Datasets:

---

ftopal

/

huggingface-models

like 0

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "diffusers", "tensorboard", "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", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - embracellm/sushi_LoRA_2\n\n<Gallery />", "## Model description\n\nThese are embracellm/sushi_LoRA_2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of sushi to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #tensorboard #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 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - embracellm/sushi_LoRA_2\n\n<Gallery />", "## Model description\n\nThese are embracellm/sushi_LoRA_2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: madebyollin/sdxl-vae-fp16-fix.", "## Trigger words\n\nYou should use a photo of sushi to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "transformers", "safetensors", "stablelm", "text-generation", "merge", "mergekit", "lazymergekit", "aipib/stablelm-2-1_6b_slerpmerge", "stabilityai/stablelm-2-1_6b", "conversational", "base_model:aipib/stablelm-2-1_6b_slerpmerge", "base_model:stabilityai/stablelm-2-1_6b", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# stablelm-2-zephyr-1.6b-slerpx2\n\nstablelm-2-zephyr-1.6b-slerpx2 is a merge of the following models using LazyMergekit:\n* aipib/stablelm-2-1_6b_slerpmerge\n* stabilityai/stablelm-2-1_6b", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #merge #mergekit #lazymergekit #aipib/stablelm-2-1_6b_slerpmerge #stabilityai/stablelm-2-1_6b #conversational #base_model-aipib/stablelm-2-1_6b_slerpmerge #base_model-stabilityai/stablelm-2-1_6b #autotrain_compatible #endpoints_compatible #region-us \n", "# stablelm-2-zephyr-1.6b-slerpx2\n\nstablelm-2-zephyr-1.6b-slerpx2 is a merge of the following models using LazyMergekit:\n* aipib/stablelm-2-1_6b_slerpmerge\n* stabilityai/stablelm-2-1_6b", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:HuggingFaceH4/mistral-7b-sft-beta", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_5iters_bs256_nodpo_only4w_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-HuggingFaceH4/mistral-7b-sft-beta #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_5iters_bs256_nodpo_only4w_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "bert", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #bert #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "idefics", "pretraining", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #idefics #pretraining #arxiv-1910.09700 #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "gguf", "llama-cpp", "gguf-my-repo", "license:cc-by-nc-4.0", "region:us" ]

[]

[]

[ "# EnverLee/DAVinCI-42dot_LLM-PLM-1.3B-v1.2-Q4_0-GGUF\nThis model was converted to GGUF format from 'jungyuko/DAVinCI-42dot_LLM-PLM-1.3B-v1.2' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #llama-cpp #gguf-my-repo #license-cc-by-nc-4.0 #region-us \n", "# EnverLee/DAVinCI-42dot_LLM-PLM-1.3B-v1.2-Q4_0-GGUF\nThis model was converted to GGUF format from 'jungyuko/DAVinCI-42dot_LLM-PLM-1.3B-v1.2' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "gguf", "en", "base_model:Manavshah/llama4-dolphin-8B", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #en #base_model-Manavshah/llama4-dolphin-8B #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "stablelm", "text-generation", "merge", "mergekit", "lazymergekit", "aipib/stablelm-2-zephyr-1.6b-slerpx2", "aipib/stablelm-2-1_6b_slerpmerge", "conversational", "base_model:aipib/stablelm-2-zephyr-1.6b-slerpx2", "base_model:aipib/stablelm-2-1_6b_slerpmerge", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# stablelm-2-zephyr-1.6b-slerpx3\n\nstablelm-2-zephyr-1.6b-slerpx3 is a merge of the following models using LazyMergekit:\n* aipib/stablelm-2-zephyr-1.6b-slerpx2\n* aipib/stablelm-2-1_6b_slerpmerge", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #merge #mergekit #lazymergekit #aipib/stablelm-2-zephyr-1.6b-slerpx2 #aipib/stablelm-2-1_6b_slerpmerge #conversational #base_model-aipib/stablelm-2-zephyr-1.6b-slerpx2 #base_model-aipib/stablelm-2-1_6b_slerpmerge #autotrain_compatible #endpoints_compatible #region-us \n", "# stablelm-2-zephyr-1.6b-slerpx3\n\nstablelm-2-zephyr-1.6b-slerpx3 is a merge of the following models using LazyMergekit:\n* aipib/stablelm-2-zephyr-1.6b-slerpx2\n* aipib/stablelm-2-1_6b_slerpmerge", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "gemma", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "doi:10.57967/hf/2132", "region:us" ]

[]

[]

[ "# rakib72642/Face_Detection_Logic", "# HuggingFace: URL", "# Setup Global API\n\nsudo apt install iproute2 -y && sudo apt install wget -y && sudo apt install unzip -y && sudo apt install unzip -y && sudo apt install nvtop -y && sudo apt-get install git-all -y && sudo apt-get install git-lfs -y && sudo apt-get update && sudo apt-get install libgl1 -y && sudo apt install curl -y && curl -s URL | sudo tee /etc/apt/URL.d/URL >/dev/null && echo \"deb URL buster main\" | sudo tee /etc/apt/URL.d/URL && sudo apt update && sudo apt install ngrok -y && sudo apt update && sudo apt upgrade -y && ngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && ngrok http --domain=URL 8060", "# Setup Local API\n\ngit clone URL && cd Face_Detection_Logic && pip install -r URL && sudo apt update && sudo apt upgrade -y && python face_logic_api.py\n\ncd Face_Detection_Logic && python face_logic_api.py", "# hypercorn face_logic_api:app --bind 127.0.0.1:8060 --workers 4" ]

[ "TAGS\n#doi-10.57967/hf/2132 #region-us \n", "# rakib72642/Face_Detection_Logic", "# HuggingFace: URL", "# Setup Global API\n\nsudo apt install iproute2 -y && sudo apt install wget -y && sudo apt install unzip -y && sudo apt install unzip -y && sudo apt install nvtop -y && sudo apt-get install git-all -y && sudo apt-get install git-lfs -y && sudo apt-get update && sudo apt-get install libgl1 -y && sudo apt install curl -y && curl -s URL | sudo tee /etc/apt/URL.d/URL >/dev/null && echo \"deb URL buster main\" | sudo tee /etc/apt/URL.d/URL && sudo apt update && sudo apt install ngrok -y && sudo apt update && sudo apt upgrade -y && ngrok config add-authtoken 2Qm8hS1zPhVXiLjEdlI4738tLzF_2QJwGJMK5oTbQD33QSVXS && ngrok http --domain=URL 8060", "# Setup Local API\n\ngit clone URL && cd Face_Detection_Logic && pip install -r URL && sudo apt update && sudo apt upgrade -y && python face_logic_api.py\n\ncd Face_Detection_Logic && python face_logic_api.py", "# hypercorn face_logic_api:app --bind 127.0.0.1:8060 --workers 4" ]

[ "diffusers", "safetensors", "code", "unconditional-image-generation", "en", "dataset:huggan/smithsonian_butterflies_subset", "license:mit", "diffusers:DDPMPipeline", "region:us" ]

[]

[ "en" ]

[ "# 此模型是用于生成蝴蝶图像的无条件生成扩散模型 by shoe\n\n'''python\nfrom diffusers import DDPMPipeline\npipeline = DDPMPipeline.from_pretrained('{hub_model_id}')\nimage = pipeline().images[0]\nimage" ]

[ "TAGS\n#diffusers #safetensors #code #unconditional-image-generation #en #dataset-huggan/smithsonian_butterflies_subset #license-mit #diffusers-DDPMPipeline #region-us \n", "# 此模型是用于生成蝴蝶图像的无条件生成扩散模型 by shoe\n\n'''python\nfrom diffusers import DDPMPipeline\npipeline = DDPMPipeline.from_pretrained('{hub_model_id}')\nimage = pipeline().images[0]\nimage" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "gguf", "mistral", "mix", "en", "base_model:CalderaAI/Hexoteric-7B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #mistral #mix #en #base_model-CalderaAI/Hexoteric-7B #license-apache-2.0 #endpoints_compatible #region-us \n" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:HuggingFaceH4/mistral-7b-sft-beta", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.0_4iters_bs256_nodpo_only4w_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-HuggingFaceH4/mistral-7b-sft-beta #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.0_4iters_bs256_nodpo_only4w_iter_1\n\nThis model is a fine-tuned version of HuggingFaceH4/mistral-7b-sft-beta on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

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

[]

[]

[]

[ "TAGS\n#gguf #license-apache-2.0 #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "region:us" ]

[]

[]

[ "# radiopaedia_cl-llama3_8b-240426\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 8\n- eval_batch_size: 16\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us \n", "# radiopaedia_cl-llama3_8b-240426\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 8\n- eval_batch_size: 16\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 100\n- num_epochs: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:TitleOS/EinsteinBagel-8B", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #mergekit #merge #en #base_model-TitleOS/EinsteinBagel-8B #license-llama3 #endpoints_compatible #region-us \n" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# CS505_COQE_viT5_total_Instruction0_SOPAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_total_Instruction0_SOPAL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "orpo", "conversational", "en", "dataset:mlabonne/orpo-dpo-mix-40k", "base_model:meta-llama/Meta-Llama-3-8B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# OrpoLlama3-8B\n\n\n!image/jpeg\n\nThis is an ORPO fine-tune of meta-llama/Meta-Llama-3-8B on 1.5k steps of mlabonne/orpo-dpo-mix-40k.", "## Usage", "## Training curves\n\nWandb Report\n\n\n!image/png", "## Evaluation\n\n!image/png" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #orpo #conversational #en #dataset-mlabonne/orpo-dpo-mix-40k #base_model-meta-llama/Meta-Llama-3-8B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# OrpoLlama3-8B\n\n\n!image/jpeg\n\nThis is an ORPO fine-tune of meta-llama/Meta-Llama-3-8B on 1.5k steps of mlabonne/orpo-dpo-mix-40k.", "## Usage", "## Training curves\n\nWandb Report\n\n\n!image/png", "## Evaluation\n\n!image/png" ]

[ "transformers", "safetensors", "swinv2", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swinv2-tiny-patch4-window16-256", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#transformers #safetensors #swinv2 #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swinv2-tiny-patch4-window16-256 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1", "liminerity/llama-3-8b-silent-star", "conversational", "base_model:Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1", "base_model:liminerity/llama-3-8b-silent-star", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# llama-lexi-star-uncensored-8b-slerp\n\nllama-lexi-star-uncensored-8b-slerp is a merge of the following models using LazyMergekit:\n* Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1\n* liminerity/llama-3-8b-silent-star", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1 #liminerity/llama-3-8b-silent-star #conversational #base_model-Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1 #base_model-liminerity/llama-3-8b-silent-star #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# llama-lexi-star-uncensored-8b-slerp\n\nllama-lexi-star-uncensored-8b-slerp is a merge of the following models using LazyMergekit:\n* Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1\n* liminerity/llama-3-8b-silent-star", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "phi3", "text-generation", "custom_code", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #custom_code #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "base_model:bert-base-cased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'AdamWeightDecay', 'learning\\_rate': 2e-05, 'decay': 0.0, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight\\_decay\\_rate': 0.01}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* TensorFlow 2.15.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tf #bert #text-classification #generated_from_keras_callback #base_model-bert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'AdamWeightDecay', 'learning\\_rate': 2e-05, 'decay': 0.0, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight\\_decay\\_rate': 0.01}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* TensorFlow 2.15.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "xtuner", "gguf", "llama-cpp", "gguf-my-repo", "image-text-to-text", "dataset:Lin-Chen/ShareGPT4V", "region:us" ]

[]

[]

[ "# nullt3r/llava-llama-3-8b-v1_1-Q8_0-GGUF\nThis model was converted to GGUF format from 'xtuner/llava-llama-3-8b-v1_1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#xtuner #gguf #llama-cpp #gguf-my-repo #image-text-to-text #dataset-Lin-Chen/ShareGPT4V #region-us \n", "# nullt3r/llava-llama-3-8b-v1_1-Q8_0-GGUF\nThis model was converted to GGUF format from 'xtuner/llava-llama-3-8b-v1_1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# CS505_COQE_viT5_total_Instruction0_SOPAL_v1_h1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 25\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_total_Instruction0_SOPAL_v1_h1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 25\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "hubert", "audio-classification", "generated_from_trainer", "dataset:HareemFatima/stutteringdetection", "base_model:ntu-spml/distilhubert", "license:apache-2.0", "model-index", "endpoints_compatible", "has_space", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #hubert #audio-classification #generated_from_trainer #dataset-HareemFatima/stutteringdetection #base_model-ntu-spml/distilhubert #license-apache-2.0 #model-index #endpoints_compatible #has_space #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

[]

[]

[ "# Reinforce Agent playing CartPole-v1\n This is a trained model of a Reinforce agent playing CartPole-v1 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "TAGS\n#CartPole-v1 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us \n", "# Reinforce Agent playing CartPole-v1\n This is a trained model of a Reinforce agent playing CartPole-v1 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "gguf", "merge", "mergekit", "lazymergekit", "Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1", "liminerity/llama-3-8b-silent-star", "llama-cpp", "gguf-my-repo", "base_model:Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1", "base_model:liminerity/llama-3-8b-silent-star", "region:us" ]

[]

[]

[ "# gate369/llama-lexi-star-uncensored-8b-slerp-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'liminerity/llama-lexi-star-uncensored-8b-slerp' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #merge #mergekit #lazymergekit #Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1 #liminerity/llama-3-8b-silent-star #llama-cpp #gguf-my-repo #base_model-Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1 #base_model-liminerity/llama-3-8b-silent-star #region-us \n", "# gate369/llama-lexi-star-uncensored-8b-slerp-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'liminerity/llama-lexi-star-uncensored-8b-slerp' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ "transformers", "safetensors", "llama", "text-generation", "not-for-all-audiences", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# miqu-evil-dpo", "# Model Details", "## Description\nmiqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a.\n\nIt is trained with evil-tune method applied.\n\n!image/png", "## Prompt template: Mistral Inst", "## Disclaimer\nThe AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #not-for-all-audiences #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# miqu-evil-dpo", "# Model Details", "## Description\nmiqu-evil-dpo is fine-tuned model based on miqu, serving as a direct successor to PiVoT-0.1-Evil-a.\n\nIt is trained with evil-tune method applied.\n\n!image/png", "## Prompt template: Mistral Inst", "## Disclaimer\nThe AI model provided herein is intended for experimental purposes only. The creator of this model makes no representations or warranties of any kind, either express or implied, as to the model's accuracy, reliability, or suitability for any particular purpose. The creator shall not be held liable for any outcomes, decisions, or actions taken on the basis of the information generated by this model. Users of this model assume full responsibility for any consequences resulting from its use." ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: xsa-dev\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: xsa-dev\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "stablelm", "text-generation", "merge", "mergekit", "lazymergekit", "aipib/stablelm-2-zephyr-1.6b-slerpx3", "stabilityai/stablelm-2-zephyr-1_6b", "conversational", "base_model:aipib/stablelm-2-zephyr-1.6b-slerpx3", "base_model:stabilityai/stablelm-2-zephyr-1_6b", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# stablelm-2-zephyr-1.6b-slerpx9\n\nstablelm-2-zephyr-1.6b-slerpx9 is a merge of the following models using LazyMergekit:\n* aipib/stablelm-2-zephyr-1.6b-slerpx3\n* stabilityai/stablelm-2-zephyr-1_6b", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #merge #mergekit #lazymergekit #aipib/stablelm-2-zephyr-1.6b-slerpx3 #stabilityai/stablelm-2-zephyr-1_6b #conversational #base_model-aipib/stablelm-2-zephyr-1.6b-slerpx3 #base_model-stabilityai/stablelm-2-zephyr-1_6b #autotrain_compatible #endpoints_compatible #region-us \n", "# stablelm-2-zephyr-1.6b-slerpx9\n\nstablelm-2-zephyr-1.6b-slerpx9 is a merge of the following models using LazyMergekit:\n* aipib/stablelm-2-zephyr-1.6b-slerpx3\n* stabilityai/stablelm-2-zephyr-1_6b", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# uzbek-sentiment-analysis\n\nIt achieves the following results on the evaluation set:\n- eval_loss: 0.6374\n- eval_accuracy: {'accuracy': 0.7862348178137651}\n- eval_f1score: {'f1': 0.7880364308572618}\n- eval_runtime: 7.593\n- eval_samples_per_second: 162.65\n- eval_steps_per_second: 20.414\n- step: 0", "## Model description\n\nuzbek-sentiment-analysis modelidan foydalanish.", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 864\n- num_epochs: 7", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.4.0.dev20240416+cu121\n- Datasets 1.18.3\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# uzbek-sentiment-analysis\n\nIt achieves the following results on the evaluation set:\n- eval_loss: 0.6374\n- eval_accuracy: {'accuracy': 0.7862348178137651}\n- eval_f1score: {'f1': 0.7880364308572618}\n- eval_runtime: 7.593\n- eval_samples_per_second: 162.65\n- eval_steps_per_second: 20.414\n- step: 0", "## Model description\n\nuzbek-sentiment-analysis modelidan foydalanish.", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 864\n- num_epochs: 7", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.4.0.dev20240416+cu121\n- Datasets 1.18.3\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "stable-baselines3", "PandaReachDense-v3", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "TAGS\n#stable-baselines3 #PandaReachDense-v3 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# A2C Agent playing PandaReachDense-v3\nThis is a trained model of a A2C agent playing PandaReachDense-v3\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "region:us" ]

[]

[]

[ "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n- PEFT 0.4.0\n\n- PEFT 0.4.0" ]

[ "TAGS\n#peft #region-us \n", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16\n\nThe following 'bitsandbytes' quantization config was used during training:\n- quant_method: bitsandbytes\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: False\n- bnb_4bit_compute_dtype: float16", "### Framework versions\n\n- PEFT 0.4.0\n\n- PEFT 0.4.0" ]

[ "transformers", "tensorboard", "safetensors", "speecht5", "text-to-audio", "generated_from_trainer", "vi", "dataset:mozilla-foundation/common_voice_13_0", "base_model:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]

[]

[ "vi" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #speecht5 #text-to-audio #generated_from_trainer #vi #dataset-mozilla-foundation/common_voice_13_0 #base_model-microsoft/speecht5_tts #license-mit #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 2\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "phi3", "text-generation", "nlp", "code", "phi-3", "function-calling", "conversational", "custom_code", "en", "dataset:Trelis/function_calling_v3", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "### Using tokenizer.apply\\_chat\\_template\n\n\nFor an easier application of the prompt, you can set up as follows (note that the conversation below is complete, i.e. you need to remove assistant messages if you want to feed in the conversation to the model):\n\n\nSet up 'messages':\n\n\nwith 'FUNCTION\\_METADATA' as:\n\n\nand then apply the chat template to get a formatted prompt:\n\n\nIf you are using a gated model, you need to first run:", "### Manual Prompt:\n\n\njson\n{\n\"function\": \"get\\_big\\_stocks\",\n\"parameters\": {\n\"number\": 5,\n\"region\": \"World\"\n}\n}\n\n\nDataset\n=======\n\n\nSee Trelis/function\\_calling\\_v3.\n\n\n\n```\nThe original repo card follows below.\n\n```\n\nModel Summary\n-------------\n\n\nThe Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets.\nThis dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties.\nThe model belongs to the Phi-3 family with the Mini version in two variants 4K and 128K which is the context length (in tokens) that it can support.\n\n\nAfter initial training, the model underwent a post-training process that involved supervised fine-tuning and direct preference optimization to enhance its ability to follow instructions and adhere to safety measures.\nWhen evaluated against benchmarks that test common sense, language understanding, mathematics, coding, long-term context, and logical reasoning, the Phi-3 Mini-128K-Instruct demonstrated robust and state-of-the-art performance among models with fewer than 13 billion parameters.\nResources and Technical Documentation:\n\n\n* Phi-3 Microsoft Blog\n* Phi-3 Technical Report\n* Phi-3 on Azure AI Studio\n* Phi-3 ONNX: 128K\n\n\nIntended Uses\n-------------\n\n\nPrimary use cases\n\n\nThe model is intended for commercial and research use in English. The model provides uses for applications which require:\n\n\n1. Memory/compute constrained environments\n2. Latency bound scenarios\n3. Strong reasoning (especially code, math and logic)\n\n\nOur model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features.\n\n\nUse case considerations\n\n\nOur models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case.\n\n\nNothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under.\n\n\nHow to Use\n----------\n\n\nPhi-3 Mini-128K-Instruct has been integrated in the development version (4.40.0) of 'transformers'. Until the official version is released through 'pip', ensure that you are doing one of the following:\n\n\n* When loading the model, ensure that 'trust\\_remote\\_code=True' is passed as an argument of the 'from\\_pretrained()' function.\n* Update your local 'transformers' to the development version: 'pip uninstall -y transformers && pip install git+URL The previous command is an alternative to cloning and installing from the source.\n\n\nThe current 'transformers' version can be verified with: 'pip list | grep transformers'.", "### Tokenizer\n\n\nPhi-3 Mini-128K-Instruct supports a vocabulary size of up to '32064' tokens. The tokenizer files already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size.", "### Chat Format\n\n\nGiven the nature of the training data, the Phi-3 Mini-128K-Instruct model is best suited for prompts using the chat format as follows.\nYou can provide the prompt as a question with a generic template as follow:\n\n\nFor example:\n\n\nwhere the model generates the text after '<|assistant|>'. In case of few-shots prompt, the prompt can be formatted as the following:", "### Sample inference code\n\n\nThis code snippets show how to get quickly started with running the model on a GPU:\n\n\n*Some applications/frameworks might not include a BOS token ('~~') at the start of the conversation. Please ensure that it is included since it provides more reliable results.~~*\n\n\nResponsible AI Considerations\n-----------------------------\n\n\nLike other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:\n\n\n* Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English.\n* Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.\n* Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.\n* Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.\n* Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as \"typing, math, random, collections, datetime, itertools\". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.\n\n\nDevelopers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include:\n\n\n* Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques.\n* High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context.\n* Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG).\n* Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case.\n* Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations.\n\n\nTraining\n--------", "### Model\n\n\n* Architecture: Phi-3 Mini-128K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.\n* Inputs: Text. It is best suited for prompts using chat format.\n* Context length: 128K tokens\n* GPUs: 512 H100-80G\n* Training time: 7 days\n* Training data: 3.3T tokens\n* Outputs: Generated text in response to the input\n* Dates: Our models were trained between February and April 2024\n* Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models.", "### Datasets\n\n\nOur training data includes a wide variety of sources, totaling 3.3 trillion tokens, and is a combination of\n\n\n1. Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code;\n2. Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.);\n3. High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness.", "### Fine-tuning\n\n\nA basic example of multi-GPUs supervised fine-tuning (SFT) with TRL and Accelerate modules is provided here.\n\n\nBenchmarks\n----------\n\n\nWe report the results for Phi-3-Mini-128K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Phi-2, Mistral-7b-v0.1, Mixtral-8x7b, Gemma 7B, Llama-3-8B-Instruct, and GPT-3.5.\n\n\nAll the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation.\n\n\nAs is now standard, we use few-shot prompts to evaluate the models, at temperature 0.\nThe prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3.\nMore specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model.\n\n\nThe number of k–shot examples is listed per-benchmark.\n\n\n\nSoftware\n--------\n\n\n* PyTorch\n* DeepSpeed\n* Transformers\n* Flash-Attention\n\n\nHardware\n--------\n\n\nNote that by default, the Phi-3-mini model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:\n\n\n* NVIDIA A100\n* NVIDIA A6000\n* NVIDIA H100\n\n\nIf you want to run the model on:\n\n\n* NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from\\_pretrained() with attn\\_implementation=\"eager\"\n* Optimized inference on GPU, CPU, and Mobile: use the ONNX models 128K\n\n\nCross Platform Support\n----------------------\n\n\nONNX runtime ecosystem now supports Phi-3 Mini models across platforms and hardware. You can find the optimized Phi-3 Mini-128K-Instruct ONNX model here.\n\n\nOptimized Phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML support lets developers bring hardware acceleration to Windows devices at scale across AMD, Intel, and NVIDIA GPUs. \n\nAlong with DirectML, ONNX Runtime provides cross platform support for Phi-3 across a range of devices CPU, GPU, and mobile.\n\n\nHere are some of the optimized configurations we have added:\n\n\n1. ONNX models for int4 DML: Quantized to int4 via AWQ\n2. ONNX model for fp16 CUDA\n3. ONNX model for int4 CUDA: Quantized to int4 via RTN\n4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN\n\n\nLicense\n-------\n\n\nThe model is licensed under the MIT license.\n\n\nTrademarks\n----------\n\n\nThis project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies." ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #nlp #code #phi-3 #function-calling #conversational #custom_code #en #dataset-Trelis/function_calling_v3 #autotrain_compatible #endpoints_compatible #region-us \n", "### Using tokenizer.apply\\_chat\\_template\n\n\nFor an easier application of the prompt, you can set up as follows (note that the conversation below is complete, i.e. you need to remove assistant messages if you want to feed in the conversation to the model):\n\n\nSet up 'messages':\n\n\nwith 'FUNCTION\\_METADATA' as:\n\n\nand then apply the chat template to get a formatted prompt:\n\n\nIf you are using a gated model, you need to first run:", "### Manual Prompt:\n\n\njson\n{\n\"function\": \"get\\_big\\_stocks\",\n\"parameters\": {\n\"number\": 5,\n\"region\": \"World\"\n}\n}\n\n\nDataset\n=======\n\n\nSee Trelis/function\\_calling\\_v3.\n\n\n\n```\nThe original repo card follows below.\n\n```\n\nModel Summary\n-------------\n\n\nThe Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets.\nThis dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties.\nThe model belongs to the Phi-3 family with the Mini version in two variants 4K and 128K which is the context length (in tokens) that it can support.\n\n\nAfter initial training, the model underwent a post-training process that involved supervised fine-tuning and direct preference optimization to enhance its ability to follow instructions and adhere to safety measures.\nWhen evaluated against benchmarks that test common sense, language understanding, mathematics, coding, long-term context, and logical reasoning, the Phi-3 Mini-128K-Instruct demonstrated robust and state-of-the-art performance among models with fewer than 13 billion parameters.\nResources and Technical Documentation:\n\n\n* Phi-3 Microsoft Blog\n* Phi-3 Technical Report\n* Phi-3 on Azure AI Studio\n* Phi-3 ONNX: 128K\n\n\nIntended Uses\n-------------\n\n\nPrimary use cases\n\n\nThe model is intended for commercial and research use in English. The model provides uses for applications which require:\n\n\n1. Memory/compute constrained environments\n2. Latency bound scenarios\n3. Strong reasoning (especially code, math and logic)\n\n\nOur model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features.\n\n\nUse case considerations\n\n\nOur models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case.\n\n\nNothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under.\n\n\nHow to Use\n----------\n\n\nPhi-3 Mini-128K-Instruct has been integrated in the development version (4.40.0) of 'transformers'. Until the official version is released through 'pip', ensure that you are doing one of the following:\n\n\n* When loading the model, ensure that 'trust\\_remote\\_code=True' is passed as an argument of the 'from\\_pretrained()' function.\n* Update your local 'transformers' to the development version: 'pip uninstall -y transformers && pip install git+URL The previous command is an alternative to cloning and installing from the source.\n\n\nThe current 'transformers' version can be verified with: 'pip list | grep transformers'.", "### Tokenizer\n\n\nPhi-3 Mini-128K-Instruct supports a vocabulary size of up to '32064' tokens. The tokenizer files already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size.", "### Chat Format\n\n\nGiven the nature of the training data, the Phi-3 Mini-128K-Instruct model is best suited for prompts using the chat format as follows.\nYou can provide the prompt as a question with a generic template as follow:\n\n\nFor example:\n\n\nwhere the model generates the text after '<|assistant|>'. In case of few-shots prompt, the prompt can be formatted as the following:", "### Sample inference code\n\n\nThis code snippets show how to get quickly started with running the model on a GPU:\n\n\n*Some applications/frameworks might not include a BOS token ('~~') at the start of the conversation. Please ensure that it is included since it provides more reliable results.~~*\n\n\nResponsible AI Considerations\n-----------------------------\n\n\nLike other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:\n\n\n* Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English.\n* Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.\n* Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.\n* Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.\n* Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as \"typing, math, random, collections, datetime, itertools\". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.\n\n\nDevelopers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include:\n\n\n* Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques.\n* High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context.\n* Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG).\n* Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case.\n* Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations.\n\n\nTraining\n--------", "### Model\n\n\n* Architecture: Phi-3 Mini-128K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.\n* Inputs: Text. It is best suited for prompts using chat format.\n* Context length: 128K tokens\n* GPUs: 512 H100-80G\n* Training time: 7 days\n* Training data: 3.3T tokens\n* Outputs: Generated text in response to the input\n* Dates: Our models were trained between February and April 2024\n* Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models.", "### Datasets\n\n\nOur training data includes a wide variety of sources, totaling 3.3 trillion tokens, and is a combination of\n\n\n1. Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code;\n2. Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.);\n3. High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness.", "### Fine-tuning\n\n\nA basic example of multi-GPUs supervised fine-tuning (SFT) with TRL and Accelerate modules is provided here.\n\n\nBenchmarks\n----------\n\n\nWe report the results for Phi-3-Mini-128K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Phi-2, Mistral-7b-v0.1, Mixtral-8x7b, Gemma 7B, Llama-3-8B-Instruct, and GPT-3.5.\n\n\nAll the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation.\n\n\nAs is now standard, we use few-shot prompts to evaluate the models, at temperature 0.\nThe prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3.\nMore specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model.\n\n\nThe number of k–shot examples is listed per-benchmark.\n\n\n\nSoftware\n--------\n\n\n* PyTorch\n* DeepSpeed\n* Transformers\n* Flash-Attention\n\n\nHardware\n--------\n\n\nNote that by default, the Phi-3-mini model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:\n\n\n* NVIDIA A100\n* NVIDIA A6000\n* NVIDIA H100\n\n\nIf you want to run the model on:\n\n\n* NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from\\_pretrained() with attn\\_implementation=\"eager\"\n* Optimized inference on GPU, CPU, and Mobile: use the ONNX models 128K\n\n\nCross Platform Support\n----------------------\n\n\nONNX runtime ecosystem now supports Phi-3 Mini models across platforms and hardware. You can find the optimized Phi-3 Mini-128K-Instruct ONNX model here.\n\n\nOptimized Phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML support lets developers bring hardware acceleration to Windows devices at scale across AMD, Intel, and NVIDIA GPUs. \n\nAlong with DirectML, ONNX Runtime provides cross platform support for Phi-3 across a range of devices CPU, GPU, and mobile.\n\n\nHere are some of the optimized configurations we have added:\n\n\n1. ONNX models for int4 DML: Quantized to int4 via AWQ\n2. ONNX model for fp16 CUDA\n3. ONNX model for int4 CUDA: Quantized to int4 via RTN\n4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN\n\n\nLicense\n-------\n\n\nThe model is licensed under the MIT license.\n\n\nTrademarks\n----------\n\n\nThis project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies." ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "swinv2", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swinv2-tiny-patch4-window16-256", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#transformers #safetensors #swinv2 #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swinv2-tiny-patch4-window16-256 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "stablelm", "text-generation", "merge", "mergekit", "lazymergekit", "aipib/stablelm-2-zephyr-1.6b-slerpx9", "stabilityai/stablelm-2-zephyr-1_6b", "conversational", "base_model:aipib/stablelm-2-zephyr-1.6b-slerpx9", "base_model:stabilityai/stablelm-2-zephyr-1_6b", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# stablelm-2-zephyr-1.6b-slerpx10\n\nstablelm-2-zephyr-1.6b-slerpx10 is a merge of the following models using LazyMergekit:\n* aipib/stablelm-2-zephyr-1.6b-slerpx9\n* stabilityai/stablelm-2-zephyr-1_6b", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #stablelm #text-generation #merge #mergekit #lazymergekit #aipib/stablelm-2-zephyr-1.6b-slerpx9 #stabilityai/stablelm-2-zephyr-1_6b #conversational #base_model-aipib/stablelm-2-zephyr-1.6b-slerpx9 #base_model-stabilityai/stablelm-2-zephyr-1_6b #autotrain_compatible #endpoints_compatible #region-us \n", "# stablelm-2-zephyr-1.6b-slerpx10\n\nstablelm-2-zephyr-1.6b-slerpx10 is a merge of the following models using LazyMergekit:\n* aipib/stablelm-2-zephyr-1.6b-slerpx9\n* stabilityai/stablelm-2-zephyr-1_6b", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_iter_2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_4iters_bs128_nodpo_only4w_iter_3\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_4iters_bs128_nodpo_only4w_iter_3\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 128\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_22M", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mahdibaghbanzadeh/seqsight_16384_512_22M #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0005\n* train\\_batch\\_size: 128\n* eval\\_batch\\_size: 128\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* training\\_steps: 10000", "### Training results", "### Framework versions\n\n\n* PEFT 0.9.0\n* Transformers 4.38.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.1\n* Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:VietAI/vit5-large", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# CS505_COQE_viT5_total_Instruction0_SAOPL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-VietAI/vit5-large #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# CS505_COQE_viT5_total_Instruction0_SAOPL_v1\n\nThis model is a fine-tuned version of VietAI/vit5-large on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 20\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:rujengelal/nepali_t5", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-rujengelal/nepali_t5 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]