Datasets:

---

ftopal

/

huggingface-models

like 0

[ "ml-agents", "tensorboard", "onnx", "SnowballTarget", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SnowballTarget", "region:us" ]

[]

[]

[ "# ppo Agent playing SnowballTarget\n This is a trained model of a ppo agent playing SnowballTarget\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: ed-butcher/ppo-SnowballTarget\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #SnowballTarget #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SnowballTarget #region-us \n", "# ppo Agent playing SnowballTarget\n This is a trained model of a ppo agent playing SnowballTarget\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: ed-butcher/ppo-SnowballTarget\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

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

[ "1910.09700" ]

[]

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

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

[ "diffusers", "text-to-image", "lora", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers", "base_model:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]

[]

[]

[ "# LoRA DreamBooth - abdd68/output\n\nThese are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using DreamBooth. You can find some example images in the following. \n\n!img_0\n!img_1\n!img_2\n!img_3\n\n\nLoRA for the text encoder was enabled: False.", "## 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 #lora #diffusers-training #stable-diffusion #stable-diffusion-diffusers #base_model-runwayml/stable-diffusion-v1-5 #license-creativeml-openrail-m #region-us \n", "# LoRA DreamBooth - abdd68/output\n\nThese are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of sks dog using DreamBooth. You can find some example images in the following. \n\n!img_0\n!img_1\n!img_2\n!img_3\n\n\nLoRA for the text encoder was enabled: False.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "pt", "dataset:adalbertojunior/dolphin_pt_test", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "pt" ]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #pt #dataset-adalbertojunior/dolphin_pt_test #model-index #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #hubert #audio-classification #generated_from_trainer #dataset-marsyas/gtzan #base_model-ntu-spml/distilhubert #license-apache-2.0 #model-index #endpoints_compatible #has_space #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "gguf", "math", "semantic", "extraction", "graph", "relations", "science", "synthetic", "text-generation", "en", "dataset:DehydratedWater42/semantic_relations_extraction", "license:llama2", "region:us" ]

[]

[ "en" ]

[ "# SeELLama (Semantic Extraction LLama)\nModel is based on LLama2-7b and fine-tuned with the 'DehydratedWater42/semantic_relations_extraction' dataset.\n\nThe purpose of this model is to extract semantic relations from text in a structured way.", "#### Simplified Example:\n- Initial Text: \"While there is beautiful weather outside the building, from the window we can see a car. And what's the most annoying, pigeons love to sit on that car.\"\n- Entities: [\"pigeon\", \"car\", \"building\"]\n- Relations between entities: {\"pigeon -> car\": \"pigeon sits on the car\", \"car -> building\": \"car is parked outside the building\"}\n\nNote: The text example above is too short for the actual model; please use at least 500-token text segments for extraction to avoid hallucinations.", "### Other versions:\n- Get SeELLama as Safetensors: DehydratedWater42/SeELLama\n- Get SeELLama as adapter: DehydratedWater42/SeELLama-qlora-adapter\n\n*", "## How to use it:", "### Template:\nUse the prompt template provided below to extract relations from text. Replace '<<your_text_for_extraction>>' with your selected text, ideally between 500-1500 tokens, \nwith an optimal range of about 800-1000 tokens. You can adjust the temperature between 0.3 and 1.0; a good starting point is between 0.6 and 0.7. \nTemperatures below 0.3 may lead to never ending 'section_description'. The higher the temperature, the more the model will fill in the gaps in the provided text. \nIt was fine-tuned on scientific articles, so it will supplement missing information with general knowledge. \nModel was trained on 2560 context lenght where 1000-1500 tokens where used as input text.\n\n\nThe 'JSON' opening is not necessary but it improves stability. Remember to use double '{{' instead of singular '{' if you are using LangChain prompts with fstring formatting.", "### Quantized versions:\n\n- 'q2_k': Uses Q4_K for the URL and feed_forward.w2 tensors, Q2_K for the other tensors.\n- 'q3_k_l': Uses Q5_K for the URL, URL, and feed_forward.w2 tensors, else Q3_K\n- 'q3_k_m': Uses Q4_K for the URL, URL, and feed_forward.w2 tensors, else Q3_K\n- 'q3_k_s': Uses Q3_K for all tensors\n- 'q4_0': Original quant method, 4-bit.\n- 'q4_1': Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.\n- 'q4_k_m': Uses Q6_K for half of the URL and feed_forward.w2 tensors, else Q4_K\n- 'q4_k_s': Uses Q4_K for all tensors\n- 'q5_0': Higher accuracy, higher resource usage and slower inference.\n- 'q5_1': Even higher accuracy, resource usage and slower inference.\n- 'q5_k_m': Uses Q6_K for half of the URL and feed_forward.w2 tensors, else Q5_K\n- 'q5_k_s': Uses Q5_K for all tensors\n- 'q6_k': Uses Q8_K for all tensors\n- 'q8_0': Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.", "### Starter code", "### Extract generated json", "### Example:\nExtracting information from Minecraft Wiki.", "#### Initial template", "#### Result (about game):", "### Smaller example (About crafting)", "### Dopamine example", "### Longer example (dirt block)" ]

[ "TAGS\n#transformers #gguf #math #semantic #extraction #graph #relations #science #synthetic #text-generation #en #dataset-DehydratedWater42/semantic_relations_extraction #license-llama2 #region-us \n", "# SeELLama (Semantic Extraction LLama)\nModel is based on LLama2-7b and fine-tuned with the 'DehydratedWater42/semantic_relations_extraction' dataset.\n\nThe purpose of this model is to extract semantic relations from text in a structured way.", "#### Simplified Example:\n- Initial Text: \"While there is beautiful weather outside the building, from the window we can see a car. And what's the most annoying, pigeons love to sit on that car.\"\n- Entities: [\"pigeon\", \"car\", \"building\"]\n- Relations between entities: {\"pigeon -> car\": \"pigeon sits on the car\", \"car -> building\": \"car is parked outside the building\"}\n\nNote: The text example above is too short for the actual model; please use at least 500-token text segments for extraction to avoid hallucinations.", "### Other versions:\n- Get SeELLama as Safetensors: DehydratedWater42/SeELLama\n- Get SeELLama as adapter: DehydratedWater42/SeELLama-qlora-adapter\n\n*", "## How to use it:", "### Template:\nUse the prompt template provided below to extract relations from text. Replace '<<your_text_for_extraction>>' with your selected text, ideally between 500-1500 tokens, \nwith an optimal range of about 800-1000 tokens. You can adjust the temperature between 0.3 and 1.0; a good starting point is between 0.6 and 0.7. \nTemperatures below 0.3 may lead to never ending 'section_description'. The higher the temperature, the more the model will fill in the gaps in the provided text. \nIt was fine-tuned on scientific articles, so it will supplement missing information with general knowledge. \nModel was trained on 2560 context lenght where 1000-1500 tokens where used as input text.\n\n\nThe 'JSON' opening is not necessary but it improves stability. Remember to use double '{{' instead of singular '{' if you are using LangChain prompts with fstring formatting.", "### Quantized versions:\n\n- 'q2_k': Uses Q4_K for the URL and feed_forward.w2 tensors, Q2_K for the other tensors.\n- 'q3_k_l': Uses Q5_K for the URL, URL, and feed_forward.w2 tensors, else Q3_K\n- 'q3_k_m': Uses Q4_K for the URL, URL, and feed_forward.w2 tensors, else Q3_K\n- 'q3_k_s': Uses Q3_K for all tensors\n- 'q4_0': Original quant method, 4-bit.\n- 'q4_1': Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.\n- 'q4_k_m': Uses Q6_K for half of the URL and feed_forward.w2 tensors, else Q4_K\n- 'q4_k_s': Uses Q4_K for all tensors\n- 'q5_0': Higher accuracy, higher resource usage and slower inference.\n- 'q5_1': Even higher accuracy, resource usage and slower inference.\n- 'q5_k_m': Uses Q6_K for half of the URL and feed_forward.w2 tensors, else Q5_K\n- 'q5_k_s': Uses Q5_K for all tensors\n- 'q6_k': Uses Q8_K for all tensors\n- 'q8_0': Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.", "### Starter code", "### Extract generated json", "### Example:\nExtracting information from Minecraft Wiki.", "#### Initial template", "#### Result (about game):", "### Smaller example (About crafting)", "### Dopamine example", "### Longer example (dirt block)" ]

[ "transformers", "safetensors", "mistral", "text-generation", "mergekit", "merge", "alpaca", "not-for-all-audiences", "nsfw", "conversational", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# IceCoffeeRP-7b-4.2bpw-exl2\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* G:\\FModels\\IceCoffeeTest10\n* G:\\FModels\\IceCoffeeTest5", "### Configuration\n\nThe following YAML configuration was used to produce this model:", "## How to download From the command line\n\nI recommend using the 'huggingface-hub' Python library:\n\n\n\nTo download the 'main' branch to a folder called 'IceCoffeeRP-7b-4.2bpw-exl2':\n\n\n\n<details>\n <summary>More advanced huggingface-cli download usage</summary>\n\nIf you remove the '--local-dir-use-symlinks False' parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: '~/.cache/huggingface'), and symlinks will be added to the specified '--local-dir', pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.\n\nThe cache location can be changed with the 'HF_HOME' environment variable, and/or the '--cache-dir' parameter to 'huggingface-cli'.\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf_transfer':\n\n\n\nAnd set environment variable 'HF_HUB_ENABLE_HF_TRANSFER' to '1':\n\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF_HUB_ENABLE_HF_TRANSFER=1' before the download command.\n</details>" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #alpaca #not-for-all-audiences #nsfw #conversational #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# IceCoffeeRP-7b-4.2bpw-exl2\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* G:\\FModels\\IceCoffeeTest10\n* G:\\FModels\\IceCoffeeTest5", "### Configuration\n\nThe following YAML configuration was used to produce this model:", "## How to download From the command line\n\nI recommend using the 'huggingface-hub' Python library:\n\n\n\nTo download the 'main' branch to a folder called 'IceCoffeeRP-7b-4.2bpw-exl2':\n\n\n\n<details>\n <summary>More advanced huggingface-cli download usage</summary>\n\nIf you remove the '--local-dir-use-symlinks False' parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: '~/.cache/huggingface'), and symlinks will be added to the specified '--local-dir', pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.\n\nThe cache location can be changed with the 'HF_HOME' environment variable, and/or the '--cache-dir' parameter to 'huggingface-cli'.\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf_transfer':\n\n\n\nAnd set environment variable 'HF_HUB_ENABLE_HF_TRANSFER' to '1':\n\n\n\nWindows Command Line users: You can set the environment variable by running 'set HF_HUB_ENABLE_HF_TRANSFER=1' before the download command.\n</details>" ]

[ "transformers", "pytorch", "safetensors", "mistral", "text-generation", "conversational", "base_model:teknium/Hermes-Trismegistus-Mistral-7B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #pytorch #safetensors #mistral #text-generation #conversational #base_model-teknium/Hermes-Trismegistus-Mistral-7B #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.01_4iters_bs256_nodpo_only4w_iter_2\n\nThis model is a fine-tuned version of ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.01_4iters_bs256_nodpo_only4w_iter_2\n\nThis model is a fine-tuned version of ShenaoZhang/0.01_4iters_bs256_nodpo_only4w_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "peft", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-v0.1", "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 #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-v0.1 #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", "llama", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Experto-4X8B-untrained\n\nExperto-4X8B-untrained is a merge of the following models using mergoo:\n* meta-llama/Meta-Llama-3-8B\n* cognitivecomputations/dolphin-2.9-llama3-8b\n* abacusai/Llama-3-Smaug-8B\n* Weyaxi/Einstein-v6.1-Llama3-8B\n* dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2", "## Configuration\n\n\n\nWARNING: This model needs further training to train the router layers" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Experto-4X8B-untrained\n\nExperto-4X8B-untrained is a merge of the following models using mergoo:\n* meta-llama/Meta-Llama-3-8B\n* cognitivecomputations/dolphin-2.9-llama3-8b\n* abacusai/Llama-3-Smaug-8B\n* Weyaxi/Einstein-v6.1-Llama3-8B\n* dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2", "## Configuration\n\n\n\nWARNING: This model needs further training to train the router layers" ]

[ "transformers", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "llama-cpp", "gguf-my-repo", "en", "dataset:tatsu-lab/alpaca", "base_model:unsloth/llama-3-8b-bnb-4bit", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# hus960/Llama-3-NeuralPaca-8b-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'NeuralNovel/Llama-3-NeuralPaca-8b' 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 #text-generation-inference #unsloth #llama #trl #llama-cpp #gguf-my-repo #en #dataset-tatsu-lab/alpaca #base_model-unsloth/llama-3-8b-bnb-4bit #endpoints_compatible #region-us \n", "# hus960/Llama-3-NeuralPaca-8b-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'NeuralNovel/Llama-3-NeuralPaca-8b' 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", "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: flyjin\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: flyjin\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\"/>" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "diffusers", "tensorboard", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "textual_inversion", "diffusers-training", "base_model:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

[]

[]

[ "# Textual inversion text2image fine-tuning - mrtuandao/textual_inversion_corgi\nThese are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #tensorboard #safetensors #stable-diffusion #stable-diffusion-diffusers #text-to-image #textual_inversion #diffusers-training #base_model-runwayml/stable-diffusion-v1-5 #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "# Textual inversion text2image fine-tuning - mrtuandao/textual_inversion_corgi\nThese are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

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

[ "1910.09700" ]

[]

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

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

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "summarization", "generated_from_trainer", "base_model:eenzeenee/t5-small-korean-summarization", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# t5-small-korean-summarization_JU_FineTune_AIHUB_Law\n\nThis model is a fine-tuned version of eenzeenee/t5-small-korean-summarization 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: 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- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #summarization #generated_from_trainer #base_model-eenzeenee/t5-small-korean-summarization #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# t5-small-korean-summarization_JU_FineTune_AIHUB_Law\n\nThis model is a fine-tuned version of eenzeenee/t5-small-korean-summarization 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: 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- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

[ "transformers", "tf", "bert", "text-classification", "generated_from_keras_callback", "base_model:bert-large-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* 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': False, 'is\\_legacy\\_optimizer': False, 'learning\\_rate': 2e-05, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* TensorFlow 2.15.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tf #bert #text-classification #generated_from_keras_callback #base_model-bert-large-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* 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': False, 'is\\_legacy\\_optimizer': False, 'learning\\_rate': 2e-05, 'beta\\_1': 0.9, 'beta\\_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}\n* training\\_precision: float32", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* TensorFlow 2.15.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "bert", "token-classification", "historical", "de", "la", "fr", "en", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "de", "la", "fr", "en" ]

[]

[ "TAGS\n#transformers #safetensors #bert #token-classification #historical #de #la #fr #en #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "saiga", "llama3", "adaround", "adaquant", "omniquant", "gptq", "triton", "conversational", "ru", "arxiv:2004.10568", "arxiv:2006.10518", "base_model:IlyaGusev/saiga_llama3_8b", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "2004.10568", "2006.10518" ]

[ "ru" ]

[ "### PPL (↓)", "### Accuracy on English Benchmarks, % (↑)", "### Accuracy on Russian Benchmarks, % (↑)", "### Summary\n\n\n\nExamples\n--------", "### Imports and Model Loading\n\n\n\nExpand", "### Inference", "### Inference Using Pipeline" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #saiga #llama3 #adaround #adaquant #omniquant #gptq #triton #conversational #ru #arxiv-2004.10568 #arxiv-2006.10518 #base_model-IlyaGusev/saiga_llama3_8b #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "### PPL (↓)", "### Accuracy on English Benchmarks, % (↑)", "### Accuracy on Russian Benchmarks, % (↑)", "### Summary\n\n\n\nExamples\n--------", "### Imports and Model Loading\n\n\n\nExpand", "### Inference", "### Inference Using Pipeline" ]

[ "transformers", "safetensors", "bert", "token-classification", "historical", "de", "la", "fr", "en", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "de", "la", "fr", "en" ]

[]

[ "TAGS\n#transformers #safetensors #bert #token-classification #historical #de #la #fr #en #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "transformers", "safetensors", "bert", "token-classification", "historical", "de", "la", "fr", "en", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "de", "la", "fr", "en" ]

[]

[ "TAGS\n#transformers #safetensors #bert #token-classification #historical #de #la #fr #en #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "transformers", "pytorch", "llama", "text-generation", "Human Preference Alignment", "large language models", "conversational", "en", "dataset:openbmb/UltraFeedback", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# Introduction\nMetaAligner-UltraFeedback-1.1B is part of the <em>MetaAligner</em> project, the first policy-agnostic and generalizable method for multi-objective preference alignment of large\nlanguage models. This model is finetuned based on the TinyLLaMA-1.1B foundation model and \nthe dynamic multi-objective dataset built from the openbmb/UltraFeedback dataset. UltraFeedback-MetaAligner is trained to align responses of another general AI assistant considering\na single-turn query, but the queries include professional questions such as programming language and\nhistory, and the aligned responses are usually more complicated.\nThe model is expected to perform multi-objective alignment\nefficiently, without tuning the policy models or accessing their parameters. <em>MetaAligner</em> also exerts zero-shot preference alignment\nfor unseen objectives. To our knowledge, this work marks the first attempt at generalizable multi-\nobjective preference alignment. Experimental results show that MetaAligner can simultaneously perform effective alignment for multiple unseen objectives\nwhile maintaining performance on aligned objectives.", "# Dataset\nThis model is trained based on the following released dataset:", "# Usage\nWith the Hugging Face Transformers library, you can use the MetaAligner-UltraFeedback-1.1B model in your Python project. Here is a simple example of how to load the model:\n\n\n\nIn this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The 'device_map='auto'' argument is used to automatically\nuse the GPU if it's available.\n\nYou can align any outputs obtained from other foundation models with your self-defined objectives. For example, we have the following query from UltraFeedback, \nunaligned output examples from LLaMA2-7B,\nand target objectives:\n\n\n\nTo ensure the best performance, use the following template to prompt <em>MetaAligner</em>:\n\n\nYou can obtain an aligned response using the following codes:\n\n\n\nOne inference of MetaAligner-UltraFeedback-1.1B on the above codes has the following response:", "## License\n\nMetaAligner-UltraFeedback-1.1B is licensed under MIT. For more details, please see the MIT file." ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #Human Preference Alignment #large language models #conversational #en #dataset-openbmb/UltraFeedback #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Introduction\nMetaAligner-UltraFeedback-1.1B is part of the <em>MetaAligner</em> project, the first policy-agnostic and generalizable method for multi-objective preference alignment of large\nlanguage models. This model is finetuned based on the TinyLLaMA-1.1B foundation model and \nthe dynamic multi-objective dataset built from the openbmb/UltraFeedback dataset. UltraFeedback-MetaAligner is trained to align responses of another general AI assistant considering\na single-turn query, but the queries include professional questions such as programming language and\nhistory, and the aligned responses are usually more complicated.\nThe model is expected to perform multi-objective alignment\nefficiently, without tuning the policy models or accessing their parameters. <em>MetaAligner</em> also exerts zero-shot preference alignment\nfor unseen objectives. To our knowledge, this work marks the first attempt at generalizable multi-\nobjective preference alignment. Experimental results show that MetaAligner can simultaneously perform effective alignment for multiple unseen objectives\nwhile maintaining performance on aligned objectives.", "# Dataset\nThis model is trained based on the following released dataset:", "# Usage\nWith the Hugging Face Transformers library, you can use the MetaAligner-UltraFeedback-1.1B model in your Python project. Here is a simple example of how to load the model:\n\n\n\nIn this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The 'device_map='auto'' argument is used to automatically\nuse the GPU if it's available.\n\nYou can align any outputs obtained from other foundation models with your self-defined objectives. For example, we have the following query from UltraFeedback, \nunaligned output examples from LLaMA2-7B,\nand target objectives:\n\n\n\nTo ensure the best performance, use the following template to prompt <em>MetaAligner</em>:\n\n\nYou can obtain an aligned response using the following codes:\n\n\n\nOne inference of MetaAligner-UltraFeedback-1.1B on the above codes has the following response:", "## License\n\nMetaAligner-UltraFeedback-1.1B is licensed under MIT. For more details, please see the MIT file." ]

[ "transformers", "safetensors", "bert", "token-classification", "historical", "de", "la", "fr", "en", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "de", "la", "fr", "en" ]

[]

[ "TAGS\n#transformers #safetensors #bert #token-classification #historical #de #la #fr #en #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "transformers", "pytorch", "llama", "text-generation", "Human Preference Alignment", "large language models", "conversational", "en", "dataset:openbmb/UltraFeedback", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# Introduction\nMetaAligner-UltraFeedback-7B is part of the <em>MetaAligner</em> project, the first policy-agnostic and generalizable method for multi-objective preference alignment of large\nlanguage models. This model is finetuned based on the Meta LLaMA2-7B foundation model and \nthe dynamic multi-objective dataset built from the openbmb/UltraFeedback dataset. UltraFeedback-MetaAligner is trained to align responses of another general AI assistant considering\na single-turn query, but the queries include professional questions such as programming language and\nhistory, and the aligned responses are usually more complicated.\nThe model is expected to perform multi-objective alignment\nefficiently, without tuning the policy models or accessing their parameters. <em>MetaAligner</em> also exerts zero-shot preference alignment\nfor unseen objectives. To our knowledge, this work marks the first attempt at generalizable multi-\nobjective preference alignment. Experimental results show that MetaAligner can simultaneously perform effective alignment for multiple unseen objectives\nwhile maintaining performance on aligned objectives.", "# Dataset\nThis model is trained based on the following released dataset:", "# Usage\nWith the Hugging Face Transformers library, you can use the MetaAligner-UltraFeedback-7B model in your Python project. Here is a simple example of how to load the model:\n\n\n\nIn this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The 'device_map='auto'' argument is used to automatically\nuse the GPU if it's available.\n\nYou can align any outputs obtained from other foundation models with your self-defined objectives. For example, we have the following query from UltraFeedback, \nunaligned output examples from LLaMA2-7B,\nand target objectives:\n\n\n\nTo ensure the best performance, use the following template to prompt <em>MetaAligner</em>:\n\n\nYou can obtain an aligned response using the following codes:\n\n\n\nOne inference of MetaAligner-UltraFeedback-7B on the above codes has the following response:", "## License\n\nMetaAligner-UltraFeedback-7B is licensed under MIT. For more details, please see the MIT file." ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #Human Preference Alignment #large language models #conversational #en #dataset-openbmb/UltraFeedback #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Introduction\nMetaAligner-UltraFeedback-7B is part of the <em>MetaAligner</em> project, the first policy-agnostic and generalizable method for multi-objective preference alignment of large\nlanguage models. This model is finetuned based on the Meta LLaMA2-7B foundation model and \nthe dynamic multi-objective dataset built from the openbmb/UltraFeedback dataset. UltraFeedback-MetaAligner is trained to align responses of another general AI assistant considering\na single-turn query, but the queries include professional questions such as programming language and\nhistory, and the aligned responses are usually more complicated.\nThe model is expected to perform multi-objective alignment\nefficiently, without tuning the policy models or accessing their parameters. <em>MetaAligner</em> also exerts zero-shot preference alignment\nfor unseen objectives. To our knowledge, this work marks the first attempt at generalizable multi-\nobjective preference alignment. Experimental results show that MetaAligner can simultaneously perform effective alignment for multiple unseen objectives\nwhile maintaining performance on aligned objectives.", "# Dataset\nThis model is trained based on the following released dataset:", "# Usage\nWith the Hugging Face Transformers library, you can use the MetaAligner-UltraFeedback-7B model in your Python project. Here is a simple example of how to load the model:\n\n\n\nIn this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The 'device_map='auto'' argument is used to automatically\nuse the GPU if it's available.\n\nYou can align any outputs obtained from other foundation models with your self-defined objectives. For example, we have the following query from UltraFeedback, \nunaligned output examples from LLaMA2-7B,\nand target objectives:\n\n\n\nTo ensure the best performance, use the following template to prompt <em>MetaAligner</em>:\n\n\nYou can obtain an aligned response using the following codes:\n\n\n\nOne inference of MetaAligner-UltraFeedback-7B on the above codes has the following response:", "## License\n\nMetaAligner-UltraFeedback-7B is licensed under MIT. For more details, please see the MIT file." ]

[ "transformers", "safetensors", "bert", "token-classification", "historical", "de", "la", "fr", "en", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "de", "la", "fr", "en" ]

[]

[ "TAGS\n#transformers #safetensors #bert #token-classification #historical #de #la #fr #en #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "transformers", "pytorch", "llama", "text-generation", "Human Preference Alignment", "large language models", "conversational", "en", "dataset:openbmb/UltraFeedback", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# Introduction\nMetaAligner-UltraFeedback-13B is part of the <em>MetaAligner</em> project, the first policy-agnostic and generalizable method for multi-objective preference alignment of large\nlanguage models. This model is finetuned based on the Meta LLaMA2-13B foundation model and \nthe dynamic multi-objective dataset built from the openbmb/UltraFeedback dataset. UltraFeedback-MetaAligner is trained to align responses of another general AI assistant considering\na single-turn query, but the queries include professional questions such as programming language and\nhistory, and the aligned responses are usually more complicated.\nThe model is expected to perform multi-objective alignment\nefficiently, without tuning the policy models or accessing their parameters. <em>MetaAligner</em> also exerts zero-shot preference alignment\nfor unseen objectives. To our knowledge, this work marks the first attempt at generalizable multi-\nobjective preference alignment. Experimental results show that MetaAligner can simultaneously perform effective alignment for multiple unseen objectives\nwhile maintaining performance on aligned objectives.", "# Dataset\nThis model is trained based on the following released dataset:", "# Usage\nWith the Hugging Face Transformers library, you can use the MetaAligner-UltraFeedback-13B model in your Python project. Here is a simple example of how to load the model:\n\n\n\nIn this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The 'device_map='auto'' argument is used to automatically\nuse the GPU if it's available.\n\nYou can align any outputs obtained from other foundation models with your self-defined objectives. For example, we have the following query from UltraFeedback, \nunaligned output examples from LLaMA2-7B,\nand target objectives:\n\n\n\nTo ensure the best performance, use the following template to prompt <em>MetaAligner</em>:\n\n\nYou can obtain an aligned response using the following codes:\n\n\n\nOne inference of MetaAligner-UltraFeedback-13B on the above codes has the following response:", "## License\n\nMetaAligner-UltraFeedback-13B is licensed under MIT. For more details, please see the MIT file." ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #Human Preference Alignment #large language models #conversational #en #dataset-openbmb/UltraFeedback #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Introduction\nMetaAligner-UltraFeedback-13B is part of the <em>MetaAligner</em> project, the first policy-agnostic and generalizable method for multi-objective preference alignment of large\nlanguage models. This model is finetuned based on the Meta LLaMA2-13B foundation model and \nthe dynamic multi-objective dataset built from the openbmb/UltraFeedback dataset. UltraFeedback-MetaAligner is trained to align responses of another general AI assistant considering\na single-turn query, but the queries include professional questions such as programming language and\nhistory, and the aligned responses are usually more complicated.\nThe model is expected to perform multi-objective alignment\nefficiently, without tuning the policy models or accessing their parameters. <em>MetaAligner</em> also exerts zero-shot preference alignment\nfor unseen objectives. To our knowledge, this work marks the first attempt at generalizable multi-\nobjective preference alignment. Experimental results show that MetaAligner can simultaneously perform effective alignment for multiple unseen objectives\nwhile maintaining performance on aligned objectives.", "# Dataset\nThis model is trained based on the following released dataset:", "# Usage\nWith the Hugging Face Transformers library, you can use the MetaAligner-UltraFeedback-13B model in your Python project. Here is a simple example of how to load the model:\n\n\n\nIn this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The 'device_map='auto'' argument is used to automatically\nuse the GPU if it's available.\n\nYou can align any outputs obtained from other foundation models with your self-defined objectives. For example, we have the following query from UltraFeedback, \nunaligned output examples from LLaMA2-7B,\nand target objectives:\n\n\n\nTo ensure the best performance, use the following template to prompt <em>MetaAligner</em>:\n\n\nYou can obtain an aligned response using the following codes:\n\n\n\nOne inference of MetaAligner-UltraFeedback-13B on the above codes has the following response:", "## License\n\nMetaAligner-UltraFeedback-13B is licensed under MIT. For more details, please see the MIT file." ]

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

[]

[]

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

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

[ "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-OHP-15k-Mathcode-2epoch", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# kaist-mistral-orpo-OHP-15k-Mathcode-2epoch-ohp-15k-strat-1-1epoch\n\nThis model is a fine-tuned version of orpo-explorers/kaist-mistral-orpo-OHP-15k-Mathcode-2epoch 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: 1", "### 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-OHP-15k-Mathcode-2epoch #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# kaist-mistral-orpo-OHP-15k-Mathcode-2epoch-ohp-15k-strat-1-1epoch\n\nThis model is a fine-tuned version of orpo-explorers/kaist-mistral-orpo-OHP-15k-Mathcode-2epoch 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: 1", "### 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", "mistral", "text-generation", "en", "sr", "hr", "bs", "arxiv:2309.09530", "arxiv:2403.19522", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2309.09530", "2403.19522" ]

[ "en", "sr", "hr", "bs" ]

[ "# Prodigy SM Base v0.1\n\n<img src=\"URL width=\"70%\" height=\"70%\">\n\nIn our latest endeavour, we performed continued pre-training of a large language model (Mistral-7b-v0.1) to understand and generate text in new languages, including Serbian, Bosnian and Croatian using an innovative approach. \n\nRather than depending only on extensive datasets in the target language, our method utilizes a more compact set of both synthetic and human-curated data along with some mixture of CC Web data, which is implemented in two strategic phases:\n\n1. Establishing a comprehensive demonstration of all grammatical and orthographic rules pertinent to the language.\n2. Supplying a diverse array of examples that not only reinforce these rules but also integrate a wide range of linguistic nuances.\n\nWhile our approach is uniquely tailored to our objectives, we have drawn some inspiration from recent advancements in language model training. Specifically, the conceptual strategies discussed in the paper ADAPTING LARGE LANGUAGE MODELS VIA READING COMPREHENSION provided valuable insights, though our methods diverge significantly in practice. By adopting this inspired approach, we aim to efficiently teach the model new languages with a balanced blend of accuracy and linguistic diversity.\n\nSo... Did it work?!", "# Yes!\nSee the benchmark results, or even better, download the model and try it yourself. As you know by now, there's no better benchmark than a quick 'try it yourself' vibe check. :)\n<img src=\"URL width=\"100%\" height=\"100%\">\n\nHere, we demonstrate results of benchmark that is not frequently performed, yet equally important: how adapting the model for a new language impacted its original English-only performance.\n<img src=\"URL width=\"100%\" height=\"100%\">\n\n*All evals are performed in zero shot manner. \n*Also bear in mind that llama-2-7b, llama-3-8b and mistral-7b models compared to Prodigy SM base aren't trained on extensive Serbian language datasets, and these benchmarks demonstrate that primarily English models can be adapted to other languages.\n\nSo, as you can see, we successfully improved the original model's performance for Serbian language use cases while retaining or even slightly improving its performance for English language.", "### Training results\nTraining results of continued pre-training of mistral-7b-v0.1\n\n<img src=\"URL width=\"70%\" height=\"70%\">\n<img src=\"URL width=\"70%\" height=\"70%\">\n\nAs last experimental step we merged produced model with Mistral-7B-v0.1 and two earlier checkpoints from prodigy-sm-base using Model Stock method.", "# Notes\nAs this is base model, there is no chat template or strict chat following capabilities, this model is best candidate for further pre-train on Serbian language as there is a lot more room for improvement (you can hit sweet spot), or next step in the pipeline, such as some form of chat or instruct tuning.\n\nIf you want model that is already instruction tuned we did that too, check Prodigy SM Instruct v0.1", "# Prodigy SM Instruct v0.1\n[prodigy-sm-instruct]() COMING SOON\n\nAnd stay tuned for: \n[prodigy-sm-base (llama-3)]() COMING SOON \n[prodigy-sm-instruct (llama-3)]() COMING SOON\n\n Also we are excited to announce that URL will soon launch an API platform featuring advanced Prodigy series of models, advanced AI tools and much more!", "# Thanks\n - gordicaleksa/serbian-llm-eval and his community for curating translations and adaptation of lm-evaluation-harness\nthat we used to perform benchmarks.\n - jondurbin for amazing airoboros framework\n - teknium for various insights shared on discord and twitter aka x.com\n - Eric for various insights shared on discord and twitter aka x.com\n - mergekit for model merging tools\n\n*Huge thanks to URL for generous DGX cloud credits* URL" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #en #sr #hr #bs #arxiv-2309.09530 #arxiv-2403.19522 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Prodigy SM Base v0.1\n\n<img src=\"URL width=\"70%\" height=\"70%\">\n\nIn our latest endeavour, we performed continued pre-training of a large language model (Mistral-7b-v0.1) to understand and generate text in new languages, including Serbian, Bosnian and Croatian using an innovative approach. \n\nRather than depending only on extensive datasets in the target language, our method utilizes a more compact set of both synthetic and human-curated data along with some mixture of CC Web data, which is implemented in two strategic phases:\n\n1. Establishing a comprehensive demonstration of all grammatical and orthographic rules pertinent to the language.\n2. Supplying a diverse array of examples that not only reinforce these rules but also integrate a wide range of linguistic nuances.\n\nWhile our approach is uniquely tailored to our objectives, we have drawn some inspiration from recent advancements in language model training. Specifically, the conceptual strategies discussed in the paper ADAPTING LARGE LANGUAGE MODELS VIA READING COMPREHENSION provided valuable insights, though our methods diverge significantly in practice. By adopting this inspired approach, we aim to efficiently teach the model new languages with a balanced blend of accuracy and linguistic diversity.\n\nSo... Did it work?!", "# Yes!\nSee the benchmark results, or even better, download the model and try it yourself. As you know by now, there's no better benchmark than a quick 'try it yourself' vibe check. :)\n<img src=\"URL width=\"100%\" height=\"100%\">\n\nHere, we demonstrate results of benchmark that is not frequently performed, yet equally important: how adapting the model for a new language impacted its original English-only performance.\n<img src=\"URL width=\"100%\" height=\"100%\">\n\n*All evals are performed in zero shot manner. \n*Also bear in mind that llama-2-7b, llama-3-8b and mistral-7b models compared to Prodigy SM base aren't trained on extensive Serbian language datasets, and these benchmarks demonstrate that primarily English models can be adapted to other languages.\n\nSo, as you can see, we successfully improved the original model's performance for Serbian language use cases while retaining or even slightly improving its performance for English language.", "### Training results\nTraining results of continued pre-training of mistral-7b-v0.1\n\n<img src=\"URL width=\"70%\" height=\"70%\">\n<img src=\"URL width=\"70%\" height=\"70%\">\n\nAs last experimental step we merged produced model with Mistral-7B-v0.1 and two earlier checkpoints from prodigy-sm-base using Model Stock method.", "# Notes\nAs this is base model, there is no chat template or strict chat following capabilities, this model is best candidate for further pre-train on Serbian language as there is a lot more room for improvement (you can hit sweet spot), or next step in the pipeline, such as some form of chat or instruct tuning.\n\nIf you want model that is already instruction tuned we did that too, check Prodigy SM Instruct v0.1", "# Prodigy SM Instruct v0.1\n[prodigy-sm-instruct]() COMING SOON\n\nAnd stay tuned for: \n[prodigy-sm-base (llama-3)]() COMING SOON \n[prodigy-sm-instruct (llama-3)]() COMING SOON\n\n Also we are excited to announce that URL will soon launch an API platform featuring advanced Prodigy series of models, advanced AI tools and much more!", "# Thanks\n - gordicaleksa/serbian-llm-eval and his community for curating translations and adaptation of lm-evaluation-harness\nthat we used to perform benchmarks.\n - jondurbin for amazing airoboros framework\n - teknium for various insights shared on discord and twitter aka x.com\n - Eric for various insights shared on discord and twitter aka x.com\n - mergekit for model merging tools\n\n*Huge thanks to URL for generous DGX cloud credits* URL" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #swinv2 #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swinv2-small-patch4-window16-256 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]

[]

[]

[ "# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: Unclad3610/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us \n", "# ppo Agent playing Huggy\n This is a trained model of a ppo agent playing Huggy\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: Unclad3610/ppo-Huggy\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "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" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "gguf", "merge", "mergekit", "lazymergekit", "llama-cpp", "gguf-my-repo", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[]

[ "# hus960/FrankenLlama-3-12B-Instruct-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'mlabonne/FrankenLlama-3-12B-Instruct' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #merge #mergekit #lazymergekit #llama-cpp #gguf-my-repo #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n", "# hus960/FrankenLlama-3-12B-Instruct-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'mlabonne/FrankenLlama-3-12B-Instruct' 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." ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "TAGS\n#FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 FrozenLake-v1\n This is a trained model of a Q-Learning agent playing FrozenLake-v1 .\n\n ## Usage" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "transformers", "safetensors", "gpt2", "text-generation", "en", "dataset:samsum", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# OpenAI GPT-2 Samsum", "## Model description\n\nThis model has been trained with the SAMSum dataset. The SAMSum dataset contains approximately 16,000 conversational dialogues accompanied by summaries. These conversations were created and written by linguists proficient in fluent English. Linguists were instructed to create conversations that reflect the ratio of topics found in real-life journalistic conversations similar to their daily written conversations. The style and tone vary; conversations can be informal, semi-formal, or formal, and may include slang terms, expressions, and spelling errors. Subsequently, the conversations were annotated with summaries. The summaries are expected to be concise summaries of what people were talking about during the conversation, written in the third person. The SAMSum dataset was prepared by the Samsung Research Institute Poland and is distributed for research purposes.", "## Training\n\nThis GPT-2 model is rated for an average of 1 hour with an L4 GPU.", "## Training Results\n\n!examples\nAuthors\n\n- Developed by: Anezatra\n- Model type: GPT2\n- Contacts: URL" ]

[ "TAGS\n#transformers #safetensors #gpt2 #text-generation #en #dataset-samsum #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# OpenAI GPT-2 Samsum", "## Model description\n\nThis model has been trained with the SAMSum dataset. The SAMSum dataset contains approximately 16,000 conversational dialogues accompanied by summaries. These conversations were created and written by linguists proficient in fluent English. Linguists were instructed to create conversations that reflect the ratio of topics found in real-life journalistic conversations similar to their daily written conversations. The style and tone vary; conversations can be informal, semi-formal, or formal, and may include slang terms, expressions, and spelling errors. Subsequently, the conversations were annotated with summaries. The summaries are expected to be concise summaries of what people were talking about during the conversation, written in the third person. The SAMSum dataset was prepared by the Samsung Research Institute Poland and is distributed for research purposes.", "## Training\n\nThis GPT-2 model is rated for an average of 1 hour with an L4 GPU.", "## Training Results\n\n!examples\nAuthors\n\n- Developed by: Anezatra\n- Model type: GPT2\n- Contacts: URL" ]

[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]

[]

[]

[ "# Model Card for Unit 1 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional image generation of cute .", "## Usage\n\n'''python\nfrom diffusers import DDPMPipeline\n\npipeline = DDPMPipeline.from_pretrained('ljw20180420/sd-class-butterflies-32')\nimage = pipeline().images[0]\nimage" ]

[ "TAGS\n#diffusers #safetensors #pytorch #unconditional-image-generation #diffusion-models-class #license-mit #diffusers-DDPMPipeline #region-us \n", "# Model Card for Unit 1 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional image generation of cute .", "## Usage\n\n'''python\nfrom diffusers import DDPMPipeline\n\npipeline = DDPMPipeline.from_pretrained('ljw20180420/sd-class-butterflies-32')\nimage = pipeline().images[0]\nimage" ]

[ "transformers", "safetensors", "llama", "text-generation", "dataset:kyujinpy/OpenOrca-KO", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Llama-3-Ko-OpenOrca", "## Model Details", "### Model Description\n\n\n\nOriginal model: beomi/Llama-3-Open-Ko-8B\n\nDataset: kyujinpy/OpenOrca-KO", "### Training details\n\nTraining: Axolotl을 이용해 LoRA-8bit로 4epoch 학습 시켰습니다.\n - sequence_len: 4096\n - bf16\n\n학습 시간: A6000x2, 6시간", "### Evaluation\n\n- 0 shot kobest\n| Tasks |n-shot| Metric |Value | |Stderr|\n|----------------|-----:|--------|-----:|---|------|\n|kobest_boolq | 0|acc |0.5021|± |0.0133|\n|kobest_copa | 0|acc |0.6920|± |0.0146|\n|kobest_hellaswag| 0|acc |0.4520|± |0.0223|\n|kobest_sentineg | 0|acc |0.7330|± |0.0222|\n|kobest_wic | 0|acc |0.4881|± |0.0141|\n\n\n- 5 shot kobest\n| Tasks |n-shot| Metric |Value | |Stderr|\n|----------------|-----:|--------|-----:|---|------|\n|kobest_boolq | 5|acc |0.7123|± |0.0121|\n|kobest_copa | 5|acc |0.7620|± |0.0135|\n|kobest_hellaswag| 5|acc |0.4780|± |0.0224|\n|kobest_sentineg | 5|acc |0.9446|± |0.0115|\n|kobest_wic | 5|acc |0.6103|± |0.0137|", "### License:\nURL" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #dataset-kyujinpy/OpenOrca-KO #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Llama-3-Ko-OpenOrca", "## Model Details", "### Model Description\n\n\n\nOriginal model: beomi/Llama-3-Open-Ko-8B\n\nDataset: kyujinpy/OpenOrca-KO", "### Training details\n\nTraining: Axolotl을 이용해 LoRA-8bit로 4epoch 학습 시켰습니다.\n - sequence_len: 4096\n - bf16\n\n학습 시간: A6000x2, 6시간", "### Evaluation\n\n- 0 shot kobest\n| Tasks |n-shot| Metric |Value | |Stderr|\n|----------------|-----:|--------|-----:|---|------|\n|kobest_boolq | 0|acc |0.5021|± |0.0133|\n|kobest_copa | 0|acc |0.6920|± |0.0146|\n|kobest_hellaswag| 0|acc |0.4520|± |0.0223|\n|kobest_sentineg | 0|acc |0.7330|± |0.0222|\n|kobest_wic | 0|acc |0.4881|± |0.0141|\n\n\n- 5 shot kobest\n| Tasks |n-shot| Metric |Value | |Stderr|\n|----------------|-----:|--------|-----:|---|------|\n|kobest_boolq | 5|acc |0.7123|± |0.0121|\n|kobest_copa | 5|acc |0.7620|± |0.0135|\n|kobest_hellaswag| 5|acc |0.4780|± |0.0224|\n|kobest_sentineg | 5|acc |0.9446|± |0.0115|\n|kobest_wic | 5|acc |0.6103|± |0.0137|", "### License:\nURL" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: ramixpe\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 #llama #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: ramixpe\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", "gguf", "llama-cpp", "gguf-my-repo", "license:other", "endpoints_compatible", "region:us" ]

[]

[]

[ "# hus960/Llama-3-13B-Instruct-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Replete-AI/Llama-3-13B-Instruct' 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 #license-other #endpoints_compatible #region-us \n", "# hus960/Llama-3-13B-Instruct-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Replete-AI/Llama-3-13B-Instruct' 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", "pytorch", "t5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #pytorch #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "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" ]

[ "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" ]

[ "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" ]

[ "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" ]

[ "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" ]

[ "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" ]

[ "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" ]

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

[]

[]

[ "## 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- Model type: Mamba\n- Language(s) (NLP): Japanese\n- Tokenizer: ku-nlp/gpt2-large-japanese-char\n- License: Model: Aptach 2.0, Tokenizer: CC-BY-SA\n\n- ## Run the model\n\n\n【LOCAL AI HACKATHON #001】240時間ハッカソンにおいてGPUをお借りしました。 \n\n関係者の方々に深く御礼申し上げます。\n\nメタデータラボ株式会社様\n【AI声づくり技術研究会】\nサーバー主：やなぎ(Yanagi)様 (@Yanagi_1112)\n【ローカルLLMに向き合う会】\nサーバー主：saldra(サルドラ)様 (@sald_ra)\nWitness様　(@i_witnessed_it)\n\nチームメンバー：\nhayashi,\nkzms,\nchatblanc,\nRyunosuke Ikeda" ]

[ "TAGS\n#transformers #safetensors #mamba #text-generation #autotrain_compatible #endpoints_compatible #region-us \n", "## 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- Model type: Mamba\n- Language(s) (NLP): Japanese\n- Tokenizer: ku-nlp/gpt2-large-japanese-char\n- License: Model: Aptach 2.0, Tokenizer: CC-BY-SA\n\n- ## Run the model\n\n\n【LOCAL AI HACKATHON #001】240時間ハッカソンにおいてGPUをお借りしました。 \n\n関係者の方々に深く御礼申し上げます。\n\nメタデータラボ株式会社様\n【AI声づくり技術研究会】\nサーバー主：やなぎ(Yanagi)様 (@Yanagi_1112)\n【ローカルLLMに向き合う会】\nサーバー主：saldra(サルドラ)様 (@sald_ra)\nWitness様　(@i_witnessed_it)\n\nチームメンバー：\nhayashi,\nkzms,\nchatblanc,\nRyunosuke Ikeda" ]

[ "transformers", "safetensors", "starcoder2", "text-generation", "conversational", "dataset:HuggingFaceH4/ultrafeedback_binarized", "dataset:HuggingFaceH4/orca_dpo_pairs", "arxiv:2311.07911", "arxiv:2402.19173", "base_model:HuggingFaceH4/starchat2-15b-sft-v0.1", "license:bigcode-openrail-m", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "2311.07911", "2402.19173" ]

[]

[ "### Model Description\n\n\n* Model type: A 16B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.\n* Language(s) (NLP): Primarily English and 600+ programming languages.\n* License: BigCode Open RAIL-M v1\n* Finetuned from model: bigcode/starcoder2-15b", "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nPerformance\n-----------\n\n\nStarChat2 15B was trained to balance chat and programming capabilities. It achieves strong performance on chat benchmarks like MT Bench and IFEval, as well as the canonical HumanEval benchmark for Python code completion. The scores reported below were obtained using the LightEval evaluation suite (commit '988959cb905df4baa050f82b4d499d46e8b537f2') and each prompt has been formatted with the model's corresponding chat template to simulate real-world usage. This is why some scores may differ from those reported in technical reports or on the Open LLM Leaderboard.\n\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was fine-tuned on a blend of chat, code, math, and reasoning datasets. As a result, the model can be used for chat and you can check out our demo to test its coding capabilities.\n\n\nHere's how you can run the model using the 'pipeline()' function from Transformers:\n\n\nBias, Risks, and Limitations\n----------------------------\n\n\nStarChat2 15B has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nModels trained primarily on code data will also have a more skewed demographic bias commensurate with the demographics of the GitHub community, for more on this see the StarCoder2 dataset\n\n\nSince the base model was pretrained on a large corpus of code, it may produce code snippets that are syntactically valid but semantically incorrect.\nFor example, it may produce code that does not compile or that produces incorrect results. \n\nIt may also produce code that is vulnerable to security exploits. \n\nWe have observed the model also has a tendency to produce false URLs which should be carefully inspected before clicking.\n\n\nStarChat2 15B was fine-tuned from the base model StarCoder2, please refer to its model card's Limitations Section for relevant information.\nIn particular, the model was evaluated on some categories of gender biases, propensity for toxicity, and risk of suggesting code completions with known security flaws; these evaluations are reported in its technical report.\n\n\nTraining details\n----------------\n\n\nThis model is a fine-tuned version of starchat2-15b-sft-v0.1 on the HuggingFaceH4/ultrafeedback\\_binarized and the HuggingFaceH4/orca\\_dpo\\_pairs datasets. Check out the recipe in the Alignment Handbook for more details.\n\n\nIt achieves the following results on the evaluation set:\n\n\n* Loss: 0.4347\n* Rewards/chosen: -0.9461\n* Rewards/rejected: -2.7745\n* Rewards/accuracies: 0.7658\n* Rewards/margins: 1.8284\n* Logps/rejected: -322.1934\n* Logps/chosen: -316.1898\n* Logits/rejected: -2.3817\n* Logits/chosen: -2.3005\n\n\nTraining procedure\n------------------", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-07\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 128\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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

[ "TAGS\n#transformers #safetensors #starcoder2 #text-generation #conversational #dataset-HuggingFaceH4/ultrafeedback_binarized #dataset-HuggingFaceH4/orca_dpo_pairs #arxiv-2311.07911 #arxiv-2402.19173 #base_model-HuggingFaceH4/starchat2-15b-sft-v0.1 #license-bigcode-openrail-m #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "### Model Description\n\n\n* Model type: A 16B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.\n* Language(s) (NLP): Primarily English and 600+ programming languages.\n* License: BigCode Open RAIL-M v1\n* Finetuned from model: bigcode/starcoder2-15b", "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nPerformance\n-----------\n\n\nStarChat2 15B was trained to balance chat and programming capabilities. It achieves strong performance on chat benchmarks like MT Bench and IFEval, as well as the canonical HumanEval benchmark for Python code completion. The scores reported below were obtained using the LightEval evaluation suite (commit '988959cb905df4baa050f82b4d499d46e8b537f2') and each prompt has been formatted with the model's corresponding chat template to simulate real-world usage. This is why some scores may differ from those reported in technical reports or on the Open LLM Leaderboard.\n\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was fine-tuned on a blend of chat, code, math, and reasoning datasets. As a result, the model can be used for chat and you can check out our demo to test its coding capabilities.\n\n\nHere's how you can run the model using the 'pipeline()' function from Transformers:\n\n\nBias, Risks, and Limitations\n----------------------------\n\n\nStarChat2 15B has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nModels trained primarily on code data will also have a more skewed demographic bias commensurate with the demographics of the GitHub community, for more on this see the StarCoder2 dataset\n\n\nSince the base model was pretrained on a large corpus of code, it may produce code snippets that are syntactically valid but semantically incorrect.\nFor example, it may produce code that does not compile or that produces incorrect results. \n\nIt may also produce code that is vulnerable to security exploits. \n\nWe have observed the model also has a tendency to produce false URLs which should be carefully inspected before clicking.\n\n\nStarChat2 15B was fine-tuned from the base model StarCoder2, please refer to its model card's Limitations Section for relevant information.\nIn particular, the model was evaluated on some categories of gender biases, propensity for toxicity, and risk of suggesting code completions with known security flaws; these evaluations are reported in its technical report.\n\n\nTraining details\n----------------\n\n\nThis model is a fine-tuned version of starchat2-15b-sft-v0.1 on the HuggingFaceH4/ultrafeedback\\_binarized and the HuggingFaceH4/orca\\_dpo\\_pairs datasets. Check out the recipe in the Alignment Handbook for more details.\n\n\nIt achieves the following results on the evaluation set:\n\n\n* Loss: 0.4347\n* Rewards/chosen: -0.9461\n* Rewards/rejected: -2.7745\n* Rewards/accuracies: 0.7658\n* Rewards/margins: 1.8284\n* Logps/rejected: -322.1934\n* Logps/chosen: -316.1898\n* Logits/rejected: -2.3817\n* Logits/chosen: -2.3005\n\n\nTraining procedure\n------------------", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-07\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 128\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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

[ "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", "vision-encoder-decoder", "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 #vision-encoder-decoder #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" ]

[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]

[]

[]

[ "# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: ed-butcher/ppo-PyramidsRND\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #Pyramids #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Pyramids #region-us \n", "# ppo Agent playing Pyramids\n This is a trained model of a ppo agent playing Pyramids\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: ed-butcher/ppo-PyramidsRND\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

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

[]

[ "en" ]

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

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

[ "1910.09700" ]

[]

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

[ "TAGS\n#transformers #safetensors #bert #text-classification #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" ]

[ "safetensors", "pytorch_model_hub_mixin", "model_hub_mixin", "region:us" ]

[]

[]

[]

[ "TAGS\n#safetensors #pytorch_model_hub_mixin #model_hub_mixin #region-us \n" ]

[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:tavtav/eros-7b-test", "base_model:ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b", "license:other", "endpoints_compatible", "region:us" ]

[]

[]

[ "# hus960/Prima-LelantaclesV7-experimentalv2-7b-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Prima-LelantaclesV7-experimentalv2-7b' 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 #mergekit #merge #llama-cpp #gguf-my-repo #base_model-tavtav/eros-7b-test #base_model-ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b #license-other #endpoints_compatible #region-us \n", "# hus960/Prima-LelantaclesV7-experimentalv2-7b-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Prima-LelantaclesV7-experimentalv2-7b' 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", "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: bingogogogo\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: bingogogogo\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.001_5iters_bs256_nodpo_only4w_iter_3", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_5iters_bs256_nodpo_only4w_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_5iters_bs256_nodpo_only4w_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-updated #dataset-original #base_model-ShenaoZhang/0.001_5iters_bs256_nodpo_only4w_iter_3 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_5iters_bs256_nodpo_only4w_iter_4\n\nThis model is a fine-tuned version of ShenaoZhang/0.001_5iters_bs256_nodpo_only4w_iter_3 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

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

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

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:tiiuae/falcon-7b-instruct", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-06\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: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.05\n* num\\_epochs: 5\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #base_model-tiiuae/falcon-7b-instruct #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-06\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: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.05\n* num\\_epochs: 5\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.1.dev0\n* Transformers 4.38.2\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "encoder-decoder", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ "gguf", "pruna-ai", "region:us" ]

[]

[]

[ "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

[ "TAGS\n#gguf #pruna-ai #region-us \n", "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:s3nh/SeverusWestLake-7B-DPO", "base_model:ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b", "license:other", "endpoints_compatible", "region:us" ]

[]

[]

[ "# hus960/Lelanta-lake-7b-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Lelanta-lake-7b' 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 #mergekit #merge #llama-cpp #gguf-my-repo #base_model-s3nh/SeverusWestLake-7B-DPO #base_model-ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b #license-other #endpoints_compatible #region-us \n", "# hus960/Lelanta-lake-7b-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'Nitral-AI/Lelanta-lake-7b' 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", "phi3", "text-generation", "orpo", "Phi 3", "conversational", "custom_code", "en", "dataset:mlabonne/orpo-dpo-mix-40k", "base_model:microsoft/Phi-3-mini-128k-instruct", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Orpo-Phi3-3B-128K\n\n!image/jpeg\n\nThis is an ORPO fine-tune of microsoft/Phi-3-mini-128k-instruct on 10k samples of mlabonne/orpo-dpo-mix-40k.", "## Usage", "## Training curves\n\nWandb Report\n\n!image/png", "## Evaluation\nComing Soon!" ]

[ "TAGS\n#transformers #safetensors #phi3 #text-generation #orpo #Phi 3 #conversational #custom_code #en #dataset-mlabonne/orpo-dpo-mix-40k #base_model-microsoft/Phi-3-mini-128k-instruct #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Orpo-Phi3-3B-128K\n\n!image/jpeg\n\nThis is an ORPO fine-tune of microsoft/Phi-3-mini-128k-instruct on 10k samples of mlabonne/orpo-dpo-mix-40k.", "## Usage", "## Training curves\n\nWandb Report\n\n!image/png", "## Evaluation\nComing Soon!" ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "longt5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#transformers #safetensors #longt5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "bart", "text2text-generation", "generated_from_trainer", "base_model:facebook/bart-large-cnn", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\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: 500\n* num\\_epochs: 4\n* label\\_smoothing\\_factor: 0.1", "### 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 #bart #text2text-generation #generated_from_trainer #base_model-facebook/bart-large-cnn #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: 5e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\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: 500\n* num\\_epochs: 4\n* label\\_smoothing\\_factor: 0.1", "### 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", "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 #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", "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" ]

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

[ "1910.09700" ]

[]

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

[ "TAGS\n#transformers #safetensors #bert #text-classification #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" ]

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

[]

[]

[ "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "TAGS\n#Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us \n", "# Q-Learning Agent playing1 Taxi-v3\n This is a trained model of a Q-Learning agent playing Taxi-v3 .\n\n ## Usage" ]

[ "gguf", "it", "license:mit", "region:us" ]

[]

[ "it" ]

[ "## Responsible AI Considerations\n\nLike other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:\n\nQuality of Service:\nThe Phi models are primarily trained on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English.\n\nRepresentation of Harms & Perpetuation of Stereotypes:\nThese models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.\n\nInappropriate or Offensive Content:\nThese models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.\n\nInformation Reliability:\nLanguage models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.\n\nLimited Scope for Code:\nThe majority of Phi-3 training data is based on Python and uses common packages such as \"typing, math, random, collections, datetime, itertools\". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.\n\nDevelopers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include:\n\nModel in Test: Continuous improvements will be made.\n\nPlease note that the responses obtained from the model should not be considered as absolute truths.", "## How to Download GGUF Files Manually?\n\nNote for Manual Downloaders:\n\nThe following clients will automatically download models for you, providing a list of available models to choose from:\n\nLM Studio\n\nUse PHI3 URL" ]

[ "TAGS\n#gguf #it #license-mit #region-us \n", "## Responsible AI Considerations\n\nLike other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:\n\nQuality of Service:\nThe Phi models are primarily trained on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English.\n\nRepresentation of Harms & Perpetuation of Stereotypes:\nThese models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.\n\nInappropriate or Offensive Content:\nThese models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.\n\nInformation Reliability:\nLanguage models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.\n\nLimited Scope for Code:\nThe majority of Phi-3 training data is based on Python and uses common packages such as \"typing, math, random, collections, datetime, itertools\". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.\n\nDevelopers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include:\n\nModel in Test: Continuous improvements will be made.\n\nPlease note that the responses obtained from the model should not be considered as absolute truths.", "## How to Download GGUF Files Manually?\n\nNote for Manual Downloaders:\n\nThe following clients will automatically download models for you, providing a list of available models to choose from:\n\nLM Studio\n\nUse PHI3 URL" ]

[ "transformers", "tensorboard", "safetensors", "bert", "text-generation", "generated_from_trainer", "dataset:eli5_category", "base_model:google-bert/bert-base-cased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# my_eli5_clm_model\n\nThis model is a fine-tuned version of google-bert/bert-base-cased on the eli5_category 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: 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: 3.0", "### 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 #bert #text-generation #generated_from_trainer #dataset-eli5_category #base_model-google-bert/bert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# my_eli5_clm_model\n\nThis model is a fine-tuned version of google-bert/bert-base-cased on the eli5_category 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: 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: 3.0", "### 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", "mistral", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ "gguf", "pruna-ai", "region:us" ]

[]

[]

[ "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

[ "TAGS\n#gguf #pruna-ai #region-us \n", "### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: llama-cpp-python docs.", "#### First install the package\n\nRun one of the following commands, according to your system:", "#### Simple llama-cpp-python example code\n\n```\n\n* Option D - Running with LangChain\n\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n\n* LangChain + llama-cpp-python\n* LangChain + ctransformers\n\n\nConfigurations\n--------------\n\n\nThe configuration info are in 'smash\\_config.json'.\n\n\nCredits & License\n-----------------\n\n\nThe license of the smashed model follows the license of the original model. Please check the license of the original model before using this model which provided the base model. The license of the 'pruna-engine' is here on Pypi.\n\n\nWant to compress other models?\n------------------------------\n\n\n* Contact us and tell us which model to compress next here.\n* Request access to easily compress your own AI models here." ]

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

[ "1910.09700" ]

[]

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

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

[ "transformers", "safetensors", "swinv2", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft", "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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.35.0\n* Pytorch 2.1.0\n* Datasets 2.14.6\n* Tokenizers 0.14.1" ]

[ "TAGS\n#transformers #safetensors #swinv2 #image-classification #generated_from_trainer #dataset-imagefolder #base_model-microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft #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: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### 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", "mistral", "text-generation", "arxiv:2304.12244", "arxiv:2306.08568", "arxiv:2308.09583", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2304.12244", "2306.08568", "2308.09583" ]

[]

[ "## News [2024/04/15]\n\nWe introduce and opensource WizardLM-2, our next generation state-of-the-art large language models, \nwhich have improved performance on complex chat, multilingual, reasoning and agent. \nNew family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B.\n\n- WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works \nand consistently outperforms all the existing state-of-the-art opensource models.\n- WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size. This model weights will be available in the coming days. \n- WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.\n\nFor more details of WizardLM-2 please read our release blog post and upcoming paper.", "## Model Details\n\n* Model name: WizardLM-2 7B\n* Developed by: WizardLM@Microsoft AI\n* Base model: mistralai/Mistral-7B-v0.1\n* Parameters: 7B\n* Language(s): Multilingual\n* Blog: Introducing WizardLM-2\n* Repository: URL\n* Paper: WizardLM-2 (Upcoming)\n* License: Apache2.0", "## Model Capacities\n\n\nMT-Bench\n\nWe also adopt the automatic MT-Bench evaluation framework based on GPT-4 proposed by lmsys to assess the performance of models. \nThe WizardLM-2 8x22B even demonstrates highly competitive performance compared to the most advanced proprietary models. \nMeanwhile, WizardLM-2 7B and WizardLM-2 70B are all the top-performing models among the other leading baselines at 7B to 70B model scales.\n\n<p align=\"center\" width=\"100%\">\n<a ><img src=\"URL alt=\"MTBench\" style=\"width: 96%; min-width: 300px; display: block; margin: auto;\"></a>\n</p>\n\n\nHuman Preferences Evaluation\n\nWe carefully collected a complex and challenging set consisting of real-world instructions, which includes main requirements of humanity, such as writing, coding, math, reasoning, agent, and multilingual. \nWe report the win:loss rate without tie:\n\n- WizardLM-2 8x22B is just slightly falling behind GPT-4-1106-preview, and significantly stronger than Command R Plus and GPT4-0314.\n- WizardLM-2 70B is better than GPT4-0613, Mistral-Large, and Qwen1.5-72B-Chat.\n- WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta.\n\n<p align=\"center\" width=\"100%\">\n<a ><img src=\"URL alt=\"Win\" style=\"width: 96%; min-width: 300px; display: block; margin: auto;\"></a>\n</p>", "## Method Overview\nWe built a fully AI powered synthetic training system to train WizardLM-2 models, please refer to our blog for more details of this system.\n\n<p align=\"center\" width=\"100%\">\n<a ><img src=\"URL alt=\"Method\" style=\"width: 96%; min-width: 300px; display: block; margin: auto;\"></a>\n</p>", "## Usage\n\n<b>Note for model system prompts usage:</b>\n\n\n<b>WizardLM-2</b> adopts the prompt format from <b>Vicuna</b> and supports multi-turn conversation. The prompt should be as following:\n\n\n\n<b> Inference WizardLM-2 Demo Script</b>\n\nWe provide a WizardLM-2 inference demo code on our github." ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-2304.12244 #arxiv-2306.08568 #arxiv-2308.09583 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## News [2024/04/15]\n\nWe introduce and opensource WizardLM-2, our next generation state-of-the-art large language models, \nwhich have improved performance on complex chat, multilingual, reasoning and agent. \nNew family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B.\n\n- WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works \nand consistently outperforms all the existing state-of-the-art opensource models.\n- WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size. This model weights will be available in the coming days. \n- WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.\n\nFor more details of WizardLM-2 please read our release blog post and upcoming paper.", "## Model Details\n\n* Model name: WizardLM-2 7B\n* Developed by: WizardLM@Microsoft AI\n* Base model: mistralai/Mistral-7B-v0.1\n* Parameters: 7B\n* Language(s): Multilingual\n* Blog: Introducing WizardLM-2\n* Repository: URL\n* Paper: WizardLM-2 (Upcoming)\n* License: Apache2.0", "## Model Capacities\n\n\nMT-Bench\n\nWe also adopt the automatic MT-Bench evaluation framework based on GPT-4 proposed by lmsys to assess the performance of models. \nThe WizardLM-2 8x22B even demonstrates highly competitive performance compared to the most advanced proprietary models. \nMeanwhile, WizardLM-2 7B and WizardLM-2 70B are all the top-performing models among the other leading baselines at 7B to 70B model scales.\n\n<p align=\"center\" width=\"100%\">\n<a ><img src=\"URL alt=\"MTBench\" style=\"width: 96%; min-width: 300px; display: block; margin: auto;\"></a>\n</p>\n\n\nHuman Preferences Evaluation\n\nWe carefully collected a complex and challenging set consisting of real-world instructions, which includes main requirements of humanity, such as writing, coding, math, reasoning, agent, and multilingual. \nWe report the win:loss rate without tie:\n\n- WizardLM-2 8x22B is just slightly falling behind GPT-4-1106-preview, and significantly stronger than Command R Plus and GPT4-0314.\n- WizardLM-2 70B is better than GPT4-0613, Mistral-Large, and Qwen1.5-72B-Chat.\n- WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta.\n\n<p align=\"center\" width=\"100%\">\n<a ><img src=\"URL alt=\"Win\" style=\"width: 96%; min-width: 300px; display: block; margin: auto;\"></a>\n</p>", "## Method Overview\nWe built a fully AI powered synthetic training system to train WizardLM-2 models, please refer to our blog for more details of this system.\n\n<p align=\"center\" width=\"100%\">\n<a ><img src=\"URL alt=\"Method\" style=\"width: 96%; min-width: 300px; display: block; margin: auto;\"></a>\n</p>", "## Usage\n\n<b>Note for model system prompts usage:</b>\n\n\n<b>WizardLM-2</b> adopts the prompt format from <b>Vicuna</b> and supports multi-turn conversation. The prompt should be as following:\n\n\n\n<b> Inference WizardLM-2 Demo Script</b>\n\nWe provide a WizardLM-2 inference demo code on our github." ]

[ "nlp", "code", "text-generation", "en", "license:mit", "region:us" ]

[]

[ "en" ]

[ "## Exllama v2 Quantizations of Phi-3-mini-128k-instruct\n\nUsing <a href=\"URL ExLlamaV2 v0.0.20</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>", "## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'Phi-3-mini-128k-instruct-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):" ]

[ "TAGS\n#nlp #code #text-generation #en #license-mit #region-us \n", "## Exllama v2 Quantizations of Phi-3-mini-128k-instruct\n\nUsing <a href=\"URL ExLlamaV2 v0.0.20</a> for quantization.\n\n<b>The \"main\" branch only contains the URL, download one of the other branches for the model (see below)</b>\n\nEach branch contains an individual bits per weight, with the main one containing only the URL for further conversions.\n\nConversion was done using the default calibration dataset.\n\nDefault arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.\n\nOriginal model: URL\n\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>\n\n<a href=\"URL bits per weight</a>", "## Download instructions\n\nWith git:\n\n\n\nWith huggingface hub (credit to TheBloke for instructions):\n\n\n\nTo download the 'main' (only useful if you only care about URL) branch to a folder called 'Phi-3-mini-128k-instruct-exl2':\n\n\n\nTo download from a different branch, add the '--revision' parameter:\n\nLinux:\n\n\n\nWindows (which apparently doesn't like _ in folders sometimes?):" ]

[ "diffusers", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "diffusers-training", "lora", "base_model:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]

[]

[]

[ "# LoRA text2image fine-tuning - zabibeau/onepiece-lora\nThese are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the YaYaB/onepiece-blip-captions dataset. You can find some example images in the following. \n\n!img_0\n!img_1\n!img_2\n!img_3", "## 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 #stable-diffusion #stable-diffusion-diffusers #text-to-image #diffusers-training #lora #base_model-runwayml/stable-diffusion-v1-5 #license-creativeml-openrail-m #region-us \n", "# LoRA text2image fine-tuning - zabibeau/onepiece-lora\nThese are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the YaYaB/onepiece-blip-captions dataset. You can find some example images in the following. \n\n!img_0\n!img_1\n!img_2\n!img_3", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "transformers", "tensorboard", "safetensors", "gemma", "text-generation", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "conversational", "dataset:argilla/dpo-mix-7k", "base_model:HuggingFaceH4/zephyr-7b-gemma-sft-v0.1", "license:other", "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-07\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 128\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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gemma #text-generation #alignment-handbook #trl #dpo #generated_from_trainer #conversational #dataset-argilla/dpo-mix-7k #base_model-HuggingFaceH4/zephyr-7b-gemma-sft-v0.1 #license-other #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-07\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 128\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* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 6.7e-06\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\\_steps: 500\n* num\\_epochs: 4", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\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-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 6.7e-06\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\\_steps: 500\n* num\\_epochs: 4", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "mt5", "text-classification", "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 #mt5 #text-classification #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", "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" ]