Datasets:

---

ftopal

/

huggingface-models

like 0

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "TAGS\n#stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# PPO Agent playing LunarLander-v2\nThis is a trained model of a PPO agent playing LunarLander-v2\nusing the stable-baselines3 library.", "## Usage (with Stable-baselines3)\nTODO: Add your code" ]

[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:autoevaluate/binary-classification", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-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* num\\_epochs: 2", "### 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 #distilbert #text-classification #generated_from_trainer #base_model-autoevaluate/binary-classification #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* learning\\_rate: 2e-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* num\\_epochs: 2", "### 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" ]

[ "fastai", "region:us", "has_space" ]

[]

[]

[ "# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!", "# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---", "# Model card", "## Model description\nMore information needed", "## Intended uses & limitations\nMore information needed", "## Training and evaluation data\nMore information needed" ]

[ "TAGS\n#fastai #region-us #has_space \n", "# Amazing!\n\n Congratulations on hosting your fastai model on the Hugging Face Hub!", "# Some next steps\n1. Fill out this model card with more information (see the template below and the documentation here)!\n\n2. Create a demo in Gradio or Streamlit using Spaces (documentation here).\n\n3. Join the fastai community on the Fastai Discord!\n\nGreetings fellow fastlearner ! Don't forget to delete this content from your model card.\n\n\n---", "# Model card", "## Model description\nMore information needed", "## Intended uses & limitations\nMore information needed", "## Training and evaluation data\nMore information needed" ]

[ "gguf", "moe", "merge", "mergekit", "01-ai/Yi-9B-200K", "TechxGenus/Yi-9B-Coder", "llama-cpp", "gguf-my-repo", "base_model:01-ai/Yi-9B-200K", "base_model:TechxGenus/Yi-9B-Coder", "license:apache-2.0", "region:us" ]

[]

[]

[ "# NotAiLOL/Boundary-Coder-Yi-2x9B-MoE-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'NotAiLOL/Boundary-Coder-Yi-2x9B-MoE' 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 #moe #merge #mergekit #01-ai/Yi-9B-200K #TechxGenus/Yi-9B-Coder #llama-cpp #gguf-my-repo #base_model-01-ai/Yi-9B-200K #base_model-TechxGenus/Yi-9B-Coder #license-apache-2.0 #region-us \n", "# NotAiLOL/Boundary-Coder-Yi-2x9B-MoE-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'NotAiLOL/Boundary-Coder-Yi-2x9B-MoE' 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." ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 48\n* eval\\_batch\\_size: 48\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.0\n* Tokenizers 0.15.2" ]

[ "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", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 48\n* eval\\_batch\\_size: 48\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.37.2\n* Pytorch 2.2.0+cu121\n* Datasets 2.17.0\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swin-large-patch4-window7-224-in22k", "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 #swin #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swin-large-patch4-window7-224-in22k #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", "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: cchakons\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 #safetensors #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: cchakons\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", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:t5-small", "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: 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* num\\_epochs: 2\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 #t5 #text2text-generation #generated_from_trainer #base_model-t5-small #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: 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* num\\_epochs: 2\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_4096_512_27M", "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_4096_512_27M #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", "mergekit", "merge", "facebook", "meta", "pytorch", "llama-3", "conversational", "en", "ko", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en", "ko" ]

[ "## KoDolph-2x8b\n\n> Update @ 2024.04.26: Linear Merge of Llama-3-Open-Ko-8B-Instruct-preview and dolphin-2.9-llama3-8b", "### Model Details\n\nKoDolph-2x8b: \nI had this idea at night that it would make sense to make a Linear Merge\n\nModel Merge: \nLinear Merge", "### Composition\n\n1. Base Layers from Llama-3-Open-Ko-8B-Instruct-preview:\n - Range: Layers 0 to 20\n - Purpose: These layers are utilized for their strong foundational language processing capabilities specifically in Korean. They are crucial for processing and understanding Korean text effectively, handling basic linguistic functions and intermediate language understanding.\n\n2. Advanced Layers from Dolphin-2.9-llama3-8b:\n - Range: Layers 15 to 24\n - Purpose: These layers provide advanced domain-specific capabilities, particularly suited for coding and technical tasks. Beginning integration from layer 15 enhances the model's ability to manage complex scenarios involving technical language and coding tasks.\n\nPurpose and Utility:\n\nThis \"Linear Merge\" strategically combines the strengths of both models through weighted averaging, ensuring a balanced influence in the merged output. This approach is designed to provide robust performance in applications requiring a deep understanding and generation of Korean text, along with the capability to handle specialized tasks involving technical descriptions and coding. It is ideal for creating advanced AI assistants, coding bots, or any application where high linguistic and technical precision is needed.", "### Configuration", "### Test Result\n\nRoot Cause:\n- Bad Response: There were some strange answers, so I think there may have been a problem during the merge process. We are merging and investigating again as the instructions are not in the Korean version.\n\n\n<a href=\"URL src=\"https://i.URL alt=\"Screenshot-2024-04-27-at-12-25-46-PM\" border=\"0\" /></a>" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #facebook #meta #pytorch #llama-3 #conversational #en #ko #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## KoDolph-2x8b\n\n> Update @ 2024.04.26: Linear Merge of Llama-3-Open-Ko-8B-Instruct-preview and dolphin-2.9-llama3-8b", "### Model Details\n\nKoDolph-2x8b: \nI had this idea at night that it would make sense to make a Linear Merge\n\nModel Merge: \nLinear Merge", "### Composition\n\n1. Base Layers from Llama-3-Open-Ko-8B-Instruct-preview:\n - Range: Layers 0 to 20\n - Purpose: These layers are utilized for their strong foundational language processing capabilities specifically in Korean. They are crucial for processing and understanding Korean text effectively, handling basic linguistic functions and intermediate language understanding.\n\n2. Advanced Layers from Dolphin-2.9-llama3-8b:\n - Range: Layers 15 to 24\n - Purpose: These layers provide advanced domain-specific capabilities, particularly suited for coding and technical tasks. Beginning integration from layer 15 enhances the model's ability to manage complex scenarios involving technical language and coding tasks.\n\nPurpose and Utility:\n\nThis \"Linear Merge\" strategically combines the strengths of both models through weighted averaging, ensuring a balanced influence in the merged output. This approach is designed to provide robust performance in applications requiring a deep understanding and generation of Korean text, along with the capability to handle specialized tasks involving technical descriptions and coding. It is ideal for creating advanced AI assistants, coding bots, or any application where high linguistic and technical precision is needed.", "### Configuration", "### Test Result\n\nRoot Cause:\n- Bad Response: There were some strange answers, so I think there may have been a problem during the merge process. We are merging and investigating again as the instructions are not in the Korean version.\n\n\n<a href=\"URL src=\"https://i.URL alt=\"Screenshot-2024-04-27-at-12-25-46-PM\" border=\"0\" /></a>" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: kchopra04\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 #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: kchopra04\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\"/>" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "text-generation", "en", "base_model:meta-llama/Meta-Llama-3-8B", "license:llama3", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #text-generation #en #base_model-meta-llama/Meta-Llama-3-8B #license-llama3 #region-us \n" ]

[ "transformers", "pytorch", "tensorboard", "deberta-v2", "token-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15", "### Training results", "### Framework versions\n\n\n* Transformers 4.30.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #tensorboard #deberta-v2 #token-classification #generated_from_trainer #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15", "### Training results", "### Framework versions\n\n\n* Transformers 4.30.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3" ]

[ "transformers", "safetensors", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "Kaoeiri/Keiana-L3-Test5.4-8B-10", "Undi95/Llama-3-LewdPlay-8B", "Kaoeiri/Keiana-L3-Test4.7-8B-3", "conversational", "base_model:Kaoeiri/Keiana-L3-Test5.4-8B-10", "base_model:Undi95/Llama-3-LewdPlay-8B", "base_model:Kaoeiri/Keiana-L3-Test4.7-8B-3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Keiana-L3-Test5.75-8B-13.5\n\nKeiana-L3-Test5.75-8B-13.5 is a merge of the following models using LazyMergekit:", "# Keep in mind that, this merged model isn't usually tested at the moment, which could benefit in vocabulary error.\n* Kaoeiri/Keiana-L3-Test5.4-8B-10\n* Undi95/Llama-3-LewdPlay-8B\n* Kaoeiri/Keiana-L3-Test4.7-8B-3", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #Kaoeiri/Keiana-L3-Test5.4-8B-10 #Undi95/Llama-3-LewdPlay-8B #Kaoeiri/Keiana-L3-Test4.7-8B-3 #conversational #base_model-Kaoeiri/Keiana-L3-Test5.4-8B-10 #base_model-Undi95/Llama-3-LewdPlay-8B #base_model-Kaoeiri/Keiana-L3-Test4.7-8B-3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Keiana-L3-Test5.75-8B-13.5\n\nKeiana-L3-Test5.75-8B-13.5 is a merge of the following models using LazyMergekit:", "# Keep in mind that, this merged model isn't usually tested at the moment, which could benefit in vocabulary error.\n* Kaoeiri/Keiana-L3-Test5.4-8B-10\n* Undi95/Llama-3-LewdPlay-8B\n* Kaoeiri/Keiana-L3-Test4.7-8B-3", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "mistral", "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 #mistral #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" ]

[ "gguf", "llama3", "comedy", "comedian", "fun", "funny", "llama38b", "laugh", "sarcasm", "roleplay", "text-generation", "en", "license:other", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#gguf #llama3 #comedy #comedian #fun #funny #llama38b #laugh #sarcasm #roleplay #text-generation #en #license-other #region-us \n" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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", "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 #mistral #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_4096_512_27M", "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_4096_512_27M #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" ]

[ "sentence-transformers", "bert", "ctranslate2", "int8", "float16", "feature-extraction", "sentence-similarity", "en", "dataset:s2orc", "dataset:flax-sentence-embeddings/stackexchange_xml", "dataset:ms_marco", "dataset:gooaq", "dataset:yahoo_answers_topics", "dataset:code_search_net", "dataset:search_qa", "dataset:eli5", "dataset:snli", "dataset:multi_nli", "dataset:wikihow", "dataset:natural_questions", "dataset:trivia_qa", "dataset:embedding-data/sentence-compression", "dataset:embedding-data/flickr30k-captions", "dataset:embedding-data/altlex", "dataset:embedding-data/simple-wiki", "dataset:embedding-data/QQP", "dataset:embedding-data/SPECTER", "dataset:embedding-data/PAQ_pairs", "dataset:embedding-data/WikiAnswers", "arxiv:1904.06472", "arxiv:2102.07033", "arxiv:2104.08727", "arxiv:1704.05179", "arxiv:1810.09305", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[ "1904.06472", "2102.07033", "2104.08727", "1704.05179", "1810.09305" ]

[ "en" ]

[ "# Fast-Inference with Ctranslate2\n=================================\n\n\nSpeedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.\n\n\nquantized version of sentence-transformers/all-MiniLM-L6-v2\n\n\nCheckpoint compatible to ctranslate2>=3.17.1\nand hf-hub-ctranslate2>=2.12.0\n\n\n* 'compute\\_type=int8\\_float16' for 'device=\"cuda\"'\n* 'compute\\_type=int8' for 'device=\"cpu\"'\n\n\nConverted on 2023-10-13 using\n\n\nLicence and other remarks:\n==========================\n\n\nThis is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.\n\n\nOriginal description\n====================\n\n\nall-MiniLM-L6-v2\n================\n\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.\n\n\nUsage (Sentence-Transformers)\n-----------------------------\n\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\nThen you can use the model like this:\n\n\nUsage (HuggingFace Transformers)\n--------------------------------\n\n\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.\n\n\nEvaluation Results\n------------------\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL\n\n\n\n\n---\n\n\nBackground\n----------\n\n\nThe project aims to train sentence embedding models on very large sentence level datasets using a self-supervised\ncontrastive learning objective. We used the pretrained 'nreimers/MiniLM-L6-H384-uncased' model and fine-tuned in on a\n1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.\n\n\nWe developped this model during the\nCommunity week using JAX/Flax for NLP & CV,\norganized by Hugging Face. We developped this model as part of the project:\nTrain the Best Sentence Embedding Model Ever with 1B Training Pairs. We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.\n\n\nIntended uses\n-------------\n\n\nOur model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures\nthe semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.\n\n\nBy default, input text longer than 256 word pieces is truncated.\n\n\nTraining procedure\n------------------", "### Pre-training\n\n\nWe use the pretrained 'nreimers/MiniLM-L6-H384-uncased' model. Please refer to the model card for more detailed information about the pre-training procedure.", "### Fine-tuning\n\n\nWe fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.\nWe then apply the cross entropy loss by comparing with true pairs.", "#### Hyper parameters\n\n\nWe trained ou model on a TPU v3-8. We train the model during 100k steps using a batch size of 1024 (128 per TPU core).\nWe use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with\na 2e-5 learning rate. The full training script is accessible in this current repository: 'train\\_script.py'.", "#### Training data\n\n\nWe use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.\nWe sampled each dataset given a weighted probability which configuration is detailed in the 'data\\_config.json' file." ]

[ "TAGS\n#sentence-transformers #bert #ctranslate2 #int8 #float16 #feature-extraction #sentence-similarity #en #dataset-s2orc #dataset-flax-sentence-embeddings/stackexchange_xml #dataset-ms_marco #dataset-gooaq #dataset-yahoo_answers_topics #dataset-code_search_net #dataset-search_qa #dataset-eli5 #dataset-snli #dataset-multi_nli #dataset-wikihow #dataset-natural_questions #dataset-trivia_qa #dataset-embedding-data/sentence-compression #dataset-embedding-data/flickr30k-captions #dataset-embedding-data/altlex #dataset-embedding-data/simple-wiki #dataset-embedding-data/QQP #dataset-embedding-data/SPECTER #dataset-embedding-data/PAQ_pairs #dataset-embedding-data/WikiAnswers #arxiv-1904.06472 #arxiv-2102.07033 #arxiv-2104.08727 #arxiv-1704.05179 #arxiv-1810.09305 #license-apache-2.0 #endpoints_compatible #region-us \n", "# Fast-Inference with Ctranslate2\n=================================\n\n\nSpeedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.\n\n\nquantized version of sentence-transformers/all-MiniLM-L6-v2\n\n\nCheckpoint compatible to ctranslate2>=3.17.1\nand hf-hub-ctranslate2>=2.12.0\n\n\n* 'compute\\_type=int8\\_float16' for 'device=\"cuda\"'\n* 'compute\\_type=int8' for 'device=\"cpu\"'\n\n\nConverted on 2023-10-13 using\n\n\nLicence and other remarks:\n==========================\n\n\nThis is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.\n\n\nOriginal description\n====================\n\n\nall-MiniLM-L6-v2\n================\n\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.\n\n\nUsage (Sentence-Transformers)\n-----------------------------\n\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\nThen you can use the model like this:\n\n\nUsage (HuggingFace Transformers)\n--------------------------------\n\n\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.\n\n\nEvaluation Results\n------------------\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL\n\n\n\n\n---\n\n\nBackground\n----------\n\n\nThe project aims to train sentence embedding models on very large sentence level datasets using a self-supervised\ncontrastive learning objective. We used the pretrained 'nreimers/MiniLM-L6-H384-uncased' model and fine-tuned in on a\n1B sentence pairs dataset. We use a contrastive learning objective: given a sentence from the pair, the model should predict which out of a set of randomly sampled other sentences, was actually paired with it in our dataset.\n\n\nWe developped this model during the\nCommunity week using JAX/Flax for NLP & CV,\norganized by Hugging Face. We developped this model as part of the project:\nTrain the Best Sentence Embedding Model Ever with 1B Training Pairs. We benefited from efficient hardware infrastructure to run the project: 7 TPUs v3-8, as well as intervention from Googles Flax, JAX, and Cloud team member about efficient deep learning frameworks.\n\n\nIntended uses\n-------------\n\n\nOur model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures\nthe semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.\n\n\nBy default, input text longer than 256 word pieces is truncated.\n\n\nTraining procedure\n------------------", "### Pre-training\n\n\nWe use the pretrained 'nreimers/MiniLM-L6-H384-uncased' model. Please refer to the model card for more detailed information about the pre-training procedure.", "### Fine-tuning\n\n\nWe fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each possible sentence pairs from the batch.\nWe then apply the cross entropy loss by comparing with true pairs.", "#### Hyper parameters\n\n\nWe trained ou model on a TPU v3-8. We train the model during 100k steps using a batch size of 1024 (128 per TPU core).\nWe use a learning rate warm up of 500. The sequence length was limited to 128 tokens. We used the AdamW optimizer with\na 2e-5 learning rate. The full training script is accessible in this current repository: 'train\\_script.py'.", "#### Training data\n\n\nWe use the concatenation from multiple datasets to fine-tune our model. The total number of sentence pairs is above 1 billion sentences.\nWe sampled each dataset given a weighted probability which configuration is detailed in the 'data\\_config.json' file." ]

[ "transformers", "bert", "endpoints_compatible", "region:us" ]

[]

[]

[ "# # Fast-Inference with Ctranslate2\nSpeedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.\n\nquantized version of sentence-transformers/all-MiniLM-L12-v2\n\n\n\n\nCheckpoint compatible to ctranslate2>=3.17.1\nand hf-hub-ctranslate2>=2.12.0\n- 'compute_type=int8_float16' for 'device=\"cuda\"'\n- 'compute_type=int8' for 'device=\"cpu\"'\n\nConverted on 2023-10-13 using", "# Licence and other remarks:\nThis is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.", "# Original description" ]

[ "TAGS\n#transformers #bert #endpoints_compatible #region-us \n", "# # Fast-Inference with Ctranslate2\nSpeedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.\n\nquantized version of sentence-transformers/all-MiniLM-L12-v2\n\n\n\n\nCheckpoint compatible to ctranslate2>=3.17.1\nand hf-hub-ctranslate2>=2.12.0\n- 'compute_type=int8_float16' for 'device=\"cuda\"'\n- 'compute_type=int8' for 'device=\"cpu\"'\n\nConverted on 2023-10-13 using", "# Licence and other remarks:\nThis is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.", "# Original description" ]

[ "sentence-transformers", "bert", "feature-extraction", "ctranslate2", "int8", "float16", "sentence-similarity", "transformers", "multilingual", "arxiv:1908.10084", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[ "1908.10084" ]

[ "multilingual" ]

[ "# # Fast-Inference with Ctranslate2\nSpeedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.\n\nquantized version of sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2\n\n\n\n\nCheckpoint compatible to ctranslate2>=3.17.1\nand hf-hub-ctranslate2>=2.12.0\n- 'compute_type=int8_float16' for 'device=\"cuda\"'\n- 'compute_type=int8' for 'device=\"cpu\"'\n\nConverted on 2023-10-13 using", "# Licence and other remarks:\nThis is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.", "# Original description", "# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Full Model Architecture", "## Citing & Authors\n\nThis model was trained by sentence-transformers. \n \nIf you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks:" ]

[ "TAGS\n#sentence-transformers #bert #feature-extraction #ctranslate2 #int8 #float16 #sentence-similarity #transformers #multilingual #arxiv-1908.10084 #license-apache-2.0 #endpoints_compatible #region-us \n", "# # Fast-Inference with Ctranslate2\nSpeedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU.\n\nquantized version of sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2\n\n\n\n\nCheckpoint compatible to ctranslate2>=3.17.1\nand hf-hub-ctranslate2>=2.12.0\n- 'compute_type=int8_float16' for 'device=\"cuda\"'\n- 'compute_type=int8' for 'device=\"cpu\"'\n\nConverted on 2023-10-13 using", "# Licence and other remarks:\nThis is just a quantized version. Licence conditions are intended to be idential to original huggingface repo.", "# Original description", "# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2\n\nThis is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.", "## Usage (Sentence-Transformers)\n\nUsing this model becomes easy when you have sentence-transformers installed:\n\n\n\nThen you can use the model like this:", "## Usage (HuggingFace Transformers)\nWithout sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.", "## Evaluation Results\n\n\n\nFor an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: URL", "## Full Model Architecture", "## Citing & Authors\n\nThis model was trained by sentence-transformers. \n \nIf you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks:" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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", "pytorch", "tensorboard", "vit", "image-classification", "image-clasification", "generated_from_trainer", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\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: 4", "### Training results", "### Framework versions\n\n\n* Transformers 4.30.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #tensorboard #vit #image-classification #image-clasification #generated_from_trainer #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* learning\\_rate: 0.0002\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: 4", "### Training results", "### Framework versions\n\n\n* Transformers 4.30.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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" ]

[ "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\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: 2\n* training\\_steps: 1200\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\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: 2\n* training\\_steps: 1200\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "Kaoeiri/Keiana-L3-Test5.4-8B-10", "Undi95/Llama-3-LewdPlay-8B", "Kaoeiri/Keiana-L3-Test4.7-8B-3", "conversational", "base_model:Kaoeiri/Keiana-L3-Test5.4-8B-10", "base_model:Undi95/Llama-3-LewdPlay-8B", "base_model:Kaoeiri/Keiana-L3-Test4.7-8B-3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Keiana-L3-Test5.8-8B-14\n\nKeiana-L3-Test5.8-8B-14 is a merge of the following models using LazyMergekit:", "# Keep in mind that, this merged model isn't usually tested at the moment, which could benefit in vocabulary error.\n* Kaoeiri/Keiana-L3-Test5.4-8B-10\n* Undi95/Llama-3-LewdPlay-8B\n* Kaoeiri/Keiana-L3-Test4.7-8B-3", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #Kaoeiri/Keiana-L3-Test5.4-8B-10 #Undi95/Llama-3-LewdPlay-8B #Kaoeiri/Keiana-L3-Test4.7-8B-3 #conversational #base_model-Kaoeiri/Keiana-L3-Test5.4-8B-10 #base_model-Undi95/Llama-3-LewdPlay-8B #base_model-Kaoeiri/Keiana-L3-Test4.7-8B-3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Keiana-L3-Test5.8-8B-14\n\nKeiana-L3-Test5.8-8B-14 is a merge of the following models using LazyMergekit:", "# Keep in mind that, this merged model isn't usually tested at the moment, which could benefit in vocabulary error.\n* Kaoeiri/Keiana-L3-Test5.4-8B-10\n* Undi95/Llama-3-LewdPlay-8B\n* Kaoeiri/Keiana-L3-Test4.7-8B-3", "## Configuration", "## Usage" ]

[ "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" ]

[ "transformers", "pytorch", "tensorboard", "deberta-v2", "token-classification", "generated_from_trainer", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15", "### Training results", "### Framework versions\n\n\n* Transformers 4.30.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #tensorboard #deberta-v2 #token-classification #generated_from_trainer #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 3e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 32\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 15", "### Training results", "### Framework versions\n\n\n* Transformers 4.30.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.13.3" ]

[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "en", "ko", "base_model:meta-llama/Meta-Llama-3-8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en", "ko" ]

[ "# acidsound/Bllossom-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'MLP-KTLim/Bllossom' 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#transformers #gguf #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B #license-apache-2.0 #endpoints_compatible #region-us \n", "# acidsound/Bllossom-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'MLP-KTLim/Bllossom' 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_4096_512_27M", "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_4096_512_27M #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", "mergekit", "merge", "conversational", "arxiv:2403.19522", "base_model:ResplendentAI/Aura_Uncensored_l3_8B", "base_model:vicgalle/Roleplay-Llama-3-8B", "base_model:Undi95/Llama-3-LewdPlay-8B-evo", "base_model:abhishek/autotrain-llama3-orpo", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2403.19522" ]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using ResplendentAI/Aura_Uncensored_l3_8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* vicgalle/Roleplay-Llama-3-8B\n* Undi95/Llama-3-LewdPlay-8B-evo\n* abhishek/autotrain-llama3-orpo", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2403.19522 #base_model-ResplendentAI/Aura_Uncensored_l3_8B #base_model-vicgalle/Roleplay-Llama-3-8B #base_model-Undi95/Llama-3-LewdPlay-8B-evo #base_model-abhishek/autotrain-llama3-orpo #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the Model Stock merge method using ResplendentAI/Aura_Uncensored_l3_8B as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* vicgalle/Roleplay-Llama-3-8B\n* Undi95/Llama-3-LewdPlay-8B-evo\n* abhishek/autotrain-llama3-orpo", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "tf", "distilbert", "question-answering", "generated_from_keras_callback", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'Adam', 'weight\\_decay': None, 'clipnorm': None, 'global\\_clipnorm': None, 'clipvalue': None, 'use\\_ema': False, 'ema\\_momentum': 0.99, 'ema\\_overwrite\\_frequency': None, 'jit\\_compile': True, 'is\\_legacy\\_optimizer': False, 'learning\\_rate': {'module': 'keras.optimizers.schedules', 'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 2e-05, 'decay\\_steps': 436, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\\_name': None}, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}\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 #distilbert #question-answering #generated_from_keras_callback #base_model-distilbert/distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* optimizer: {'name': 'Adam', 'weight\\_decay': None, 'clipnorm': None, 'global\\_clipnorm': None, 'clipvalue': None, 'use\\_ema': False, 'ema\\_momentum': 0.99, 'ema\\_overwrite\\_frequency': None, 'jit\\_compile': True, 'is\\_legacy\\_optimizer': False, 'learning\\_rate': {'module': 'keras.optimizers.schedules', 'class\\_name': 'PolynomialDecay', 'config': {'initial\\_learning\\_rate': 2e-05, 'decay\\_steps': 436, 'end\\_learning\\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\\_name': None}, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}\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" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:t5-small", "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: 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* num\\_epochs: 4\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-t5-small #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: 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* num\\_epochs: 4\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", "qwen2", "text-generation", "chat", "qwen", "gptq", "int8", "8bits", "110b", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[ "en" ]

[ "# Qwen1.5-110B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: \n\n* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in human preference for chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.\n<br>", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.", "## Training details\nWe pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #chat #qwen #gptq #int8 #8bits #110b #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# Qwen1.5-110B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: \n\n* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in human preference for chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.\n<br>", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.", "## Training details\nWe pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:unsloth/mistral-7b-instruct-v0.2-bnb-4bit", "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 0.9.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-unsloth/mistral-7b-instruct-v0.2-bnb-4bit #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 0.9.0" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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", "gemma", "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 #gemma #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_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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", "qwen2", "text-generation", "qwen", "32b", "gptq", "int8", "chat", "conversational", "en", "zh", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[ "en", "zh" ]

[ "# Qwen1.5-32B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: \n\n* 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in human preference for chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.\n<br>", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention.", "## Training details\nWe pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #qwen #32b #gptq #int8 #chat #conversational #en #zh #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# Qwen1.5-32B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: \n\n* 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B and 72B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in human preference for chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.\n<br>", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B) and the mixture of SWA and full attention.", "## Training details\nWe pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "transformers", "safetensors", "llama", "text-generation", "llama-factory", "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 #llama-factory #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" ]

[ "diffusers", "text-to-image", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]

[]

[]

[ "# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.7.2\n\n<Gallery />", "## Model description\n\nThese are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.7.2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of\ngenerating images for the Critical Dream\nproject.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: True.\n\nSpecial VAE used for training: stabilityai/sdxl-vae.", "## Trigger words\n\nYou should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\" 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.", "## Tracker run link\n\nURL", "## 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 #text-to-image #stable-diffusion-xl #stable-diffusion-xl-diffusers #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-openrail++ #region-us \n", "# Critical Dream - cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.7.2\n\n<Gallery />", "## Model description\n\nThese are cosmicBboy/stable-diffusion-xl-base-1.0-lora-dreambooth-critdream-v0.7.2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0, for the purposes of\ngenerating images for the Critical Dream\nproject.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: True.\n\nSpecial VAE used for training: stabilityai/sdxl-vae.", "## Trigger words\n\nYou should use a picture of [dm-matt-mercer], a dungeon master. background is a forest. fantasy art style, high quality, highly detailed, sharp focus\" 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.", "## Tracker run link\n\nURL", "## 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]" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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" ]

[ "safetensors", "generated_from_trainer", "base_model:HuggingFaceM4/idefics2-8b", "license:apache-2.0", "region:us" ]

[]

[]

[ "# idefics2-8b-docvqa-finetuned-tutorial\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown 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: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 50\n- num_epochs: 2\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#safetensors #generated_from_trainer #base_model-HuggingFaceM4/idefics2-8b #license-apache-2.0 #region-us \n", "# idefics2-8b-docvqa-finetuned-tutorial\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown 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: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 50\n- num_epochs: 2\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-bert-base-uncased #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* 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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.41.0.dev0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "tensorboard", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "orpo", "generated_from_trainer", "conversational", "dataset:orpo-explorers/OHP-15k-Stratified-1", "base_model:orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch\n\nThis model is a fine-tuned version of orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch on the orpo-explorers/OHP-15k-Stratified-1 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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 64\n- total_eval_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 2", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2.post303\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #tensorboard #safetensors #mistral #text-generation #alignment-handbook #trl #orpo #generated_from_trainer #conversational #dataset-orpo-explorers/OHP-15k-Stratified-1 #base_model-orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch\n\nThis model is a fine-tuned version of orpo-explorers/kaist-mistral-orpo-capybara-beta-0.05-1epoch on the orpo-explorers/OHP-15k-Stratified-1 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-06\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 4\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 64\n- total_eval_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- num_epochs: 2", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.1.2.post303\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "mamba", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Model Card for Model ID\n\nFine-tuning for CS5242 project", "## Model Details", "### Model Description\n\n\n\n- Developed by: [DreamOnRain]\n- Finetuned from model [optional]: state-spaces/mamba-1.4b-hf", "### Model Sources [optional]\n\n\n\n- Repository: URL", "## Training Details", "### Training Data\n\n\n\nURL" ]

[ "TAGS\n#transformers #safetensors #mamba #text-generation #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID\n\nFine-tuning for CS5242 project", "## Model Details", "### Model Description\n\n\n\n- Developed by: [DreamOnRain]\n- Finetuned from model [optional]: state-spaces/mamba-1.4b-hf", "### Model Sources [optional]\n\n\n\n- Repository: URL", "## Training Details", "### Training Data\n\n\n\nURL" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:google/flan-t5-base", "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: 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* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-google/flan-t5-base #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: 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* num\\_epochs: 5", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B", "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 0.7.2.dev0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B #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 0.7.2.dev0" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B", "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 0.7.2.dev0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B #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 0.7.2.dev0" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B", "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 0.7.2.dev0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B #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 0.7.2.dev0" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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", "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" ]

[ "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" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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", "Translation", "Mistral", "English", "Spanish", "en", "es", "dataset:Thermostatic/ShareGPT_NeuralTranslate_v0.1", "arxiv:1910.09700", "license:mit", "region:us" ]

[ "1910.09700" ]

[ "en", "es" ]

[ "# Model Card for NeuralTranslate\n\n\n\nTHIS MODEL USES CHATML TEMPLATE!! BE CAREFUL OR YOU MIGHT FIND UNEXPECTED BEHAVIOURS.\n\nThis is the second alpha version of NeuralTranslate. This alpha version doesn't contain overfitting (or at least that's what I think), so no unexpected behaviour should happen and Mistral's native reasoning capabilities aren't lost.\n\nNeuralTranslate is an open-source family of models for bidirectional translation between English & Spanish, achieving high accuracy at fast speed.\n\nYou can donate towards this project at my ko-fi! URL", "## 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" ]

[ "TAGS\n#gguf #Translation #Mistral #English #Spanish #en #es #dataset-Thermostatic/ShareGPT_NeuralTranslate_v0.1 #arxiv-1910.09700 #license-mit #region-us \n", "# Model Card for NeuralTranslate\n\n\n\nTHIS MODEL USES CHATML TEMPLATE!! BE CAREFUL OR YOU MIGHT FIND UNEXPECTED BEHAVIOURS.\n\nThis is the second alpha version of NeuralTranslate. This alpha version doesn't contain overfitting (or at least that's what I think), so no unexpected behaviour should happen and Mistral's native reasoning capabilities aren't lost.\n\nNeuralTranslate is an open-source family of models for bidirectional translation between English & Spanish, achieving high accuracy at fast speed.\n\nYou can donate towards this project at my ko-fi! URL", "## 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" ]

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "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 #stablelm #text-generation #conversational #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" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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", "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", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:google/gemma-2b", "license:gemma", "region:us" ]

[]

[]

[ "# gemma2b-dolly15k-r128\n\nThis model is a fine-tuned version of google/gemma-2b on an unknown 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: 1\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: 100\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-google/gemma-2b #license-gemma #region-us \n", "# gemma2b-dolly15k-r128\n\nThis model is a fine-tuned version of google/gemma-2b on an unknown 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: 1\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: 100\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:n00854180t/ErisMaidFlame-7B", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #mergekit #merge #en #base_model-n00854180t/ErisMaidFlame-7B #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "qwen2", "text-generation", "chat", "qwen", "gptq", "int4", "4bits", "110b", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[ "en" ]

[ "# Qwen1.5-110B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: \n\n* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in human preference for chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.\n<br>", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.", "## Training details\nWe pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #chat #qwen #gptq #int4 #4bits #110b #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Qwen1.5-110B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nQwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previous released Qwen, the improvements include: \n\n* 9 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, 72B, and 110B dense models, and an MoE model of 14B with 2.7B activated;\n* Significant performance improvement in human preference for chat models;\n* Multilingual support of both base and chat models;\n* Stable support of 32K context length for models of all sizes\n* No need of 'trust_remote_code'.\n\nFor more details, please refer to our blog post and GitHub repo.\n<br>", "## Model Details\nQwen1.5 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily we did not include GQA (except for 32B and 110B) and the mixture of SWA and full attention.", "## Training details\nWe pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "transformers", "safetensors", "mixtral", "text-generation", "merge", "mergekit", "moe", "frankenmoe", "abacusai/Llama-3-Smaug-8B", "cognitivecomputations/dolphin-2.9-llama3-8b", "Weyaxi/Einstein-v6.1-Llama3-8B", "dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2", "base_model:abacusai/Llama-3-Smaug-8B", "base_model:cognitivecomputations/dolphin-2.9-llama3-8b", "base_model:Weyaxi/Einstein-v6.1-Llama3-8B", "base_model:dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Skyro-4X8B\nSkyro-4X8B is a Mixure of Experts (MoE) made with the following models using Mergekit:\n\n* abacusai/Llama-3-Smaug-8B\n* cognitivecomputations/dolphin-2.9-llama3-8b\n* Weyaxi/Einstein-v6.1-Llama3-8B\n* dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2", "## Configuration", "## Usage", "## Sample output" ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #merge #mergekit #moe #frankenmoe #abacusai/Llama-3-Smaug-8B #cognitivecomputations/dolphin-2.9-llama3-8b #Weyaxi/Einstein-v6.1-Llama3-8B #dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2 #base_model-abacusai/Llama-3-Smaug-8B #base_model-cognitivecomputations/dolphin-2.9-llama3-8b #base_model-Weyaxi/Einstein-v6.1-Llama3-8B #base_model-dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Skyro-4X8B\nSkyro-4X8B is a Mixure of Experts (MoE) made with the following models using Mergekit:\n\n* abacusai/Llama-3-Smaug-8B\n* cognitivecomputations/dolphin-2.9-llama3-8b\n* Weyaxi/Einstein-v6.1-Llama3-8B\n* dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2", "## Configuration", "## Usage", "## Sample output" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_27M", "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_4096_512_27M #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_4096_512_27M", "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_4096_512_27M #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_4096_512_46M", "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_4096_512_46M #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", "xlm-roberta", "feature-extraction", "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 #xlm-roberta #feature-extraction #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", "llama-3", "llama", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "en", "base_model:aaditya/OpenBioLLM-Llama3-8B", "license:llama3", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #llama-3 #llama #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #en #base_model-aaditya/OpenBioLLM-Llama3-8B #license-llama3 #endpoints_compatible #region-us \n" ]

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_4096_512_46M", "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_4096_512_46M #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_4096_512_46M", "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_4096_512_46M #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_4096_512_46M", "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_4096_512_46M #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", "qwen2", "text-generation", "codeqwen", "code", "chat", "gptq", "int4", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[ "en" ]

[ "# CodeQwen1.5-7B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance on text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #codeqwen #code #chat #gptq #int4 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# CodeQwen1.5-7B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance on text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "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", "transformer", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "4-bit", "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 #transformer #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-Instruct-v0.2 #4-bit #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", "qwen2", "text-generation", "chat", "gptq", "codeqwen", "int8", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[ "en" ]

[ "# CodeQwen1.5-7B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance on text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "TAGS\n#transformers #safetensors #qwen2 #text-generation #chat #gptq #codeqwen #int8 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "# CodeQwen1.5-7B-Chat", "## About Quantization\n我们使用modelscope swift仓库进行GPTQ量化. 量化文档可以查看这里. 量化命令如下:\n\nWe use the modelscope swift repository to perform GPTQ quantization. Quantization documentation can be found here. The quantization command is as follows:", "## Introduction\n\nCodeQwen1.5 is the Code-Specific version of Qwen1.5. It is a transformer-based decoder-only language model pretrained on a large amount of data of codes. \n\n* Strong code generation capabilities and competitve performance across a series of benchmarks;\n* Supporting long context understanding and generation with the context length of 64K tokens;\n* Supporting 92 coding languages\n* Excellent performance on text-to-SQL, bug fix, etc.\n\n\nFor more details, please refer to our blog post and GitHub repo.", "## Model Details\nCodeQwen1.5 is based on Qwen1.5, a language model series including decoder language models of different model sizes. It is trained on 3 trillion tokens of data of codes, and it includes group query attention (GQA) for efficient inference.", "## Requirements\nThe code of Qwen1.5 has been in the latest Hugging face transformers and we advise you to install 'transformers>=4.37.0', or you might encounter the following error:", "## Quickstart\n\nHere provides a code snippet with 'apply_chat_template' to show you how to load the tokenizer and model and how to generate contents.", "## Tips\n\n* If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in 'generation_config.json'.\n\n\nIf you find our work helpful, feel free to give us a cite." ]

[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:google/vit-base-patch16-224-in21k", "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: 0.0002\n* train\\_batch\\_size: 32\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* num\\_epochs: 15", "### 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 #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-google/vit-base-patch16-224-in21k #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: 0.0002\n* train\\_batch\\_size: 32\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* num\\_epochs: 15", "### 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", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# distilbert-rotten_tomatoes\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown 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: 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- num_epochs: 2", "### Training results", "### Framework versions\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 #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# distilbert-rotten_tomatoes\n\nThis model is a fine-tuned version of distilbert-base-uncased on an unknown 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: 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- num_epochs: 2", "### Training results", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "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" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: kchopra04\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-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 #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Uploaded model\n\n- Developed by: kchopra04\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:salangarica/BioMistral-LLM", "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: constant\n* lr\\_scheduler\\_warmup\\_ratio: 0.03\n* num\\_epochs: 20.0", "### Training results", "### Framework versions\n\n\n* PEFT 0.8.2\n* Transformers 4.38.1\n* Pytorch 2.0.0\n* Datasets 2.15.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-salangarica/BioMistral-LLM #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: constant\n* lr\\_scheduler\\_warmup\\_ratio: 0.03\n* num\\_epochs: 20.0", "### Training results", "### Framework versions\n\n\n* PEFT 0.8.2\n* Transformers 4.38.1\n* Pytorch 2.0.0\n* Datasets 2.15.0\n* Tokenizers 0.15.2" ]

[ "peft", "safetensors", "base_model:unsloth/gemma-7b-bnb-4bit", "region:us" ]

[]

[]

[ "### Framework versions\n\n- PEFT 0.10.0" ]

[ "TAGS\n#peft #safetensors #base_model-unsloth/gemma-7b-bnb-4bit #region-us \n", "### Framework versions\n\n- PEFT 0.10.0" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: kchopra04\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-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 #pytorch #llama #text-generation #text-generation-inference #unsloth #trl #conversational #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: kchopra04\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "merge", "mergekit", "lazymergekit", "automerger", "license:apache-2.0", "region:us" ]

[]

[]

[ "# Ognoexperiment27multi_verse_modelMeliodas-7B\n\nOgnoexperiment27multi_verse_modelMeliodas-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

[ "TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n", "# Ognoexperiment27multi_verse_modelMeliodas-7B\n\nOgnoexperiment27multi_verse_modelMeliodas-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]