 01-ai/Yi-1.5-9B model-index: - name: dao-9b results: [] --- <div align="center"> <span style="font-size:5rem;">☯️</span> <h1>Dao-9B</h1> </div> ## Intro Dao-9B is the smaller, open-source version of the translation model powering the [Omni Translator](https://app.readomni.com), a state-of-the-art literary translation tool. While less capable than the full model, as it's on a less recent methodology and data, Dao-9B is still a powerful translation model that can be run locally and performs especially well on Chinese webnovels. While no comparison is available for this model, you can find the comparison page (against several other translation tools) for the full model [here](https://readomni.com/compare). ## Quick Start To get started quickly, you can explore the starter Colab notebook [here](https://colab.research.google.com/drive/1RTJ1zFmvTe4CVQyH2y_CWiStzVeARJ0Y?usp=sharing). We do not provide inference service for this model, you can instead try out the more powerful full model on the [Omni Translator](https://app.readomni.com). ## Usage To fully utilize the capability of this model in translation, it is recommended to follow the steps below: 1. Preprocessing: Prepare the text to be translated. Make sure that `\n\n` is used to separate paragraphs. Normalize the text via Unicode normalization (NFKC) and remove any extra spaces. 2. Chunking: Break the text into chunks of approximately 350 characters. This is to ensure that the model can handle the text efficiently. 3. Term Extraction: Extract terms from the text to be translated. This is especially useful for translating novels, where the same terms are used repeatedly across the chapters. 4. Translation: Translate the text using the model. Provide the terms extracted in step 3, and the previous chunk of text to the model to improve the translation quality. We provide a starting code that demonstrates most of the above steps in the [starter Colab notebook](https://colab.research.google.com/readomni). ### Extracting Terms Use the following prompt template to extract terms from the text: ```plaintext <context> {context} </context> <passage> {input} </passage> Given the above passage, please list out the terminologies and namings present that may be reused in the translations of future passages. Output the terminologies in the format of Raw, English. Use the CSV format. ``` ### Performing Translation Use the following prompt template to perform translation: ```plaintext <context> {context} </context> <passage> {input} </passage> <terms> {terms} </terms> You are a professional translator. Given the above passage, please translate the passage to English. ``` ## Limitations - This model is uncensored and may generate content that is inappropriate for some audiences. Please use with caution. - This model is trained with mainly Chinese -> English data, and may not perform well on other language pairs.
abc88767/3sc51	abc88767	2024-05-14T10:52:30Z	129	0	transformers	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T10:50:56Z	--- 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]
Mag0g/Ezekiel27_1	Mag0g	2024-05-14T10:49:18Z	128	0	transformers	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T10:48:06Z	--- 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]
Lumen8/SRA	Lumen8	2024-05-14T10:48:15Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2024-05-14T10:48:15Z	--- license: apache-2.0 ---
decentmakeover13/distilbert-imdb	decentmakeover13	2024-05-14T10:47:21Z	108	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-05-13T17:28:24Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer model-index: - name: distilbert-imdb 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-imdb 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: 5e-05 - train_batch_size: 70 - eval_batch_size: 70 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| No log \| 1.0 \| 358 \| 0.1874 \| 0.927 \| ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.1+cu121 - Datasets 2.14.5 - Tokenizers 0.15.1
Litzy619/G0513HMA5H	Litzy619	2024-05-14T10:39:58Z	0	0	null	[ "safetensors", "generated_from_trainer", "base_model:google/gemma-2b", "base_model:finetune:google/gemma-2b", "license:gemma", "region:us" ]	null	2024-05-14T06:01:24Z	--- license: gemma base_model: google/gemma-2b tags: - generated_from_trainer model-index: - name: G0513HMA5H 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. --> # G0513HMA5H This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1235 ## 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: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 3.1714 \| 0.09 \| 10 \| 2.8600 \| \| 2.6228 \| 0.18 \| 20 \| 2.1695 \| \| 1.764 \| 0.27 \| 30 \| 1.2598 \| \| 0.9021 \| 0.36 \| 40 \| 0.4452 \| \| 0.2786 \| 0.45 \| 50 \| 0.1866 \| \| 0.1669 \| 0.54 \| 60 \| 0.1556 \| \| 0.153 \| 0.63 \| 70 \| 0.1524 \| \| 0.1532 \| 0.73 \| 80 \| 0.1498 \| \| 0.1427 \| 0.82 \| 90 \| 0.1490 \| \| 0.1461 \| 0.91 \| 100 \| 0.1486 \| \| 0.1494 \| 1.0 \| 110 \| 0.1487 \| \| 0.1435 \| 1.09 \| 120 \| 0.1487 \| \| 0.145 \| 1.18 \| 130 \| 0.1473 \| \| 0.1452 \| 1.27 \| 140 \| 0.1461 \| \| 0.1475 \| 1.36 \| 150 \| 0.1447 \| \| 0.1413 \| 1.45 \| 160 \| 0.1474 \| \| 0.1427 \| 1.54 \| 170 \| 0.1444 \| \| 0.1437 \| 1.63 \| 180 \| 0.1426 \| \| 0.1429 \| 1.72 \| 190 \| 0.1420 \| \| 0.1386 \| 1.81 \| 200 \| 0.1366 \| \| 0.1382 \| 1.9 \| 210 \| 0.1363 \| \| 0.1371 \| 1.99 \| 220 \| 0.1320 \| \| 0.1312 \| 2.08 \| 230 \| 0.1298 \| \| 0.1277 \| 2.18 \| 240 \| 0.1323 \| \| 0.1296 \| 2.27 \| 250 \| 0.1320 \| \| 0.1297 \| 2.36 \| 260 \| 0.1298 \| \| 0.1283 \| 2.45 \| 270 \| 0.1276 \| \| 0.1258 \| 2.54 \| 280 \| 0.1272 \| \| 0.122 \| 2.63 \| 290 \| 0.1250 \| \| 0.1214 \| 2.72 \| 300 \| 0.1234 \| \| 0.1275 \| 2.81 \| 310 \| 0.1233 \| \| 0.1236 \| 2.9 \| 320 \| 0.1235 \| \| 0.1247 \| 2.99 \| 330 \| 0.1235 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.0
compressa-ai/Meta-Llama-3-8B-Instruct-medchat-LoRA	compressa-ai	2024-05-14T10:37:17Z	5	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:NousResearch/Meta-Llama-3-8B-Instruct", "base_model:adapter:NousResearch/Meta-Llama-3-8B-Instruct", "region:us" ]	null	2024-05-13T04:43:43Z	--- library_name: peft base_model: NousResearch/Meta-Llama-3-8B-Instruct --- # 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 0.7.1
Manpa/crypto-math-llama7b	Manpa	2024-05-14T10:36:36Z	7	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T10:33:02Z	--- 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]
hackint0sh/new_model	hackint0sh	2024-05-14T10:32:11Z	141	0	transformers	[ "transformers", "safetensors", "phi3", "text-generation", "conversational", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2024-05-14T10:12:13Z	--- 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]
Toastmachine/Orsay_museum_test_ko	Toastmachine	2024-05-14T10:31:07Z	0	0	peft	[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:saltlux/Ko-Llama3-Luxia-8B", "base_model:adapter:saltlux/Ko-Llama3-Luxia-8B", "license:llama3", "region:us" ]	null	2024-05-14T08:07:36Z	--- license: llama3 library_name: peft tags: - trl - sft - generated_from_trainer base_model: saltlux/Ko-Llama3-Luxia-8B model-index: - name: Orsay_museum_test_ko 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. --> # Orsay_museum_test_ko This model is a fine-tuned version of [saltlux/Ko-Llama3-Luxia-8B](https://huggingface.co/saltlux/Ko-Llama3-Luxia-8B) on the Orsay_meseum_exhibited 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: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - training_steps: 2000 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.2 - Pytorch 2.2.1+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1
neopolita/yi-1.5-6b-chat-gguf	neopolita	2024-05-14T10:30:41Z	16	0	null	[ "gguf", "endpoints_compatible", "region:us", "conversational" ]	null	2024-05-14T10:07:42Z	--- {} --- # GGUF quants for [01-ai/Yi-1.5-6B-Chat](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) using [llama.cpp](https://github.com/ggerganov/llama.cpp) Terms of Use: Please check the [original model](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) <picture> <img alt="cthulhu" src="https://huggingface.co/neopolita/common/resolve/main/profile.png"> </picture> ## Quants * `q2_k`: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors. * `q3_k_s`: Uses Q3_K for all tensors * `q3_k_m`: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K * `q3_k_l`: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K * `q4_0`: Original quant method, 4-bit. * `q4_1`: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. * `q4_k_s`: Uses Q4_K for all tensors * `q4_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K * `q5_0`: Higher accuracy, higher resource usage and slower inference. * `q5_1`: Even higher accuracy, resource usage and slower inference. * `q5_k_s`: Uses Q5_K for all tensors * `q5_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K * `q6_k`: Uses Q8_K for all tensors * `q8_0`: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.
mrhacker7599/moondream1.0	mrhacker7599	2024-05-14T10:29:18Z	113	1	transformers	[ "transformers", "pytorch", "safetensors", "moondream1", "text-generation", "custom_code", "en", "autotrain_compatible", "region:us" ]	text-generation	2024-05-14T10:24:19Z	--- language: - en --- # 🌔 moondream1 1.6B parameter model built by [@vikhyatk](https://x.com/vikhyatk) using SigLIP, Phi-1.5 and the LLaVa training dataset. The model is release for research purposes only, commercial use is not allowed. Try it out on [Huggingface Spaces](https://huggingface.co/spaces/mrhacker7599/moondream-Vision)! Usage ``` pip install transformers timm einops ``` ```python from transformers import AutoModelForCausalLM, CodeGenTokenizerFast as Tokenizer from PIL import Image model_id = "mrhacker7599/moondream1.0" model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True) tokenizer = Tokenizer.from_pretrained(model_id) image = Image.open('<IMAGE_PATH>') enc_image = model.encode_image(image) print(model.answer_question(enc_image, "<QUESTION>", tokenizer)) ``` ## Benchmarks \| Model \| Parameters \| VQAv2 \| GQA \| TextVQA \| \| --- \| --- \| --- \| --- \| --- \| \| LLaVA-1.5 \| 13.3B \| 80.0 \| 63.3 \| 61.3 \| \| LLaVA-1.5 \| 7.3B \| 78.5 \| 62.0 \| 58.2 \| \| moondream1 \| 1.6B \| 74.7 \| 57.9 \| 35.6 \| ## Examples \| Image \| Examples \| \| --- \| --- \| \| ![](assets/demo-1.jpg) \| What is the title of this book?<br>The Little Book of Deep Learning<br><br>What can you tell me about this book?<br>The book in the image is titled "The Little Book of Deep Learning." It appears to be a guide or manual that provides information and instructions on the subject of deep learning. The book is described as being small and thin, making it easy to carry and read. It is set in a room with a view outside, suggesting that the person holding the book might be in a living or working space with a view. The content of the book is likely to be complex, as the title implies a focus on advanced concepts in deep learning.<br><br>Where is the person standing?<br> The person is standing on a balcony or deck, which is outside. \| \| ![](assets/demo-2.jpg) \| What type of food is the girl holding?<br>The girl is holding a hamburger.<br><br>What color is the woman's hair?<br>The woman's hair is white.<br><br>What is the girl doing in the image?<br>The girl in the image is eating a hamburger. \| \| ![](assets/demo-3.jpg) \| What color is the train?<br>The train is red.<br><br>What is the bus doing in the image?<br> The bus in the image is driving down a city street, passing through an intersection.<br><br>What kind of public transportation is in the image?<br>The image features a red train or trolley as the public transportation option. \| \| ![](assets/demo-4.jpg) \| What is the girl looking at?<br>The girl is looking at her reflection in the mirror.<br><br>What color is the woman's hair?<br>The woman's hair is brown.<br><br>What is the woman doing in the mirror?<br>The woman is adjusting her hair in the mirror. \| \| ![](assets/demo-5.jpg) \| What might be the reason for the dog's aggressive behavior?<br>The dog's aggressive behavior, including its growling, baring its teeth, and showing its sharp teeth, could be due to various reasons. It is possible that the dog is feeling threatened, scared, or defensive about something in its environment, such as another animal, a loud noise, or a person nearby. Alternatively, the dog might be reacting to a command it received from its owner, or it could be experiencing discomfort or pain, which is causing it to display aggressive behavior. It is essential to observe the dog's body language and context to determine the underlying cause of its aggressive behavior and respond accordingly to address its needs or concerns.<br><br>What kind of dog is in the picture?<br>The dog in the picture is a small, black and white chihuahua. \|
Ham1mad1/videomae-base-Vsl-Lab-PC-V10	Ham1mad1	2024-05-14T10:28:28Z	63	0	transformers	[ "transformers", "safetensors", "videomae", "video-classification", "generated_from_trainer", "endpoints_compatible", "region:us" ]	video-classification	2024-05-14T04:43:22Z	--- tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-Vsl-Lab-PC-V10 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. --> # videomae-base-Vsl-Lab-PC-V10 This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.9720 - Accuracy: 0.8584 ## 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: 10 - eval_batch_size: 10 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 160 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.0 \| 0.51 \| 81 \| 1.2591 \| 0.8283 \| \| 0.0001 \| 1.49 \| 160 \| 0.9720 \| 0.8584 \| ### Framework versions - Transformers 4.39.1 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
aur0307/pii-bert	aur0307	2024-05-14T10:27:47Z	106	0	transformers	[ "transformers", "safetensors", "bert", "token-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	token-classification	2024-05-14T10:27:17Z	--- 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]
nayohan/llama3-instrucTrans-enko-8b	nayohan	2024-05-14T10:26:20Z	769	26	transformers	[ "transformers", "safetensors", "llama", "text-generation", "translation", "enko", "ko", "conversational", "en", "dataset:nayohan/aihub-en-ko-translation-1.2m", "dataset:nayohan/translate_corpus_313k", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-13T13:49:09Z	--- language: - en - ko license: llama3 library_name: transformers tags: - translation - enko - ko base_model: - meta-llama/Meta-Llama-3-8B-Instruct datasets: - nayohan/aihub-en-ko-translation-1.2m - nayohan/translate_corpus_313k pipeline_tag: text-generation metrics: - sacrebleu --- # instructTrans ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6152b4b9ecf3ca6ab820e325/oRlzxHQy3Qvqf4zfh5Wcj.png) # Introduction llama3-8b-instructTrans-en-ko model is trained on translation datasets(english->korean) based on Llama-3-8B-it. To translate the English instruction dataset. - [nayohan/aihub-en-ko-translation-1.2m](https://huggingface.co/datasets/nayohan/aihub-en-ko-translation-1.2m) - [nayohan/translate_corpus_313k](https://huggingface.co/datasets/nayohan/translate_corpus_313k) ### Loading the Model Use the following Python code to load the model: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "nayohan/llama3-instrucTrans-enko-8b" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, device_map="auto", torch_dtype=torch.bfloat16 ) ``` ### Generating Text This model supports translation from english to korean. To translate text, use the following Python code: ```python system_prompt="당신은 번역기 입니다. 영어를 한국어로 번역하세요." sentence = "The aerospace industry is a flower in the field of technology and science." conversation = [{'role': 'system', 'content': system_prompt}, {'role': 'user', 'content': sentence}] inputs = tokenizer.apply_chat_template( conversation, tokenize=True, add_generation_prompt=True, return_tensors='pt' ).to("cuda") outputs = model.generate(inputs, max_new_tokens=4096) # Finetuned with length 4096 print(tokenizer.decode(outputs[0][len(inputs[0]):])) ``` ``` # Result INPUT: <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|>\n\n당신은 번역기 입니다. 영어를 한국어로 번역하세요.<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|>\n\nThe aerospace industry is a flower in the field of technology and science.<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|>\n\n OUTPUT: 항공우주 산업은 기술과 과학 분야의 꽃입니다.<\|eot_id\|> INPUT: <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|>\n\n당신은 번역기 입니다. 영어를 한국어로 번역하세요.<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|>\n\n Technical and basic sciences are very important in terms of research. It has a significant impact on the industrial development of a country. Government policies control the research budget.<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|>\n\n OUTPUT: 기술 및 기초 과학은 연구 측면에서 매우 중요합니다. 이는 한 국가의 산업 발전에 큰 영향을 미칩니다. 정부 정책은 연구 예산을 통제합니다.<\|eot_id\|> ``` ``` # EVAL_RESULT (2405_KO_NEWS) (max_new_tokens=512) "en_ref":"This controversy arose around a new advertisement for the latest iPad Pro that Apple released on YouTube on the 7th. The ad shows musical instruments, statues, cameras, and paints being crushed in a press, followed by the appearance of the iPad Pro in their place. It appears to emphasize the new iPad Pro's artificial intelligence features, advanced display, performance, and thickness. Apple mentioned that the newly unveiled iPad Pro is equipped with the latest 'M4' chip and is the thinnest device in Apple's history. The ad faced immediate backlash upon release, as it graphically depicts objects symbolizing creators being crushed. Critics argue that the imagery could be interpreted as technology trampling on human creators. Some have also voiced concerns that it evokes a situation where creators are losing ground due to AI." "ko_ref":"이번 논란은 애플이 지난 7일 유튜브에 공개한 신형 아이패드 프로 광고를 둘러싸고 불거졌다. 해당 광고 영상은 악기와 조각상, 카메라, 물감 등을 압착기로 짓누른 뒤 그 자리에 아이패드 프로를 등장시키는 내용이었다. 신형 아이패드 프로의 인공지능 기능들과 진화된 디스플레이와 성능, 두께 등을 강조하기 위한 취지로 풀이된다. 애플은 이번에 공개한 아이패드 프로에 신형 ‘M4’ 칩이 탑재되며 두께는 애플의 역대 제품 중 가장 얇다는 설명도 덧붙였다. 광고는 공개 직후 거센 비판에 직면했다. 창작자를 상징하는 물건이 짓눌려지는 과정을 지나치게 적나라하게 묘사한 점이 문제가 됐다. 기술이 인간 창작자를 짓밟는 모습을 묘사한 것으로 해석될 여지가 있다는 문제의식이다. 인공지능(AI)으로 인해 창작자가 설 자리가 줄어드는 상황을 연상시킨다는 목소리도 나왔다." "InstrucTrans":"이번 논란은 애플이 지난 7일 유튜브에 공개한 최신 아이패드 프로 광고를 중심으로 불거졌다. 이 광고는 악기, 조각상, 카메라, 물감 등을 누르기 시작하는 장면과 함께 그 자리에 아이패드 프로가 등장하는 장면을 보여준다. 이는 새로운 아이패드 프로의 인공지능 기능, 고급 디스플레이, 성능, 두께를 강조하는 것으로 보인다. 애플은 이번에 공개한 아이패드 프로에 최신 'M4' 칩이 탑재됐으며, 애플 역사상 가장 얇은 기기라고 언급했다. 이 광고는 출시하자마자 크리에이터를 상징하는 물건이 파쇄되는 장면이 그대로 그려져 논란이 되고 있다. 비평가들은 이 이미지가 기술이 인간 크리에이터를 짓밟는다는 의미로 해석될 수 있다고 주장한다. 또한 AI로 인해 크리에이터들이 밀리고 있다는 상황을 연상시킨다는 우려의 목소리도 나온다." "KULLM3":"이 논란은 애플이 유튜브에 7일에 발표한 최신 iPad Pro 광고 주위에서 발생했습니다. 광고에서는 악기, 조각상, 카메라, 그리고 물감이 압축기에서 파괴되는 모습이 보여지고, 그 자리에 iPad Pro가 나타납니다. 이는 새로운 iPad Pro의 인공지능 기능, 고급 디스플레이, 성능, 그리고 얇은 디자인을 강조하는 것으로 보입니다. 애플은 최신 'M4' 칩을 탑재한 새로 공개된 iPad Pro가 자사 역사상 가장 얇은 기기라고 언급했습니다. 하지만 광고는 출시 직후 즉각적인 반발을 받았습니다. 광고에서는 창작자를 상징하는 물건들이 파괴되는 모습이 그래픽하게 보여지기 때문입니다. 비판자들은 이 이미지가 기술이 인간 창작자를 압도하는 것으로 해석될 수 있다고 주장하며, 일부는 이가 창작자들이 AI 때문에 지위를 잃는 상황을 연상시킨다고 우려하고 있습니다." "EEVE-10.8b-it":해당 논란은 애플이 7일에 유튜브에 공개한 최신 아이패드 프로 광고와 관련하여 발생했습니다. 해당 광고에서는 악기, 조각상, 카메라, 그리고 붓이 눌러져 부서지는 모습과 함께 그 자리에 새로운 아이패드 프로가 등장하는 장면을 생생하게 보여주고 있습니다. 이는 새로운 아이패드 프로의 인공지능 기능, 진보된 디스플레이, 성능, 그리고 두께를 부각시키고자 하는 것으로 보입니다. 애플은 갓 발표된 아이패드 프로가 최신 'M4' 칩을 탑재하고 있으며, 애플 제품 중 가장 얇은 장치라고 언급했습니다. 광고가 출시되자마자 바로 뭇매를 맞았는데, 이는 창작자들을 상징하는 물건들이 눌려 부서지는 잔인한 장면을 담고 있기 때문입니다. 비판자들은 이러한 이미지가 기술이 인간 창작자들을 짓밟은 것으로 해석될 수 있다고 주장하고 있습니다. 일부 사람들은 또한 AI로 인해 창작자들이 도태되고 있는 상황을 암시하는 것 같아 우려를 표하고 있습니다." "Seagull-13B":"이 논란이 발생한 것은 7일에 Apple이 YouTube에 공개한 최신 iPad Pro의 새로운 광고와 관련이 있습니다. 이 광고는 악기, 동상, 카메라, 물감을 프레스에 누르는 장면을 보여준 다음 그 자리에 iPad Pro가 나타납니다. 새로운 iPad Pro의 인공지능 기능, 고급 디스플레이, 성능 및 두께를 강조하는 것으로 보입니다. Apple은 새로 공개 된 iPad Pro에 최신 'M4' 칩이 장착되어 있으며 Apple 역사상 가장 얇은 장치라고 언급했습니다. 이 광고는 크리에이터를 상징하는 물체를 그래픽으로 표현하여 공개 직후 반발을 불러일으켰습니다. 비평가들은 이 이미지가 딥러닝이 인간 창작자를 짓밟는 기술로 해석될 수 있다고 지적합니다. 일부는 AI로 인해 크리에이터가 토대를 잃는 상황을 연상시킨다는 우려의 목소리도 제기했습니다.\n" "Synatra-7B":"이 논란은 7일 Apple이 YouTube에 올린 최신 iPad Pro의 신규 광고를 중심으로 벌어졌습니다. 이 광고에는 목관악기, 조각상, 카메라, 물감이 압력을 가한 후 그 자리에 iPad Pro가 나타나는 장면이 표시되는 무단장식 광고입니다. 그 광고는 새 iPad Pro의 인공지능 기능, 고급 디스플레이, 성능 및 두께를 강조하는 것으로 보입니다. Apple은 새롭게 발표된 iPad Pro에는 최신 'M4' 칩이 탑재되어 있으며 역사상 가장 얇은 기기라고 언급했습니다. 이 광고는 크리에이터를 상징하는 물체가 짓기에 맞서 있다는 모습을 그래픽으로 표현한 후 즉시 반발을 불러 일으켰습니다. 비평가들은 이 이미지가 기술이 인간 크리에이터를 협박하는 것으로 해석될 수 있다고 주장합니다. 일부는 또한 AI로 인해 크리에이터가 지위를 잃는 상황을 불러일으킬 수 있다고 우려하는 목소리도 있습니다." "nhndq-nllb":"이 논란은 애플이 7일 유튜브에 공개한 최신 아이패드 프로의 새 광고를 둘러싸고 불거졌다. 광고는 악기, 조각상, 카메라, 페인트 등이 프레스에서 으깨지고 그 자리에 아이패드 프로가 등장하는 모습을 보여준다. 이는 새로운 아이패드 프로의 인공지능 기능과 고급 디스플레이, 성능, 두께 등을 강조하는 것으로 보인다. 애플은 새로 공개된 아이패드 프로가 최신 'M4' 칩을 장착하고 있으며 애플 역사상 가장 얇은 장치라고 언급했다. AI로 인해 즉각" "our-tech":"이번 논란은 애플이 지난 7일 유튜브에 공개한 최신 아이패드 프로 광고를 둘러싸고 불거졌다. 광고는 악기, 조각상, 카메라, 물감 등을 압착기에 넣어 부숴버리다가 그 자리에 아이패드 프로가 등장하는 것으로, 새로 공개된 아이패드 프로가 최신 'M4'칩을 탑재하고 애플 사상 가장 얇은 기기라는 점을 강조한 것으로 보인다. 광고는 출시 즉시 창작자를 상징하는 물건들이 압착기에 갈겨버리는 장면을 그래픽으로 보여줘, 기술이 인간 창작자를 짓밟는 것으로 해석될 수 있다는 지적과 함께, AI로 인해 창작자들이 지위를 잃어가는 상황을 연상시킨다는 비판이 제기됐다." "our-general":이번 논란은 애플이 지난 7일 유튜브에 공개한 최신 아이패드 프로 광고를 중심으로 불거졌다. 광고는 악기, 조각상, 카메라, 물감 등을 누르기에 충분한 힘을 가진 프레스에 집어넣고 으깨는 모습을 보여준다. 이어 그 자리에 아이패드 프로가 등장하는 것으로, 새로 공개된 아이패드 프로가 최신 'M4' 칩을 탑재하고 애플 역사상 가장 얇은 기기라는 점을 강조한 것으로 보인다. 이 광고는 공개 직후부터 논란이 일었는데, 창작자를 상징하는 물건들이 으깨지는 장면이 그대로 담겨있어 기술이 창작자를 짓밟는다는 해석이 나올 수 있다는 지적이 나왔다. 또 AI에 밀려 창작자들이 힘을 잃는 상황을 연상시킨다는 우려도 제기됐다." "our-sharegpt":"7일, Apple이 YouTube에 공개한 최신 iPad Pro의 새로운 광고와 관련하여 논란이 일어났습니다. 이 광고는 악기, 조각상, 카메라, 물감이 프레스에서 부서지는 장면을 보여준 후 그 자리에 iPad Pro가 등장합니다. 새로운 iPad Pro의 인공 지능 기능, 고급 디스플레이, 성능 및 두께를 강조하는 것으로 보입니다. Apple은 새로 공개된 iPad Pro가 최신 'M4' 칩이 탑재되어 있으며 Apple 역사상 가장 얇은 기기라고 언급했습니다. 이 광고는 크리에이터를 상징하는 물체가 부서지는 것을 그래픽으로 묘사하고 있어 출시와 동시에 반발을 불러일으켰습니다. 비평가들은 이 이미지가 기술이 인간 크리에이터를 짓밟는 것으로 해석될 수 있다고 주장합니다. 또한 일부에서는 크리에이터가 인공지능으로 인해 주눅 들고 있는 상황을 연상시킨다고 우려하는 목소리도 있습니다." ``` <br><br> # Evalution Result 영어->한국어 번역 성능을 평가하기위한 데이터셋을 선정하여 평가를 진행하였습니다. ### 평가 데이터셋 출처 - Aihub/FLoRes: [traintogpb/aihub-flores-koen-integrated-sparta-30k](https://huggingface.co/datasets/traintogpb/aihub-flores-koen-integrated-sparta-30k) \| (test set 1k) - iwslt-2023 : [shreevigneshs/iwslt-2023-en-ko-train-val-split-0.1](https://huggingface.co/datasets/shreevigneshs/iwslt-2023-en-ko-train-val-split-0.1) \| (f_test 597, if_test 597) - ko_news_2024: [nayohan/ko_news_eval40](https://huggingface.co/datasets/nayohan/ko_news_eval40) \| (40) ### 모델 평가방법 - 각 모델은 허깅페이스에 ReadMe에 적혀있는 추론코드를 기반으로 각각 추론하였습니다. (공통: max_new_tokens=512) - EEVE는 명령어("당신은 번역기 입니다. 영어를 한국어로 번역하세요.")를 시스템프롬프트에 추가하였고, KULLM3는 기존 시스템프롬프트를 유지하고, 유저의 입력 맨 앞에 추가하였습니다. <br> ## Aihub 영-한 번역데이터셋 평가 * [Aihub 평가 데이터셋](https://huggingface.co/datasets/traintogpb/aihub-flores-koen-integrated-sparta-30k)은 모델들이 학습데이터셋에 포함되었을 수 있습니다. 카테고리별 성능을 확인하는 용도로만 참고해주세요. [[카테고리 설명 링크]](https://huggingface.co/datasets/traintogpb/aihub-koen-translation-integrated-tiny-100k) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6152b4b9ecf3ca6ab820e325/TMo05LOUhPGYNbT2ADOgi.png) \| model \| aihub-111 \| aihub-124 \| aihub-125 \| aihub-126 \| aihub-563 \| aihub-71265 \| aihub-71266 \| aihub-71382 \| average \| \|:-----------------\|------------:\|------------:\|------------:\|------------:\|------------:\|--------------:\|--------------:\|--------------:\|----------:\| \| [EEVE-10.8b-it](https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0) \| 6.15 \| 11.81 \| 5.78 \| 4.99 \| 6.31 \| 10.99 \| 9.41 \| 6.44 \| 7.73 \| \| [KULLM3](https://huggingface.co/nlpai-lab/KULLM3) \| 9.00 \| 13.49 \| 10.43 \| 5.90 \| 1.92 \| 16.37 \| 10.02 \| 8.39 \| 9.44 \| \| [Seagull-13B](https://huggingface.co/kuotient/Seagull-13b-translation) \| 9.8 \| 18.38 \| 8.51 \| 5.53 \| 8.74 \| 17.44 \| 10.11 \| 11.21 \| 11.21 \| \| [Synatra-7B](https://huggingface.co/maywell/Synatra-7B-v0.3-Translation) \| 6.99 \| 25.14 \| 7.79 \| 5.31 \| 9.95 \| 19.27 \| 13.20 \| 8.93 \| 12.07 \| \| [nhndq-nllb](https://huggingface.co/NHNDQ/nllb-finetuned-en2ko) \| 24.09 \| 48.71 \| 22.89 \| 13.98 \| 18.71 \| 30.18 \| 32.49 \| 18.62 \| 26.20 \| \| [our-tech](nayohan/llama3-8b-it-translation-tech-en-ko-1sent) \| 20.19 \| 37.48 \| 18.50 \| 12.45 \| 16.96 \| 13.92 \| 43.54 \| 9.62 \| 21.58 \| \| [our-general](https://huggingface.co/nayohan/llama3-8b-it-translation-general-en-ko-1sent) \| 24.72 \| 45.22 \| 21.61 \| 18.97 \| 17.23 \| 30.00 \| 32.08 \| 13.55 \| 25.42 \| \| [our-sharegpt](https://huggingface.co/nayohan/llama3-8b-it-translation-sharegpt-en-ko) \| 12.42 \| 19.23 \| 10.91 \| 9.18 \| 14.30 \| 26.43 \| 12.62 \| 15.57 \| 15.08 \| \| our-instrucTrans \| 24.89 \| 47.00 \| 22.78 \| 21.78 \| 24.27 \| 27.98 \| 31.31 \| 15.42 \|26.92 \| ## FLoRes 영-한 번역데이터셋 평가 [FloRes](https://huggingface.co/datasets/facebook/flores)는 페이스북에서 공개한 영어와 적은 리소스의 언어 200개에 대해서 병렬로 구성한 번역 벤치마크 데이터셋입니다. [traintogpb/aihub-flores-koen-integrated-sparta-30k](https://huggingface.co/datasets/traintogpb/aihub-flores-koen-integrated-sparta-30k)를 활용하여 평가를 진행하였습니다. (한문장 구성) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6152b4b9ecf3ca6ab820e325/ZDeA-7e-0xfXaGOmyS9zs.png) \| model \| flores-dev \| flores-devtest \| average \| \|:-----------------\|-------------:\|-----------------:\|----------:\| \| EEVE-10.8b-it \| 10.99 \| 11.71 \| 11.35 \| \| KULLM3 \| 12.83 \| 13.23 \| 13.03 \| \| Seagull-13B \| 11.48 \| 11.99 \| 11.73 \| \| Synatra-7B \| 10.98 \| 10.81 \| 10.89 \| \| nhndq-nllb \| 12.79 \| 15.15 \| 13.97 \| \| our-tech \| 12.14 \| 12.04 \| 12.09 \| \| our-general \| 14.93 \| 14.58 \| 14.75 \| \| our-sharegpt \| 14.71 \| 16.69 \| 15.70 \| \| our-instrucTrans \| 14.49 \| 17.69 \| 16.09 \| ## iwslt-2023 [iwslt-2023 데이터셋](https://huggingface.co/datasets/shreevigneshs/iwslt-2023-en-ko-train-val-split-0.1)은 동일한 영어문장을 각각 반말, 존댓말의 한국어로 평가데이터셋이 구성되어 있습니다. 모델의 존대/반말 경향을 상대적으로 확인할 수 있습니다. (한문장 구성) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6152b4b9ecf3ca6ab820e325/UJvuCnbjWokBWQNhD4L63.png) \| model \| iwslt_zondae \| iwslt_banmal \| average \| \|:-----------------\|---------------------:\|------------------:\|----------:\| \| EEVE-10.8b-it \| 4.62 \| 3.79 \| 4.20 \| \| KULLM3 \| 5.94 \| 5.24 \| 5.59 \| \| Seagull-13B \| 6.14 \| 4.54 \| 5.34 \| \| Synatra-7B \| 5.43 \| 4.73 \| 5.08 \| \| nhndq-nllb \| 8.36 \| 7.44 \| 7.90 \| \| our-tech \| 3.99 \| 3.95 \| 3.97 \| \| our-general \| 7.33 \| 6.18 \| 6.75 \| \| our-sharegpt \| 7.83 \| 6.35 \| 7.09 \| \| our-instrucTrans \| 8.63 \| 6.97 \| 7.80 \| ## ko_news_eval40 [ko_news_eval40 데이터셋](https://huggingface.co/datasets/nayohan/ko_news_eval40)은 학습되지 않았을 새로운 데이터셋에 평가하고자 24년5월 뉴스를 각 카테고리(4) 별 10개씩 기사 내 문단 일부를 수집하고, GPT4로 번역하여 구성하였습니다. 영어를 일상뉴스에 사용되는 한국어로 잘 번역하는지를 평가합니다. (문단 구성) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6152b4b9ecf3ca6ab820e325/OaE5z_yQT9sIIz0zsn644.png) \| model \| IT/과학 \| 경제 \| 사회 \| 오피니언 \| average \| \|:-----------------\|----------:\|-------:\|-------:\|------------:\|----------:\| \| EEVE-10.8b-it \| 9.03 \| 6.42 \| 5.56 \| 5.10 \| 6.52 \| \| KULLM3 \| 9.82 \| 5.26 \| 3.48 \| 7.48 \| 6.51 \| \| Seagull-13B \| 7.41 \| 6.78 \| 4.76 \| 4.85 \| 5.95 \| \| Synatra-7B \| 11.44 \| 5.59 \| 4.57 \| 6.31 \| 6.97 \| \| nhndq-nllb \| 11.97 \| 11.12 \| 6.14 \| 5.28 \| 8.62 \| \| our-tech \| 10.45 \| 9.98 \| 5.13 \| 10.15 \| 8.92 \| \| our-general \| 16.22 \| 10.61 \| 8.51 \| 7.33 \| 10.66 \| \| our-sharegpt \| 12.71 \| 8.06 \| 7.70 \| 6.43 \| 8.72 \| \| our-instrucTrans \| 20.42 \| 12.77 \| 11.40 \| 10.31 \|13.72 \| ## Average ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6152b4b9ecf3ca6ab820e325/bf2qjeg-03WRVTIbqvG7C.png) \| model \| aihub \| flores \| iwslt \| news \| average \| \|:-----------------\|--------:\|---------:\|--------:\|--------:\|----------:\| \| [EEVE-10.8b-it](https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0) \| 7.73 \| 11.35 \| 4.20 \| 6.52 \| 7.45 \| \| [KULLM3](https://huggingface.co/nlpai-lab/KULLM3) \| 9.44 \| 13.03 \| 5.59 \| 6.51 \| 8.64 \| \| [Seagull-13B](https://huggingface.co/kuotient/Seagull-13b-translation) \| 11.21 \| 11.73 \| 5.34 \| 5.95 \| 8.56 \| \| [Synatra-7B](https://huggingface.co/maywell/Synatra-7B-v0.3-Translation) \| 12.07 \| 10.89 \| 5.08 \| 6.97 \| 8.75 \| \| [nhndq-nllb](https://huggingface.co/NHNDQ/nllb-finetuned-en2ko) \| 26.20 \| 13.97 \|7.90 \| 8.62 \| 14.17 \| \| [our-tech](nayohan/llama3-8b-it-translation-tech-en-ko-1sent) \| 21.58 \| 12.09 \| 3.97 \| 8.92 \| 11.64 \| \| [our-general](https://huggingface.co/nayohan/llama3-8b-it-translation-general-en-ko-1sent) \| 25.42 \| 14.75 \| 6.75 \| 10.66 \| 14.40 \| \| [our-sharegpt](https://huggingface.co/nayohan/llama3-8b-it-translation-sharegpt-en-ko) \| 15.08 \| 15.70 \| 7.09 \| 8.72 \| 11.64 \| \| our-instrucTrans \|26.92\| 16.09\| 7.80 \|13.72\| 16.13 \| ### Citation ```bibtex @article{InstrcTrans8b, title={llama3-instrucTrans-enko-8b}, author={Na, Yohan}, year={2024}, url={https://huggingface.co/nayohan/llama3-instrucTrans-enko-8b} } ``` ```bibtex @article{llama3modelcard, title={Llama 3 Model Card}, author={AI@Meta}, year={2024}, url={https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md} } ```
Litzy619/G0513HMA19H	Litzy619	2024-05-14T10:21:21Z	0	0	null	[ "safetensors", "generated_from_trainer", "base_model:google/gemma-2b", "base_model:finetune:google/gemma-2b", "license:gemma", "region:us" ]	null	2024-05-14T09:06:59Z	--- license: gemma base_model: google/gemma-2b tags: - generated_from_trainer model-index: - name: G0513HMA19H 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. --> # G0513HMA19H This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1260 ## 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: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 60 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 3.1408 \| 0.09 \| 10 \| 2.7234 \| \| 2.2777 \| 0.18 \| 20 \| 1.6102 \| \| 1.1251 \| 0.27 \| 30 \| 0.5583 \| \| 0.3105 \| 0.36 \| 40 \| 0.1700 \| \| 0.1607 \| 0.45 \| 50 \| 0.1518 \| \| 0.1511 \| 0.54 \| 60 \| 0.1510 \| \| 0.1503 \| 0.63 \| 70 \| 0.1517 \| \| 0.1515 \| 0.73 \| 80 \| 0.1494 \| \| 0.1429 \| 0.82 \| 90 \| 0.1487 \| \| 0.1455 \| 0.91 \| 100 \| 0.1479 \| \| 0.149 \| 1.0 \| 110 \| 0.1491 \| \| 0.1437 \| 1.09 \| 120 \| 0.1489 \| \| 0.1447 \| 1.18 \| 130 \| 0.1486 \| \| 0.1445 \| 1.27 \| 140 \| 0.1475 \| \| 0.1484 \| 1.36 \| 150 \| 0.1462 \| \| 0.1417 \| 1.45 \| 160 \| 0.1461 \| \| 0.1436 \| 1.54 \| 170 \| 0.1454 \| \| 0.1444 \| 1.63 \| 180 \| 0.1448 \| \| 0.1456 \| 1.72 \| 190 \| 0.1476 \| \| 0.1439 \| 1.81 \| 200 \| 0.1442 \| \| 0.1421 \| 1.9 \| 210 \| 0.1423 \| \| 0.1406 \| 1.99 \| 220 \| 0.1393 \| \| 0.135 \| 2.08 \| 230 \| 0.1362 \| \| 0.131 \| 2.18 \| 240 \| 0.1343 \| \| 0.128 \| 2.27 \| 250 \| 0.1325 \| \| 0.1349 \| 2.36 \| 260 \| 0.1333 \| \| 0.1302 \| 2.45 \| 270 \| 0.1316 \| \| 0.1237 \| 2.54 \| 280 \| 0.1280 \| \| 0.12 \| 2.63 \| 290 \| 0.1267 \| \| 0.1219 \| 2.72 \| 300 \| 0.1260 \| \| 0.1235 \| 2.81 \| 310 \| 0.1259 \| \| 0.1244 \| 2.9 \| 320 \| 0.1260 \| \| 0.1228 \| 2.99 \| 330 \| 0.1260 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.0
johannhartmann/occi5_breadcrumbs_ties	johannhartmann	2024-05-14T10:20:34Z	4	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "conversational", "base_model:occiglot/occiglot-7b-de-en-instruct", "base_model:merge:occiglot/occiglot-7b-de-en-instruct", "base_model:occiglot/occiglot-7b-es-en-instruct", "base_model:merge:occiglot/occiglot-7b-es-en-instruct", "base_model:occiglot/occiglot-7b-eu5-instruct", "base_model:merge:occiglot/occiglot-7b-eu5-instruct", "base_model:occiglot/occiglot-7b-fr-en-instruct", "base_model:merge:occiglot/occiglot-7b-fr-en-instruct", "base_model:occiglot/occiglot-7b-it-en-instruct", "base_model:merge:occiglot/occiglot-7b-it-en-instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-05-14T10:16:59Z	--- base_model: - occiglot/occiglot-7b-es-en-instruct - occiglot/occiglot-7b-de-en-instruct - occiglot/occiglot-7b-eu5-instruct - occiglot/occiglot-7b-fr-en-instruct - occiglot/occiglot-7b-it-en-instruct library_name: transformers tags: - mergekit - merge --- # occi5_breadcrumbs_ties This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the breadcrumbs_ties merge method using [occiglot/occiglot-7b-eu5-instruct](https://huggingface.co/occiglot/occiglot-7b-eu5-instruct) as a base. ### Models Merged The following models were included in the merge: * [occiglot/occiglot-7b-es-en-instruct](https://huggingface.co/occiglot/occiglot-7b-es-en-instruct) * [occiglot/occiglot-7b-de-en-instruct](https://huggingface.co/occiglot/occiglot-7b-de-en-instruct) * [occiglot/occiglot-7b-fr-en-instruct](https://huggingface.co/occiglot/occiglot-7b-fr-en-instruct) * [occiglot/occiglot-7b-it-en-instruct](https://huggingface.co/occiglot/occiglot-7b-it-en-instruct) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: occiglot/occiglot-7b-eu5-instruct # no parameters necessary for base model - model: occiglot/occiglot-7b-de-en-instruct parameters: density: 0.6 weight: 0.25 - model: occiglot/occiglot-7b-it-en-instruct parameters: density: 0.6 weight: 0.25 - model: occiglot/occiglot-7b-fr-en-instruct parameters: density: 0.6 weight: 0.25 - model: occiglot/occiglot-7b-es-en-instruct parameters: density: 0.6 weight: 0.25 merge_method: breadcrumbs_ties base_model: occiglot/occiglot-7b-eu5-instruct parameters: int8_mask: true dtype: bfloat16 random_seed: 0 tokenizer_source: model:occiglot/occiglot-7b-de-en-instruct ```
WasamiKirua/Samantha-v0.1-ita-mistral-7B	WasamiKirua	2024-05-14T10:19:26Z	10	1	transformers	[ "transformers", "pytorch", "safetensors", "mistral", "text-generation", "axolotl", "generated_from_trainer", "psycology", "companion", "conversational", "it", "dataset:WasamiKirua/samantha-ita", "dataset:WasamiKirua/psycology-dataset-ita", "base_model:DeepMount00/Mistral-Ita-7b", "base_model:finetune:DeepMount00/Mistral-Ita-7b", "license:mit", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2024-04-27T15:54:39Z	--- license: mit base_model: DeepMount00/Mistral-Ita-7b tags: - axolotl - generated_from_trainer - psycology - companion model-index: - name: Samantha-ita-v0.1 results: [] datasets: - WasamiKirua/samantha-ita - WasamiKirua/psycology-dataset-ita language: - it --- <!-- 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. --> [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.0` ```yaml base_model: DeepMount00/Mistral-Ita-7b model_type: MistralForCausalLM tokenizer_type: LlamaTokenizer load_in_8bit: false load_in_4bit: false strict: false datasets: - path: /workspace/datasets/samantha-ita-sharegpt.jsonl type: sharegpt field: conversations - path: /workspace/datasets/psycology-dataset-gpt-ita.jsonl type: sharegpt field: conversations chat_template: chatml hub_model_id: Samantha-ita-v0.1 dataset_prepared_path: val_set_size: 0.05 output_dir: ./out sequence_len: 8192 sample_packing: true pad_to_sequence_len: true eval_sample_packing: false wandb_project: samantha-mistral7b wandb_entity: wandb_watch: wandb_name: Samantha-ita-v0.1 wandb_log_model: gradient_accumulation_steps: 4 micro_batch_size: 2 num_epochs: 2 optimizer: adamw_bnb_8bit lr_scheduler: cosine learning_rate: 0.000006 # 0.000006 OK better curve # 0.0005 OK train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 10 evals_per_epoch: 4 eval_table_size: eval_max_new_tokens: 128 saves_per_epoch: 1 debug: deepspeed: weight_decay: 0.0 fsdp: fsdp_config: special_tokens: bos_token: "<s>" eos_token: "<\|im_end\|>" unk_token: "<unk>" tokens: - "<\|im_start\|>" - "<\|im_end\|>" ``` </details><br> # Samantha-ita-v0.1 <img src="https://i.postimg.cc/YC6Tf65H/00005-2244133494.png" alt="cover" border="0" width="1024px"> This model is a fine-tuned version of [DeepMount00/Mistral-Ita-7b](https://huggingface.co/DeepMount00/Mistral-Ita-7b) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.7069 ## Model description Samantha is a fine-tuned Italian version based on Eric Hartford's Samantha. For this, I utilized the pre-trained Mistral 7B version. The model performs excellently! Please take a look at the datasets used. ## Intended uses & limitations Sure, here's the corrected and improved version: Samantha is a proficient companion who understands and speaks Italian fluently. She has undergone training on various topics. In addition to the original Samantha dataset translated with GPT-4, I have also incorporated a psychology conversations dataset to further enrich Samantha's knowledge in the field of psychology." ## Chat Template ``` <\|im_start\|>system YOUR PROMPT<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ``` ## Quantized Versions: GGUF availabile here: https://huggingface.co/WasamiKirua/Samantha-ita-mistral-v0.1-GGUF ## DPO Version DPO trained version available here: https://huggingface.co/WasamiKirua/Samantha-ita-mistral-v0.1-DPO ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 6e-06 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.9261 \| 0.01 \| 1 \| 1.8998 \| \| 0.8902 \| 0.25 \| 28 \| 0.8267 \| \| 0.8422 \| 0.5 \| 56 \| 0.7604 \| \| 0.8338 \| 0.75 \| 84 \| 0.7299 \| \| 0.8397 \| 1.0 \| 112 \| 0.7136 \| \| 0.6859 \| 1.22 \| 140 \| 0.7131 \| \| 0.6707 \| 1.47 \| 168 \| 0.7082 \| \| 0.7041 \| 1.72 \| 196 \| 0.7069 \| \| 0.6936 \| 1.97 \| 224 \| 0.7069 \| ### Framework versions - Transformers 4.40.0.dev0 - Pytorch 2.2.0 - Datasets 2.15.0 - Tokenizers 0.15.0
mohamed1ai/llama3-alpaca	mohamed1ai	2024-05-14T10:18:48Z	0	0	null	[ "safetensors", "region:us" ]	null	2024-05-14T09:49:58Z	## llama3-alpaca Model ### Description The llama3-alpaca model is a language model trained on vast amounts of text data. It can be used for various natural language processing tasks, including text generation, completion, and more. ### Inference Code (Using unsloth) ```python from unsloth import FastLanguageModel import torch FastLanguageModel.for_inference(model) # Enable native 2x faster inference # Define your prompt prompt = "Continue the Fibonacci sequence." # Provide input for the model inputs = tokenizer( [prompt], return_tensors="pt" ).to("cuda") # Generate output outputs = model.generate( **inputs, max_new_tokens=64, use_cache=True ) # Decode the generated output generated_text = tokenizer.batch_decode(outputs) print(generated_text) ``` ### Inference Code (HF model) ```python from transformers import AutoTokenizer, AutoModelForCausalLM # Load tokenizer and model tokenizer = AutoTokenizer.from_pretrained("mohamed1ai/llama3-alpaca") model = AutoModelForCausalLM.from_pretrained("mohamed1ai/llama3-alpaca") # Define your prompt prompt = "Continue the Fibonacci sequence." # Tokenize the prompt input_ids = tokenizer.encode(prompt, return_tensors="pt") # Generate output output = model.generate(input_ids, max_length=100, num_return_sequences=1) # Decode the generated output generated_text = tokenizer.decode(output[0], skip_special_tokens=True) print(generated_text) ```
Namrata798/whisper-large-v2-hindi-100steps	Namrata798	2024-05-14T10:14:17Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-14T10:14:12Z	--- 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]
Litzy619/G0513HMAB3	Litzy619	2024-05-14T10:12:37Z	0	0	null	[ "safetensors", "generated_from_trainer", "base_model:google/gemma-2b", "base_model:finetune:google/gemma-2b", "license:gemma", "region:us" ]	null	2024-05-14T08:58:43Z	--- license: gemma base_model: google/gemma-2b tags: - generated_from_trainer model-index: - name: G0513HMAB3 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. --> # G0513HMAB3 This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1174 ## 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: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.9144 \| 0.09 \| 10 \| 1.8171 \| \| 1.6608 \| 0.18 \| 20 \| 1.4138 \| \| 1.2059 \| 0.27 \| 30 \| 0.9062 \| \| 0.6819 \| 0.36 \| 40 \| 0.4067 \| \| 0.2762 \| 0.45 \| 50 \| 0.1792 \| \| 0.1622 \| 0.54 \| 60 \| 0.1512 \| \| 0.1503 \| 0.63 \| 70 \| 0.1473 \| \| 0.1496 \| 0.73 \| 80 \| 0.1468 \| \| 0.1422 \| 0.82 \| 90 \| 0.1453 \| \| 0.1426 \| 0.91 \| 100 \| 0.1438 \| \| 0.142 \| 1.0 \| 110 \| 0.1436 \| \| 0.1382 \| 1.09 \| 120 \| 0.1390 \| \| 0.134 \| 1.18 \| 130 \| 0.1356 \| \| 0.1342 \| 1.27 \| 140 \| 0.1369 \| \| 0.1391 \| 1.36 \| 150 \| 0.1356 \| \| 0.1326 \| 1.45 \| 160 \| 0.1313 \| \| 0.129 \| 1.54 \| 170 \| 0.1287 \| \| 0.1302 \| 1.63 \| 180 \| 0.1276 \| \| 0.1316 \| 1.72 \| 190 \| 0.1297 \| \| 0.1269 \| 1.81 \| 200 \| 0.1252 \| \| 0.1271 \| 1.9 \| 210 \| 0.1229 \| \| 0.1242 \| 1.99 \| 220 \| 0.1229 \| \| 0.1193 \| 2.08 \| 230 \| 0.1212 \| \| 0.1226 \| 2.18 \| 240 \| 0.1216 \| \| 0.1172 \| 2.27 \| 250 \| 0.1213 \| \| 0.1202 \| 2.36 \| 260 \| 0.1198 \| \| 0.1173 \| 2.45 \| 270 \| 0.1200 \| \| 0.112 \| 2.54 \| 280 \| 0.1186 \| \| 0.1126 \| 2.63 \| 290 \| 0.1182 \| \| 0.1152 \| 2.72 \| 300 \| 0.1175 \| \| 0.1133 \| 2.81 \| 310 \| 0.1174 \| \| 0.117 \| 2.9 \| 320 \| 0.1175 \| \| 0.1177 \| 2.99 \| 330 \| 0.1174 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.0
neopolita/yi-1.5-9b-gguf	neopolita	2024-05-14T10:05:29Z	8	0	null	[ "gguf", "endpoints_compatible", "region:us" ]	null	2024-05-14T09:27:30Z	--- {} --- # GGUF quants for [01-ai/Yi-1.5-9B](https://huggingface.co/01-ai/Yi-1.5-9B) using [llama.cpp](https://github.com/ggerganov/llama.cpp) Terms of Use: Please check the [original model](https://huggingface.co/01-ai/Yi-1.5-9B) <picture> <img alt="cthulhu" src="https://huggingface.co/neopolita/common/resolve/main/profile.png"> </picture> ## Quants * `q2_k`: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors. * `q3_k_s`: Uses Q3_K for all tensors * `q3_k_m`: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K * `q3_k_l`: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K * `q4_0`: Original quant method, 4-bit. * `q4_1`: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. * `q4_k_s`: Uses Q4_K for all tensors * `q4_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K * `q5_0`: Higher accuracy, higher resource usage and slower inference. * `q5_1`: Even higher accuracy, resource usage and slower inference. * `q5_k_s`: Uses Q5_K for all tensors * `q5_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K * `q6_k`: Uses Q8_K for all tensors * `q8_0`: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.
taimoor-ahmed1/climate-sentiment-model	taimoor-ahmed1	2024-05-14T10:02:30Z	120	0	transformers	[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "base_model:finetune:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-05-14T07:40:43Z	--- license: apache-2.0 base_model: distilbert-base-uncased tags: - generated_from_trainer metrics: - accuracy - f1 model-index: - name: climate-sentiment-model 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. --> # climate-sentiment-model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.4384 - Accuracy: 0.7878 - F1: 0.7840 ## 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: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 300 - num_epochs: 10 ### Training results ### Framework versions - Transformers 4.40.2 - Pytorch 2.2.1+cu121 - Datasets 2.19.1 - Tokenizers 0.19.1
ariakhosh/adapter8	ariakhosh	2024-05-14T10:02:27Z	0	0	null	[ "safetensors", "arxiv:2305.14314", "arxiv:2302.13971", "region:us" ]	null	2024-05-14T10:00:15Z	# QLoRA Instruction Tuned Models \| [Paper](https://arxiv.org/abs/2305.14314) \| [Code](https://github.com/artidoro/qlora) \| [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) \| The `QLoRA Instruction Tuned Models` are open-source models obtained through 4-bit QLoRA tuning of LLaMA base models on various instruction tuning datasets. They are available in 7B, 13B, 33B, and 65B parameter sizes. Note: The best performing chatbot models are named [Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) and finetuned on OASST1. This model card is for the other models finetuned on other instruction tuning datasets. ⚠️ These models are purely intended for research purposes and could produce problematic outputs. ## What are QLoRA Instruction Tuned Models and why use them? - Strong performance on MMLU following the QLoRA instruction tuning. - Replicable and efficient instruction tuning procedure that can be extended to new use cases. QLoRA training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora). - Rigorous comparison to 16-bit methods (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. - Lightweight checkpoints which only contain adapter weights. ## License and Intended Use QLoRA Instruction Tuned adapter weights are available under Apache 2 license. Note the use of these adapter weights, requires access to the LLaMA model weighs and therefore should be used according to the LLaMA license. ## Usage Here is an example of how you would load Flan v2 7B in 4-bits: ```python import torch from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/qlora-flan-7b' model = AutoModelForCausalLM.from_pretrained( model_name, load_in_4bit=True, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4' ), ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` Inference can then be performed as usual with HF models as follows: ```python prompt = "Introduce yourself" formatted_prompt = ( f"A chat between a curious human and an artificial intelligence assistant." f"The assistant gives helpful, detailed, and polite answers to the user's questions.\n" f"### Human: {prompt} ### Assistant:" ) inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0") outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` Expected output similar to the following: ``` A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. ### Human: Introduce yourself ### Assistant: I am an artificial intelligence assistant. I am here to help you with any questions you may have. ``` ## Current Inference Limitations Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels. Below is how you would load the model in 16 bits: ```python model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/qlora-flan-7b' model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Model Card Architecture: The models released here are LoRA adapters to be used on top of LLaMA models. They are added to all layers. For all model sizes, we use $r=64$. Base Model: These models use LLaMA as base model with sizes 7B, 13B, 33B, 65B. LLaMA is a causal language model pretrained on a large corpus of text. See [LLaMA paper](https://arxiv.org/abs/2302.13971) for more details. Note that these models can inherit biases and limitations of the base model. Finetuning Data: These models are finetuned on various instruction tuning datasets. The datasets used are: Alpaca, HH-RLHF, Unnatural Instr., Chip2, Longform, Self-Instruct, FLAN v2. Languages: The different datasets cover different languages. We direct to the various papers and resources describing the datasets for more details. Next, we describe Training and Evaluation details. ### Training QLoRA Instruction Tuned Models are the result of 4-bit QLoRA supervised finetuning on different instruction tuning datasets. All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models. For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. ### Training hyperparameters \| Parameters \| Dataset \| Batch size \| LR \| Steps \| Source Length \| Target Length \| \|------------\|----------\|------------\|------\|-------\|---------------\|---------------\| \| 7B \| All \| 16 \| 2e-4 \| 10000 \| 384 \| 128 \| \| 7B \| OASST1 \| 16 \| 2e-4 \| 1875 \| - \| 512 \| \| 7B \| HH-RLHF \| 16 \| 2e-4 \| 10000 \| - \| 768 \| \| 7B \| Longform \| 16 \| 2e-4 \| 4000 \| 512 \| 1024 \| \| 13B \| All \| 16 \| 2e-4 \| 10000 \| 384 \| 128 \| \| 13B \| OASST1 \| 16 \| 2e-4 \| 1875 \| - \| 512 \| \| 13B \| HH-RLHF \| 16 \| 2e-4 \| 10000 \| - \| 768 \| \| 13B \| Longform \| 16 \| 2e-4 \| 4000 \| 512 \| 1024 \| \| 33B \| All \| 32 \| 1e-4 \| 5000 \| 384 \| 128 \| \| 33B \| OASST1 \| 16 \| 1e-4 \| 1875 \| - \| 512 \| \| 33B \| HH-RLHF \| 32 \| 1e-4 \| 5000 \| - \| 768 \| \| 33B \| Longform \| 32 \| 1e-4 \| 2343 \| 512 \| 1024 \| \| 65B \| All \| 64 \| 1e-4 \| 2500 \| 384 \| 128 \| \| 65B \| OASST1 \| 16 \| 1e-4 \| 1875 \| - \| 512 \| \| 65B \| HH-RLHF \| 64 \| 1e-4 \| 2500 \| - \| 768 \| \| 65B \| Longform \| 32 \| 1e-4 \| 2343 \| 512 \| 1024 \| ### Evaluation We use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy. Dataset \| 7B \| 13B \| 33B \| 65B ---\|---\|---\|---\|--- LLaMA no tuning \| 35.1 \| 46.9 \| 57.8 \| 63.4 Self-Instruct \| 36.4 \| 33.3 \| 53.0 \| 56.7 Longform \| 32.1 \| 43.2 \| 56.6 \| 59.7 Chip2 \| 34.5 \| 41.6 \| 53.6 \| 59.8 HH-RLHF \| 34.9 \| 44.6 \| 55.8 \| 60.1 Unnatural Instruct \| 41.9 \| 48.1 \| 57.3 \| 61.3 OASST1 (Guanaco) \| 36.6 \| 46.4 \| 57.0 \| 62.2 Alpaca \| 38.8 \| 47.8 \| 57.3 \| 62.5 FLAN v2 \| 44.5 \| 51.4 \| 59.2 \| 63.9 We evaluate the generative language capabilities through automated evaluations on the Vicuna benchmark. We report the score of the QLoRA Instruction Finetuned Models relative to the score obtained by ChatGPT. The rater in this case is GPT-4 which is tasked to assign a score out of 10 to both ChatGPT and the model outputs for each prompt. We report scores for models ranging 7B to 65B and compare them to both academic and commercial baselilnes. \| Model / Dataset \| Params \| Model bits \| Memory \| ChatGPT vs Sys \| Sys vs ChatGPT \| Mean \| 95\% CI \| \|------------------\|--------\|------------\|--------\|----------------\|----------------\|------------------\|---------\| \| GPT-4 \| - \| - \| - \| 119.4\% \| 110.1\% \| 114.5\% \| 2.6\% \| \| Bard \| - \| - \| - \| 93.2\% \| 96.4\% \| 94.8\% \| 4.1\% \| \| Guanaco \| 65B \| 4-bit \| 41 GB \| 96.7\% \| 101.9\% \| 99.3\% \| 4.4\% \| \| Alpaca \| 65B \| 4-bit \| 41 GB \| 63.0\% \| 77.9\% \| 70.7\% \| 4.3\% \| \| FLAN v2 \| 65B \| 4-bit \| 41 GB \| 37.0\% \| 59.6\% \| 48.4\% \| 4.6\% \| \| Guanaco \| 33B \| 4-bit \| 21 GB \| 96.5\% \| 99.2\% \| 97.8\% \| 4.4\% \| \| Open Assistant \| 33B \| 16-bit \| 66 GB \| 73.4\% \| 85.7\% \| 78.1\% \| 5.3\% \| \| Alpaca \| 33B \| 4-bit \| 21 GB \| 67.2\% \| 79.7\% \| 73.6\% \| 4.2\% \| \| FLAN v2 \| 33B \| 4-bit \| 21 GB \| 26.3\% \| 49.7\% \| 38.0\% \| 3.9\% \| \| Vicuna \| 13B \| 16-bit \| 26 GB \| 91.2\% \| 98.7\% \| 94.9\% \| 4.5\% \| \| Guanaco \| 13B \| 4-bit \| 10 GB \| 87.3\% \| 93.4\% \| 90.4\% \| 5.2\% \| \| Alpaca \| 13B \| 4-bit \| 10 GB \| 63.8\% \| 76.7\% \| 69.4\% \| 4.2\% \| \| HH-RLHF \| 13B \| 4-bit \| 10 GB \| 55.5\% \| 69.1\% \| 62.5\% \| 4.7\% \| \| Unnatural Instr. \| 13B \| 4-bit \| 10 GB \| 50.6\% \| 69.8\% \| 60.5\% \| 4.2\% \| \| Chip2 \| 13B \| 4-bit \| 10 GB \| 49.2\% \| 69.3\% \| 59.5\% \| 4.7\% \| \| Longform \| 13B \| 4-bit \| 10 GB \| 44.9\% \| 62.0\% \| 53.6\% \| 5.2\% \| \| Self-Instruct \| 13B \| 4-bit \| 10 GB \| 38.0\% \| 60.5\% \| 49.1\% \| 4.6\% \| \| FLAN v2 \| 13B \| 4-bit \| 10 GB \| 32.4\% \| 61.2\% \| 47.0\% \| 3.6\% \| \| Guanaco \| 7B \| 4-bit \| 5 GB \| 84.1\% \| 89.8\% \| 87.0\% \| 5.4\% \| \| Alpaca \| 7B \| 4-bit \| 5 GB \| 57.3\% \| 71.2\% \| 64.4\% \| 5.0\% \| \| FLAN v2 \| 7B \| 4-bit \| 5 GB \| 33.3\% \| 56.1\% \| 44.8\% \| 4.0\% \| ## Citation ```bibtex @article{dettmers2023qlora, title={QLoRA: Efficient Finetuning of Quantized LLMs}, author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke}, journal={arXiv preprint arXiv:2305.14314}, year={2023} } ```
Danieljacobsen/Helsinki-DA-SV-v5	Danieljacobsen	2024-05-14T10:00:44Z	106	0	transformers	[ "transformers", "safetensors", "marian", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2024-05-14T08:30:21Z	--- 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]
ariakhosh/adapter7	ariakhosh	2024-05-14T09:59:50Z	0	0	null	[ "safetensors", "arxiv:2305.14314", "arxiv:2302.13971", "region:us" ]	null	2024-05-14T09:58:34Z	# QLoRA Instruction Tuned Models \| [Paper](https://arxiv.org/abs/2305.14314) \| [Code](https://github.com/artidoro/qlora) \| [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) \| The `QLoRA Instruction Tuned Models` are open-source models obtained through 4-bit QLoRA tuning of LLaMA base models on various instruction tuning datasets. They are available in 7B, 13B, 33B, and 65B parameter sizes. Note: The best performing chatbot models are named [Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) and finetuned on OASST1. This model card is for the other models finetuned on other instruction tuning datasets. ⚠️ These models are purely intended for research purposes and could produce problematic outputs. ## What are QLoRA Instruction Tuned Models and why use them? - Strong performance on MMLU following the QLoRA instruction tuning. - Replicable and efficient instruction tuning procedure that can be extended to new use cases. QLoRA training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora). - Rigorous comparison to 16-bit methods (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. - Lightweight checkpoints which only contain adapter weights. ## License and Intended Use QLoRA Instruction Tuned adapter weights are available under Apache 2 license. Note the use of these adapter weights, requires access to the LLaMA model weighs and therefore should be used according to the LLaMA license. ## Usage Here is an example of how you would load Flan v2 7B in 4-bits: ```python import torch from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/qlora-flan-7b' model = AutoModelForCausalLM.from_pretrained( model_name, load_in_4bit=True, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4' ), ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` Inference can then be performed as usual with HF models as follows: ```python prompt = "Introduce yourself" formatted_prompt = ( f"A chat between a curious human and an artificial intelligence assistant." f"The assistant gives helpful, detailed, and polite answers to the user's questions.\n" f"### Human: {prompt} ### Assistant:" ) inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0") outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` Expected output similar to the following: ``` A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. ### Human: Introduce yourself ### Assistant: I am an artificial intelligence assistant. I am here to help you with any questions you may have. ``` ## Current Inference Limitations Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels. Below is how you would load the model in 16 bits: ```python model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/qlora-flan-7b' model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Model Card Architecture: The models released here are LoRA adapters to be used on top of LLaMA models. They are added to all layers. For all model sizes, we use $r=64$. Base Model: These models use LLaMA as base model with sizes 7B, 13B, 33B, 65B. LLaMA is a causal language model pretrained on a large corpus of text. See [LLaMA paper](https://arxiv.org/abs/2302.13971) for more details. Note that these models can inherit biases and limitations of the base model. Finetuning Data: These models are finetuned on various instruction tuning datasets. The datasets used are: Alpaca, HH-RLHF, Unnatural Instr., Chip2, Longform, Self-Instruct, FLAN v2. Languages: The different datasets cover different languages. We direct to the various papers and resources describing the datasets for more details. Next, we describe Training and Evaluation details. ### Training QLoRA Instruction Tuned Models are the result of 4-bit QLoRA supervised finetuning on different instruction tuning datasets. All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models. For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. ### Training hyperparameters \| Parameters \| Dataset \| Batch size \| LR \| Steps \| Source Length \| Target Length \| \|------------\|----------\|------------\|------\|-------\|---------------\|---------------\| \| 7B \| All \| 16 \| 2e-4 \| 10000 \| 384 \| 128 \| \| 7B \| OASST1 \| 16 \| 2e-4 \| 1875 \| - \| 512 \| \| 7B \| HH-RLHF \| 16 \| 2e-4 \| 10000 \| - \| 768 \| \| 7B \| Longform \| 16 \| 2e-4 \| 4000 \| 512 \| 1024 \| \| 13B \| All \| 16 \| 2e-4 \| 10000 \| 384 \| 128 \| \| 13B \| OASST1 \| 16 \| 2e-4 \| 1875 \| - \| 512 \| \| 13B \| HH-RLHF \| 16 \| 2e-4 \| 10000 \| - \| 768 \| \| 13B \| Longform \| 16 \| 2e-4 \| 4000 \| 512 \| 1024 \| \| 33B \| All \| 32 \| 1e-4 \| 5000 \| 384 \| 128 \| \| 33B \| OASST1 \| 16 \| 1e-4 \| 1875 \| - \| 512 \| \| 33B \| HH-RLHF \| 32 \| 1e-4 \| 5000 \| - \| 768 \| \| 33B \| Longform \| 32 \| 1e-4 \| 2343 \| 512 \| 1024 \| \| 65B \| All \| 64 \| 1e-4 \| 2500 \| 384 \| 128 \| \| 65B \| OASST1 \| 16 \| 1e-4 \| 1875 \| - \| 512 \| \| 65B \| HH-RLHF \| 64 \| 1e-4 \| 2500 \| - \| 768 \| \| 65B \| Longform \| 32 \| 1e-4 \| 2343 \| 512 \| 1024 \| ### Evaluation We use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy. Dataset \| 7B \| 13B \| 33B \| 65B ---\|---\|---\|---\|--- LLaMA no tuning \| 35.1 \| 46.9 \| 57.8 \| 63.4 Self-Instruct \| 36.4 \| 33.3 \| 53.0 \| 56.7 Longform \| 32.1 \| 43.2 \| 56.6 \| 59.7 Chip2 \| 34.5 \| 41.6 \| 53.6 \| 59.8 HH-RLHF \| 34.9 \| 44.6 \| 55.8 \| 60.1 Unnatural Instruct \| 41.9 \| 48.1 \| 57.3 \| 61.3 OASST1 (Guanaco) \| 36.6 \| 46.4 \| 57.0 \| 62.2 Alpaca \| 38.8 \| 47.8 \| 57.3 \| 62.5 FLAN v2 \| 44.5 \| 51.4 \| 59.2 \| 63.9 We evaluate the generative language capabilities through automated evaluations on the Vicuna benchmark. We report the score of the QLoRA Instruction Finetuned Models relative to the score obtained by ChatGPT. The rater in this case is GPT-4 which is tasked to assign a score out of 10 to both ChatGPT and the model outputs for each prompt. We report scores for models ranging 7B to 65B and compare them to both academic and commercial baselilnes. \| Model / Dataset \| Params \| Model bits \| Memory \| ChatGPT vs Sys \| Sys vs ChatGPT \| Mean \| 95\% CI \| \|------------------\|--------\|------------\|--------\|----------------\|----------------\|------------------\|---------\| \| GPT-4 \| - \| - \| - \| 119.4\% \| 110.1\% \| 114.5\% \| 2.6\% \| \| Bard \| - \| - \| - \| 93.2\% \| 96.4\% \| 94.8\% \| 4.1\% \| \| Guanaco \| 65B \| 4-bit \| 41 GB \| 96.7\% \| 101.9\% \| 99.3\% \| 4.4\% \| \| Alpaca \| 65B \| 4-bit \| 41 GB \| 63.0\% \| 77.9\% \| 70.7\% \| 4.3\% \| \| FLAN v2 \| 65B \| 4-bit \| 41 GB \| 37.0\% \| 59.6\% \| 48.4\% \| 4.6\% \| \| Guanaco \| 33B \| 4-bit \| 21 GB \| 96.5\% \| 99.2\% \| 97.8\% \| 4.4\% \| \| Open Assistant \| 33B \| 16-bit \| 66 GB \| 73.4\% \| 85.7\% \| 78.1\% \| 5.3\% \| \| Alpaca \| 33B \| 4-bit \| 21 GB \| 67.2\% \| 79.7\% \| 73.6\% \| 4.2\% \| \| FLAN v2 \| 33B \| 4-bit \| 21 GB \| 26.3\% \| 49.7\% \| 38.0\% \| 3.9\% \| \| Vicuna \| 13B \| 16-bit \| 26 GB \| 91.2\% \| 98.7\% \| 94.9\% \| 4.5\% \| \| Guanaco \| 13B \| 4-bit \| 10 GB \| 87.3\% \| 93.4\% \| 90.4\% \| 5.2\% \| \| Alpaca \| 13B \| 4-bit \| 10 GB \| 63.8\% \| 76.7\% \| 69.4\% \| 4.2\% \| \| HH-RLHF \| 13B \| 4-bit \| 10 GB \| 55.5\% \| 69.1\% \| 62.5\% \| 4.7\% \| \| Unnatural Instr. \| 13B \| 4-bit \| 10 GB \| 50.6\% \| 69.8\% \| 60.5\% \| 4.2\% \| \| Chip2 \| 13B \| 4-bit \| 10 GB \| 49.2\% \| 69.3\% \| 59.5\% \| 4.7\% \| \| Longform \| 13B \| 4-bit \| 10 GB \| 44.9\% \| 62.0\% \| 53.6\% \| 5.2\% \| \| Self-Instruct \| 13B \| 4-bit \| 10 GB \| 38.0\% \| 60.5\% \| 49.1\% \| 4.6\% \| \| FLAN v2 \| 13B \| 4-bit \| 10 GB \| 32.4\% \| 61.2\% \| 47.0\% \| 3.6\% \| \| Guanaco \| 7B \| 4-bit \| 5 GB \| 84.1\% \| 89.8\% \| 87.0\% \| 5.4\% \| \| Alpaca \| 7B \| 4-bit \| 5 GB \| 57.3\% \| 71.2\% \| 64.4\% \| 5.0\% \| \| FLAN v2 \| 7B \| 4-bit \| 5 GB \| 33.3\% \| 56.1\% \| 44.8\% \| 4.0\% \| ## Citation ```bibtex @article{dettmers2023qlora, title={QLoRA: Efficient Finetuning of Quantized LLMs}, author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke}, journal={arXiv preprint arXiv:2305.14314}, year={2023} } ```
ariakhosh/adapter6	ariakhosh	2024-05-14T09:57:55Z	0	0	null	[ "safetensors", "arxiv:2305.14314", "arxiv:2302.13971", "region:us" ]	null	2024-05-14T09:56:46Z	# QLoRA Instruction Tuned Models \| [Paper](https://arxiv.org/abs/2305.14314) \| [Code](https://github.com/artidoro/qlora) \| [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) \| The `QLoRA Instruction Tuned Models` are open-source models obtained through 4-bit QLoRA tuning of LLaMA base models on various instruction tuning datasets. They are available in 7B, 13B, 33B, and 65B parameter sizes. Note: The best performing chatbot models are named [Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) and finetuned on OASST1. This model card is for the other models finetuned on other instruction tuning datasets. ⚠️ These models are purely intended for research purposes and could produce problematic outputs. ## What are QLoRA Instruction Tuned Models and why use them? - Strong performance on MMLU following the QLoRA instruction tuning. - Replicable and efficient instruction tuning procedure that can be extended to new use cases. QLoRA training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora). - Rigorous comparison to 16-bit methods (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. - Lightweight checkpoints which only contain adapter weights. ## License and Intended Use QLoRA Instruction Tuned adapter weights are available under Apache 2 license. Note the use of these adapter weights, requires access to the LLaMA model weighs and therefore should be used according to the LLaMA license. ## Usage Here is an example of how you would load Flan v2 7B in 4-bits: ```python import torch from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/qlora-flan-7b' model = AutoModelForCausalLM.from_pretrained( model_name, load_in_4bit=True, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4' ), ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` Inference can then be performed as usual with HF models as follows: ```python prompt = "Introduce yourself" formatted_prompt = ( f"A chat between a curious human and an artificial intelligence assistant." f"The assistant gives helpful, detailed, and polite answers to the user's questions.\n" f"### Human: {prompt} ### Assistant:" ) inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0") outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` Expected output similar to the following: ``` A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. ### Human: Introduce yourself ### Assistant: I am an artificial intelligence assistant. I am here to help you with any questions you may have. ``` ## Current Inference Limitations Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels. Below is how you would load the model in 16 bits: ```python model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/qlora-flan-7b' model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Model Card Architecture: The models released here are LoRA adapters to be used on top of LLaMA models. They are added to all layers. For all model sizes, we use $r=64$. Base Model: These models use LLaMA as base model with sizes 7B, 13B, 33B, 65B. LLaMA is a causal language model pretrained on a large corpus of text. See [LLaMA paper](https://arxiv.org/abs/2302.13971) for more details. Note that these models can inherit biases and limitations of the base model. Finetuning Data: These models are finetuned on various instruction tuning datasets. The datasets used are: Alpaca, HH-RLHF, Unnatural Instr., Chip2, Longform, Self-Instruct, FLAN v2. Languages: The different datasets cover different languages. We direct to the various papers and resources describing the datasets for more details. Next, we describe Training and Evaluation details. ### Training QLoRA Instruction Tuned Models are the result of 4-bit QLoRA supervised finetuning on different instruction tuning datasets. All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models. For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. ### Training hyperparameters \| Parameters \| Dataset \| Batch size \| LR \| Steps \| Source Length \| Target Length \| \|------------\|----------\|------------\|------\|-------\|---------------\|---------------\| \| 7B \| All \| 16 \| 2e-4 \| 10000 \| 384 \| 128 \| \| 7B \| OASST1 \| 16 \| 2e-4 \| 1875 \| - \| 512 \| \| 7B \| HH-RLHF \| 16 \| 2e-4 \| 10000 \| - \| 768 \| \| 7B \| Longform \| 16 \| 2e-4 \| 4000 \| 512 \| 1024 \| \| 13B \| All \| 16 \| 2e-4 \| 10000 \| 384 \| 128 \| \| 13B \| OASST1 \| 16 \| 2e-4 \| 1875 \| - \| 512 \| \| 13B \| HH-RLHF \| 16 \| 2e-4 \| 10000 \| - \| 768 \| \| 13B \| Longform \| 16 \| 2e-4 \| 4000 \| 512 \| 1024 \| \| 33B \| All \| 32 \| 1e-4 \| 5000 \| 384 \| 128 \| \| 33B \| OASST1 \| 16 \| 1e-4 \| 1875 \| - \| 512 \| \| 33B \| HH-RLHF \| 32 \| 1e-4 \| 5000 \| - \| 768 \| \| 33B \| Longform \| 32 \| 1e-4 \| 2343 \| 512 \| 1024 \| \| 65B \| All \| 64 \| 1e-4 \| 2500 \| 384 \| 128 \| \| 65B \| OASST1 \| 16 \| 1e-4 \| 1875 \| - \| 512 \| \| 65B \| HH-RLHF \| 64 \| 1e-4 \| 2500 \| - \| 768 \| \| 65B \| Longform \| 32 \| 1e-4 \| 2343 \| 512 \| 1024 \| ### Evaluation We use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy. Dataset \| 7B \| 13B \| 33B \| 65B ---\|---\|---\|---\|--- LLaMA no tuning \| 35.1 \| 46.9 \| 57.8 \| 63.4 Self-Instruct \| 36.4 \| 33.3 \| 53.0 \| 56.7 Longform \| 32.1 \| 43.2 \| 56.6 \| 59.7 Chip2 \| 34.5 \| 41.6 \| 53.6 \| 59.8 HH-RLHF \| 34.9 \| 44.6 \| 55.8 \| 60.1 Unnatural Instruct \| 41.9 \| 48.1 \| 57.3 \| 61.3 OASST1 (Guanaco) \| 36.6 \| 46.4 \| 57.0 \| 62.2 Alpaca \| 38.8 \| 47.8 \| 57.3 \| 62.5 FLAN v2 \| 44.5 \| 51.4 \| 59.2 \| 63.9 We evaluate the generative language capabilities through automated evaluations on the Vicuna benchmark. We report the score of the QLoRA Instruction Finetuned Models relative to the score obtained by ChatGPT. The rater in this case is GPT-4 which is tasked to assign a score out of 10 to both ChatGPT and the model outputs for each prompt. We report scores for models ranging 7B to 65B and compare them to both academic and commercial baselilnes. \| Model / Dataset \| Params \| Model bits \| Memory \| ChatGPT vs Sys \| Sys vs ChatGPT \| Mean \| 95\% CI \| \|------------------\|--------\|------------\|--------\|----------------\|----------------\|------------------\|---------\| \| GPT-4 \| - \| - \| - \| 119.4\% \| 110.1\% \| 114.5\% \| 2.6\% \| \| Bard \| - \| - \| - \| 93.2\% \| 96.4\% \| 94.8\% \| 4.1\% \| \| Guanaco \| 65B \| 4-bit \| 41 GB \| 96.7\% \| 101.9\% \| 99.3\% \| 4.4\% \| \| Alpaca \| 65B \| 4-bit \| 41 GB \| 63.0\% \| 77.9\% \| 70.7\% \| 4.3\% \| \| FLAN v2 \| 65B \| 4-bit \| 41 GB \| 37.0\% \| 59.6\% \| 48.4\% \| 4.6\% \| \| Guanaco \| 33B \| 4-bit \| 21 GB \| 96.5\% \| 99.2\% \| 97.8\% \| 4.4\% \| \| Open Assistant \| 33B \| 16-bit \| 66 GB \| 73.4\% \| 85.7\% \| 78.1\% \| 5.3\% \| \| Alpaca \| 33B \| 4-bit \| 21 GB \| 67.2\% \| 79.7\% \| 73.6\% \| 4.2\% \| \| FLAN v2 \| 33B \| 4-bit \| 21 GB \| 26.3\% \| 49.7\% \| 38.0\% \| 3.9\% \| \| Vicuna \| 13B \| 16-bit \| 26 GB \| 91.2\% \| 98.7\% \| 94.9\% \| 4.5\% \| \| Guanaco \| 13B \| 4-bit \| 10 GB \| 87.3\% \| 93.4\% \| 90.4\% \| 5.2\% \| \| Alpaca \| 13B \| 4-bit \| 10 GB \| 63.8\% \| 76.7\% \| 69.4\% \| 4.2\% \| \| HH-RLHF \| 13B \| 4-bit \| 10 GB \| 55.5\% \| 69.1\% \| 62.5\% \| 4.7\% \| \| Unnatural Instr. \| 13B \| 4-bit \| 10 GB \| 50.6\% \| 69.8\% \| 60.5\% \| 4.2\% \| \| Chip2 \| 13B \| 4-bit \| 10 GB \| 49.2\% \| 69.3\% \| 59.5\% \| 4.7\% \| \| Longform \| 13B \| 4-bit \| 10 GB \| 44.9\% \| 62.0\% \| 53.6\% \| 5.2\% \| \| Self-Instruct \| 13B \| 4-bit \| 10 GB \| 38.0\% \| 60.5\% \| 49.1\% \| 4.6\% \| \| FLAN v2 \| 13B \| 4-bit \| 10 GB \| 32.4\% \| 61.2\% \| 47.0\% \| 3.6\% \| \| Guanaco \| 7B \| 4-bit \| 5 GB \| 84.1\% \| 89.8\% \| 87.0\% \| 5.4\% \| \| Alpaca \| 7B \| 4-bit \| 5 GB \| 57.3\% \| 71.2\% \| 64.4\% \| 5.0\% \| \| FLAN v2 \| 7B \| 4-bit \| 5 GB \| 33.3\% \| 56.1\% \| 44.8\% \| 4.0\% \| ## Citation ```bibtex @article{dettmers2023qlora, title={QLoRA: Efficient Finetuning of Quantized LLMs}, author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke}, journal={arXiv preprint arXiv:2305.14314}, year={2023} } ```
ariakhosh/adapter5	ariakhosh	2024-05-14T09:56:28Z	0	0	null	[ "safetensors", "arxiv:2305.14314", "arxiv:2302.13971", "region:us" ]	null	2024-05-14T09:55:18Z	# QLoRA Instruction Tuned Models \| [Paper](https://arxiv.org/abs/2305.14314) \| [Code](https://github.com/artidoro/qlora) \| [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) \| The `QLoRA Instruction Tuned Models` are open-source models obtained through 4-bit QLoRA tuning of LLaMA base models on various instruction tuning datasets. They are available in 7B, 13B, 33B, and 65B parameter sizes. Note: The best performing chatbot models are named [Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) and finetuned on OASST1. This model card is for the other models finetuned on other instruction tuning datasets. ⚠️ These models are purely intended for research purposes and could produce problematic outputs. ## What are QLoRA Instruction Tuned Models and why use them? - Strong performance on MMLU following the QLoRA instruction tuning. - Replicable and efficient instruction tuning procedure that can be extended to new use cases. QLoRA training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora). - Rigorous comparison to 16-bit methods (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. - Lightweight checkpoints which only contain adapter weights. ## License and Intended Use QLoRA Instruction Tuned adapter weights are available under Apache 2 license. Note the use of these adapter weights, requires access to the LLaMA model weighs and therefore should be used according to the LLaMA license. ## Usage Here is an example of how you would load Flan v2 7B in 4-bits: ```python import torch from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/qlora-flan-7b' model = AutoModelForCausalLM.from_pretrained( model_name, load_in_4bit=True, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4' ), ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` Inference can then be performed as usual with HF models as follows: ```python prompt = "Introduce yourself" formatted_prompt = ( f"A chat between a curious human and an artificial intelligence assistant." f"The assistant gives helpful, detailed, and polite answers to the user's questions.\n" f"### Human: {prompt} ### Assistant:" ) inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0") outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` Expected output similar to the following: ``` A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. ### Human: Introduce yourself ### Assistant: I am an artificial intelligence assistant. I am here to help you with any questions you may have. ``` ## Current Inference Limitations Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels. Below is how you would load the model in 16 bits: ```python model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/qlora-flan-7b' model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Model Card Architecture: The models released here are LoRA adapters to be used on top of LLaMA models. They are added to all layers. For all model sizes, we use $r=64$. Base Model: These models use LLaMA as base model with sizes 7B, 13B, 33B, 65B. LLaMA is a causal language model pretrained on a large corpus of text. See [LLaMA paper](https://arxiv.org/abs/2302.13971) for more details. Note that these models can inherit biases and limitations of the base model. Finetuning Data: These models are finetuned on various instruction tuning datasets. The datasets used are: Alpaca, HH-RLHF, Unnatural Instr., Chip2, Longform, Self-Instruct, FLAN v2. Languages: The different datasets cover different languages. We direct to the various papers and resources describing the datasets for more details. Next, we describe Training and Evaluation details. ### Training QLoRA Instruction Tuned Models are the result of 4-bit QLoRA supervised finetuning on different instruction tuning datasets. All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models. For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. ### Training hyperparameters \| Parameters \| Dataset \| Batch size \| LR \| Steps \| Source Length \| Target Length \| \|------------\|----------\|------------\|------\|-------\|---------------\|---------------\| \| 7B \| All \| 16 \| 2e-4 \| 10000 \| 384 \| 128 \| \| 7B \| OASST1 \| 16 \| 2e-4 \| 1875 \| - \| 512 \| \| 7B \| HH-RLHF \| 16 \| 2e-4 \| 10000 \| - \| 768 \| \| 7B \| Longform \| 16 \| 2e-4 \| 4000 \| 512 \| 1024 \| \| 13B \| All \| 16 \| 2e-4 \| 10000 \| 384 \| 128 \| \| 13B \| OASST1 \| 16 \| 2e-4 \| 1875 \| - \| 512 \| \| 13B \| HH-RLHF \| 16 \| 2e-4 \| 10000 \| - \| 768 \| \| 13B \| Longform \| 16 \| 2e-4 \| 4000 \| 512 \| 1024 \| \| 33B \| All \| 32 \| 1e-4 \| 5000 \| 384 \| 128 \| \| 33B \| OASST1 \| 16 \| 1e-4 \| 1875 \| - \| 512 \| \| 33B \| HH-RLHF \| 32 \| 1e-4 \| 5000 \| - \| 768 \| \| 33B \| Longform \| 32 \| 1e-4 \| 2343 \| 512 \| 1024 \| \| 65B \| All \| 64 \| 1e-4 \| 2500 \| 384 \| 128 \| \| 65B \| OASST1 \| 16 \| 1e-4 \| 1875 \| - \| 512 \| \| 65B \| HH-RLHF \| 64 \| 1e-4 \| 2500 \| - \| 768 \| \| 65B \| Longform \| 32 \| 1e-4 \| 2343 \| 512 \| 1024 \| ### Evaluation We use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy. Dataset \| 7B \| 13B \| 33B \| 65B ---\|---\|---\|---\|--- LLaMA no tuning \| 35.1 \| 46.9 \| 57.8 \| 63.4 Self-Instruct \| 36.4 \| 33.3 \| 53.0 \| 56.7 Longform \| 32.1 \| 43.2 \| 56.6 \| 59.7 Chip2 \| 34.5 \| 41.6 \| 53.6 \| 59.8 HH-RLHF \| 34.9 \| 44.6 \| 55.8 \| 60.1 Unnatural Instruct \| 41.9 \| 48.1 \| 57.3 \| 61.3 OASST1 (Guanaco) \| 36.6 \| 46.4 \| 57.0 \| 62.2 Alpaca \| 38.8 \| 47.8 \| 57.3 \| 62.5 FLAN v2 \| 44.5 \| 51.4 \| 59.2 \| 63.9 We evaluate the generative language capabilities through automated evaluations on the Vicuna benchmark. We report the score of the QLoRA Instruction Finetuned Models relative to the score obtained by ChatGPT. The rater in this case is GPT-4 which is tasked to assign a score out of 10 to both ChatGPT and the model outputs for each prompt. We report scores for models ranging 7B to 65B and compare them to both academic and commercial baselilnes. \| Model / Dataset \| Params \| Model bits \| Memory \| ChatGPT vs Sys \| Sys vs ChatGPT \| Mean \| 95\% CI \| \|------------------\|--------\|------------\|--------\|----------------\|----------------\|------------------\|---------\| \| GPT-4 \| - \| - \| - \| 119.4\% \| 110.1\% \| 114.5\% \| 2.6\% \| \| Bard \| - \| - \| - \| 93.2\% \| 96.4\% \| 94.8\% \| 4.1\% \| \| Guanaco \| 65B \| 4-bit \| 41 GB \| 96.7\% \| 101.9\% \| 99.3\% \| 4.4\% \| \| Alpaca \| 65B \| 4-bit \| 41 GB \| 63.0\% \| 77.9\% \| 70.7\% \| 4.3\% \| \| FLAN v2 \| 65B \| 4-bit \| 41 GB \| 37.0\% \| 59.6\% \| 48.4\% \| 4.6\% \| \| Guanaco \| 33B \| 4-bit \| 21 GB \| 96.5\% \| 99.2\% \| 97.8\% \| 4.4\% \| \| Open Assistant \| 33B \| 16-bit \| 66 GB \| 73.4\% \| 85.7\% \| 78.1\% \| 5.3\% \| \| Alpaca \| 33B \| 4-bit \| 21 GB \| 67.2\% \| 79.7\% \| 73.6\% \| 4.2\% \| \| FLAN v2 \| 33B \| 4-bit \| 21 GB \| 26.3\% \| 49.7\% \| 38.0\% \| 3.9\% \| \| Vicuna \| 13B \| 16-bit \| 26 GB \| 91.2\% \| 98.7\% \| 94.9\% \| 4.5\% \| \| Guanaco \| 13B \| 4-bit \| 10 GB \| 87.3\% \| 93.4\% \| 90.4\% \| 5.2\% \| \| Alpaca \| 13B \| 4-bit \| 10 GB \| 63.8\% \| 76.7\% \| 69.4\% \| 4.2\% \| \| HH-RLHF \| 13B \| 4-bit \| 10 GB \| 55.5\% \| 69.1\% \| 62.5\% \| 4.7\% \| \| Unnatural Instr. \| 13B \| 4-bit \| 10 GB \| 50.6\% \| 69.8\% \| 60.5\% \| 4.2\% \| \| Chip2 \| 13B \| 4-bit \| 10 GB \| 49.2\% \| 69.3\% \| 59.5\% \| 4.7\% \| \| Longform \| 13B \| 4-bit \| 10 GB \| 44.9\% \| 62.0\% \| 53.6\% \| 5.2\% \| \| Self-Instruct \| 13B \| 4-bit \| 10 GB \| 38.0\% \| 60.5\% \| 49.1\% \| 4.6\% \| \| FLAN v2 \| 13B \| 4-bit \| 10 GB \| 32.4\% \| 61.2\% \| 47.0\% \| 3.6\% \| \| Guanaco \| 7B \| 4-bit \| 5 GB \| 84.1\% \| 89.8\% \| 87.0\% \| 5.4\% \| \| Alpaca \| 7B \| 4-bit \| 5 GB \| 57.3\% \| 71.2\% \| 64.4\% \| 5.0\% \| \| FLAN v2 \| 7B \| 4-bit \| 5 GB \| 33.3\% \| 56.1\% \| 44.8\% \| 4.0\% \| ## Citation ```bibtex @article{dettmers2023qlora, title={QLoRA: Efficient Finetuning of Quantized LLMs}, author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke}, journal={arXiv preprint arXiv:2305.14314}, year={2023} } ```
Litzy619/G0513HMA18H	Litzy619	2024-05-14T09:55:46Z	0	0	null	[ "safetensors", "generated_from_trainer", "base_model:google/gemma-2b", "base_model:finetune:google/gemma-2b", "license:gemma", "region:us" ]	null	2024-05-14T08:30:00Z	--- license: gemma base_model: google/gemma-2b tags: - generated_from_trainer model-index: - name: G0513HMA18H 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. --> # G0513HMA18H This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1260 ## 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: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 60 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 3.1408 \| 0.09 \| 10 \| 2.7234 \| \| 2.2777 \| 0.18 \| 20 \| 1.6102 \| \| 1.1251 \| 0.27 \| 30 \| 0.5583 \| \| 0.3105 \| 0.36 \| 40 \| 0.1700 \| \| 0.1607 \| 0.45 \| 50 \| 0.1518 \| \| 0.1511 \| 0.54 \| 60 \| 0.1510 \| \| 0.1503 \| 0.63 \| 70 \| 0.1517 \| \| 0.1515 \| 0.73 \| 80 \| 0.1494 \| \| 0.1429 \| 0.82 \| 90 \| 0.1487 \| \| 0.1455 \| 0.91 \| 100 \| 0.1479 \| \| 0.149 \| 1.0 \| 110 \| 0.1491 \| \| 0.1437 \| 1.09 \| 120 \| 0.1489 \| \| 0.1447 \| 1.18 \| 130 \| 0.1486 \| \| 0.1445 \| 1.27 \| 140 \| 0.1475 \| \| 0.1484 \| 1.36 \| 150 \| 0.1462 \| \| 0.1417 \| 1.45 \| 160 \| 0.1461 \| \| 0.1436 \| 1.54 \| 170 \| 0.1454 \| \| 0.1444 \| 1.63 \| 180 \| 0.1448 \| \| 0.1456 \| 1.72 \| 190 \| 0.1476 \| \| 0.1439 \| 1.81 \| 200 \| 0.1442 \| \| 0.1421 \| 1.9 \| 210 \| 0.1423 \| \| 0.1406 \| 1.99 \| 220 \| 0.1393 \| \| 0.135 \| 2.08 \| 230 \| 0.1362 \| \| 0.131 \| 2.18 \| 240 \| 0.1343 \| \| 0.128 \| 2.27 \| 250 \| 0.1325 \| \| 0.1349 \| 2.36 \| 260 \| 0.1333 \| \| 0.1302 \| 2.45 \| 270 \| 0.1316 \| \| 0.1237 \| 2.54 \| 280 \| 0.1280 \| \| 0.12 \| 2.63 \| 290 \| 0.1267 \| \| 0.1219 \| 2.72 \| 300 \| 0.1260 \| \| 0.1235 \| 2.81 \| 310 \| 0.1259 \| \| 0.1244 \| 2.9 \| 320 \| 0.1260 \| \| 0.1228 \| 2.99 \| 330 \| 0.1260 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.0

Subsets and Splits