Datasets:

---

ftopal

/

huggingface-models-processed

like 0

[ "peft", "safetensors", "mistral", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "dataset:hugodk-sch/aftonposten_title_prefs", "base_model:norallm/normistral-7b-warm", "4-bit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\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\n* PEFT 0.10.0\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.1" ]

[ "TAGS\n#peft #safetensors #mistral #alignment-handbook #trl #dpo #generated_from_trainer #dataset-hugodk-sch/aftonposten_title_prefs #base_model-norallm/normistral-7b-warm #4-bit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\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\n* PEFT 0.10.0\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.1" ]

[ 72, 154, 5, 55 ]

[ "TAGS\n#peft #safetensors #mistral #alignment-handbook #trl #dpo #generated_from_trainer #dataset-hugodk-sch/aftonposten_title_prefs #base_model-norallm/normistral-7b-warm #4-bit #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 8\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\n* PEFT 0.10.0\n* Transformers 4.39.0.dev0\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.1" ]

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:2305.18290", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "2305.18290" ]

[]

[ "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-2305.18290 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ 51, 491, 164, 5, 44 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-2305.18290 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1### Training results### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ "gguf", "Llama-3", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "synthetic data", "distillation", "function calling", "json mode", "en", "dataset:teknium/OpenHermes-2.5", "base_model:NousResearch/Meta-Llama-3-8B", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "# Hermes 2 Pro - Llama-3 8B\n\n!image/png", "## Model Description", "### This is the URL GGUF Quantized version of Hermes 2 Pro Llama-3 8B, for the full version, click Here\n\nHermes 2 Pro is an upgraded version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.\n\nThis new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.\n\nHermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.\n\nThis version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - '<tools>', '<tool_call>', '<tool_response>' and their closing tags are single tokens now.\n\nThis work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI\n\nLearn more about the function calling system for this model on our github repo here: URL", "## Example Outputs", "### Ask for a structured JSON output:\n!image/png", "### Write the plot for a story where anime became real life:\n!image/png", "### Coding Assistance\n!image/png", "# Prompt Format\n\nHermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.\n\nSystem prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.\n\nThis is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.\n\nThis format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.\n\nPrompt with system instruction (Use whatever system prompt you like, this is just an example!):\n\n\nThis prompt is available as a chat template, which means you can format messages using the\n'tokenizer.apply_chat_template()' method:\n\n\n\nWhen tokenizing messages for generation, set 'add_generation_prompt=True' when calling 'apply_chat_template()'. This will append '<|im_start|>assistant\\n' to your prompt, to ensure\nthat the model continues with an assistant response.\n\nTo utilize the prompt format without a system prompt, simply leave the line out.", "## Prompt Format for Function Calling\n\nOur model was trained on specific system prompts and structures for Function Calling. \n\nYou should use the system role with this message, followed by a function signature json as this example shows here.\n\n\nTo complete the function call, create a user prompt that follows the above system prompt, like so:\n\n\nThe model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: URL\n\n\nOnce you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, 'tool' like so:\n\n\nThe assistant will then read in that data from the function's response, and generate a natural language response:", "## Prompt Format for JSON Mode / Structured Outputs\n\nOur model was also trained on a specific system prompt for Structured Outputs, which should respond with only a json object response, in a specific json schema.\n\nYour schema can be made from a pydantic object using our codebase, with the standalone script 'URL' available here: URL\n\n\n\nGiven the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.", "# Benchmarks\n\n!image/png", "## GPT4All:\n\nAverage: 72.62", "## AGIEval:\n\nAverage: 42.44", "## BigBench:\n\nAverage: 43.55", "## TruthfulQA:", "# Inference Code\n\nHere is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)\n\nNote: To use function calling, you should see the github repo above.", "## Inference Code for Function Calling:\n\nAll code for utilizing, parsing, and building function calling templates is available on our github:\nURL\n\n!image/png", "# Chat Interfaces\n\nFor quantized GGUF versions of the model, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a URL backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.\nIn LM-Studio, simply select the ChatML Prefix on the settings side pane:\n\n!image/png", "# How to cite:" ]

[ "TAGS\n#gguf #Llama-3 #instruct #finetune #chatml #DPO #RLHF #gpt4 #synthetic data #distillation #function calling #json mode #en #dataset-teknium/OpenHermes-2.5 #base_model-NousResearch/Meta-Llama-3-8B #license-apache-2.0 #region-us \n", "# Hermes 2 Pro - Llama-3 8B\n\n!image/png", "## Model Description", "### This is the URL GGUF Quantized version of Hermes 2 Pro Llama-3 8B, for the full version, click Here\n\nHermes 2 Pro is an upgraded version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.\n\nThis new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.\n\nHermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.\n\nThis version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - '<tools>', '<tool_call>', '<tool_response>' and their closing tags are single tokens now.\n\nThis work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI\n\nLearn more about the function calling system for this model on our github repo here: URL", "## Example Outputs", "### Ask for a structured JSON output:\n!image/png", "### Write the plot for a story where anime became real life:\n!image/png", "### Coding Assistance\n!image/png", "# Prompt Format\n\nHermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.\n\nSystem prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.\n\nThis is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.\n\nThis format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.\n\nPrompt with system instruction (Use whatever system prompt you like, this is just an example!):\n\n\nThis prompt is available as a chat template, which means you can format messages using the\n'tokenizer.apply_chat_template()' method:\n\n\n\nWhen tokenizing messages for generation, set 'add_generation_prompt=True' when calling 'apply_chat_template()'. This will append '<|im_start|>assistant\\n' to your prompt, to ensure\nthat the model continues with an assistant response.\n\nTo utilize the prompt format without a system prompt, simply leave the line out.", "## Prompt Format for Function Calling\n\nOur model was trained on specific system prompts and structures for Function Calling. \n\nYou should use the system role with this message, followed by a function signature json as this example shows here.\n\n\nTo complete the function call, create a user prompt that follows the above system prompt, like so:\n\n\nThe model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: URL\n\n\nOnce you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, 'tool' like so:\n\n\nThe assistant will then read in that data from the function's response, and generate a natural language response:", "## Prompt Format for JSON Mode / Structured Outputs\n\nOur model was also trained on a specific system prompt for Structured Outputs, which should respond with only a json object response, in a specific json schema.\n\nYour schema can be made from a pydantic object using our codebase, with the standalone script 'URL' available here: URL\n\n\n\nGiven the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.", "# Benchmarks\n\n!image/png", "## GPT4All:\n\nAverage: 72.62", "## AGIEval:\n\nAverage: 42.44", "## BigBench:\n\nAverage: 43.55", "## TruthfulQA:", "# Inference Code\n\nHere is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)\n\nNote: To use function calling, you should see the github repo above.", "## Inference Code for Function Calling:\n\nAll code for utilizing, parsing, and building function calling templates is available on our github:\nURL\n\n!image/png", "# Chat Interfaces\n\nFor quantized GGUF versions of the model, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a URL backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.\nIn LM-Studio, simply select the ChatML Prefix on the settings side pane:\n\n!image/png", "# How to cite:" ]

[ 95, 16, 4, 286, 4, 16, 20, 10, 264, 154, 121, 8, 12, 11, 11, 6, 50, 37, 110, 5 ]

[ "TAGS\n#gguf #Llama-3 #instruct #finetune #chatml #DPO #RLHF #gpt4 #synthetic data #distillation #function calling #json mode #en #dataset-teknium/OpenHermes-2.5 #base_model-NousResearch/Meta-Llama-3-8B #license-apache-2.0 #region-us \n# Hermes 2 Pro - Llama-3 8B\n\n!image/png## Model Description### This is the URL GGUF Quantized version of Hermes 2 Pro Llama-3 8B, for the full version, click Here\n\nHermes 2 Pro is an upgraded version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.\n\nThis new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling, JSON Structured Outputs, and has improved on several other metrics as well, scoring a 90% on our function calling evaluation built in partnership with Fireworks.AI, and an 84% on our structured JSON Output evaluation.\n\nHermes Pro takes advantage of a special system prompt and multi-turn function calling structure with a new chatml role in order to make function calling reliable and easy to parse. Learn more about prompting below.\n\nThis version of Hermes 2 Pro adds several tokens to assist with agentic capabilities in parsing while streaming tokens - '<tools>', '<tool_call>', '<tool_response>' and their closing tags are single tokens now.\n\nThis work was a collaboration between Nous Research, @interstellarninja, and Fireworks.AI\n\nLearn more about the function calling system for this model on our github repo here: URL## Example Outputs### Ask for a structured JSON output:\n!image/png### Write the plot for a story where anime became real life:\n!image/png### Coding Assistance\n!image/png# Prompt Format\n\nHermes 2 Pro uses ChatML as the prompt format, opening up a much more structured system for engaging the LLM in multi-turn chat dialogue.\n\nSystem prompts allow steerability and interesting new ways to interact with an LLM, guiding rules, roles, and stylistic choices of the model.\n\nThis is a more complex format than alpaca or sharegpt, where special tokens were added to denote the beginning and end of any turn, along with roles for the turns.\n\nThis format enables OpenAI endpoint compatability, and people familiar with ChatGPT API will be familiar with the format, as it is the same used by OpenAI.\n\nPrompt with system instruction (Use whatever system prompt you like, this is just an example!):\n\n\nThis prompt is available as a chat template, which means you can format messages using the\n'tokenizer.apply_chat_template()' method:\n\n\n\nWhen tokenizing messages for generation, set 'add_generation_prompt=True' when calling 'apply_chat_template()'. This will append '<|im_start|>assistant\\n' to your prompt, to ensure\nthat the model continues with an assistant response.\n\nTo utilize the prompt format without a system prompt, simply leave the line out.## Prompt Format for Function Calling\n\nOur model was trained on specific system prompts and structures for Function Calling. \n\nYou should use the system role with this message, followed by a function signature json as this example shows here.\n\n\nTo complete the function call, create a user prompt that follows the above system prompt, like so:\n\n\nThe model will then generate a tool call, which your inference code must parse, and plug into a function (see example inference code here: URL\n\n\nOnce you parse the tool call, call the api and get the returned values for the call, and pass it back in as a new role, 'tool' like so:\n\n\nThe assistant will then read in that data from the function's response, and generate a natural language response:## Prompt Format for JSON Mode / Structured Outputs\n\nOur model was also trained on a specific system prompt for Structured Outputs, which should respond with only a json object response, in a specific json schema.\n\nYour schema can be made from a pydantic object using our codebase, with the standalone script 'URL' available here: URL\n\n\n\nGiven the {schema} that you provide, it should follow the format of that json to create it's response, all you have to do is give a typical user prompt, and it will respond in JSON.# Benchmarks\n\n!image/png## GPT4All:\n\nAverage: 72.62## AGIEval:\n\nAverage: 42.44## BigBench:\n\nAverage: 43.55## TruthfulQA:# Inference Code\n\nHere is example code using HuggingFace Transformers to inference the model (note: in 4bit, it will require around 5GB of VRAM)\n\nNote: To use function calling, you should see the github repo above.## Inference Code for Function Calling:\n\nAll code for utilizing, parsing, and building function calling templates is available on our github:\nURL\n\n!image/png# Chat Interfaces\n\nFor quantized GGUF versions of the model, I recommend using LM Studio for chatting with Hermes 2 Pro. It does not support function calling - for that use our github repo. It is a GUI application that utilizes GGUF models with a URL backend and provides a ChatGPT-like interface for chatting with the model, and supports ChatML right out of the box.\nIn LM-Studio, simply select the ChatML Prefix on the settings side pane:\n\n!image/png# How to cite:" ]

[ "transformers", "safetensors", "bart", "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 #bart #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" ]

[ 39, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#transformers #safetensors #bart #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", "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" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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", "mistral", "text-generation", "conversational", "arxiv:2305.18290", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[ "2305.18290" ]

[]

[ "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-2305.18290 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ 51, 491, 164, 5, 44 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-2305.18290 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1### Training results### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ "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" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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", "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" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 55, 151, 5, 52 ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-PrunaAI/mistralai-Mistral-7B-Instruct-v0.2-bnb-4bit-smashed #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* gradient\\_accumulation\\_steps: 4\n* total\\_train\\_batch\\_size: 16\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2\n* num\\_epochs: 10\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* PEFT 0.10.0\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", "en", "base_model:Undi95/Emerald-13B", "license:cc-by-sa-4.0", "autotrain_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "## Hypernova-experimental\nTried some new stuff this time around. Very different outcome than I expected.\nThis is an experimental model that was created for the development of NovaAI.\n\nGood at chatting and some RP. Sometimes gets characters mixed up. Can occasionally struggle with context.\n\nQuantized model here: theNovaAI/Hypernova-experimental-GPTQ", "## Prompt Template: Alpaca", "### Models Merged\n\nThe following models were included in the merge:\n* Undi95/Emerald-13B\n* Gryphe/MythoMax-L2-13b\n \nSome finetuning done as well" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #en #base_model-Undi95/Emerald-13B #license-cc-by-sa-4.0 #autotrain_compatible #text-generation-inference #region-us \n", "## Hypernova-experimental\nTried some new stuff this time around. Very different outcome than I expected.\nThis is an experimental model that was created for the development of NovaAI.\n\nGood at chatting and some RP. Sometimes gets characters mixed up. Can occasionally struggle with context.\n\nQuantized model here: theNovaAI/Hypernova-experimental-GPTQ", "## Prompt Template: Alpaca", "### Models Merged\n\nThe following models were included in the merge:\n* Undi95/Emerald-13B\n* Gryphe/MythoMax-L2-13b\n \nSome finetuning done as well" ]

[ 57, 73, 8, 45 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #en #base_model-Undi95/Emerald-13B #license-cc-by-sa-4.0 #autotrain_compatible #text-generation-inference #region-us \n## Hypernova-experimental\nTried some new stuff this time around. Very different outcome than I expected.\nThis is an experimental model that was created for the development of NovaAI.\n\nGood at chatting and some RP. Sometimes gets characters mixed up. Can occasionally struggle with context.\n\nQuantized model here: theNovaAI/Hypernova-experimental-GPTQ## Prompt Template: Alpaca### Models Merged\n\nThe following models were included in the merge:\n* Undi95/Emerald-13B\n* Gryphe/MythoMax-L2-13b\n \nSome finetuning done as well" ]

[ "gguf", "facebook", "meta", "llama", "llama-3", "llama-3-ko", "llama-cpp", "gguf-my-repo", "en", "ko", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "region:us" ]

[]

[ "en", "ko" ]

[ "# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #facebook #meta #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n", "# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ 75, 101, 52 ]

[ "TAGS\n#gguf #facebook #meta #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q4_K_S-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:Ransaka/Gemma-2b-sinhala", "region:us" ]

[]

[]

[ "# gemma-2b-aya-chatml-v3\n\nThis model is a fine-tuned version of Ransaka/Gemma-2b-sinhala on the generator 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: 0.0002\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- PEFT 0.8.2\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-Ransaka/Gemma-2b-sinhala #region-us \n", "# gemma-2b-aya-chatml-v3\n\nThis model is a fine-tuned version of Ransaka/Gemma-2b-sinhala on the generator 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: 0.0002\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- PEFT 0.8.2\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ 47, 39, 7, 9, 9, 4, 126, 5, 48 ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-Ransaka/Gemma-2b-sinhala #region-us \n# gemma-2b-aya-chatml-v3\n\nThis model is a fine-tuned version of Ransaka/Gemma-2b-sinhala on the generator 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: 0.0002\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 1### Training results### Framework versions\n\n- PEFT 0.8.2\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "mistral", "text-generation", "finetuned", "not-for-all-audiences", "custom_code", "en", "ja", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en", "ja" ]

[ "# Our Models\n- Vecteus\n\n- Ninja-v1 \n\n- Ninja-v1-NSFW\n\n- Ninja-v1-128k\n\n- Ninja-v1-NSFW-128k", "## Model Card for Ninja-v1-NSFW-128k\n\nThe Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1\n\nNinja-NSFW-128k has the following changes compared to Mistral-7B-v0.1.\n- 128k context window (8k context in v0.1)\n- Achieving both high quality Japanese and English generation\n- Memory ability that does not forget even after long-context generation\n- Can be generated NSFW\n\nThis model was created with the help of GPUs from the first LocalAI hackathon.\n\nWe would like to take this opportunity to thank", "## List of Creation Methods\n\n- Chatvector for multiple models\n- Simple linear merging of result models\n- Domain and Sentence Enhancement with LORA\n- Context expansion", "## Instruction format\n\n Ninja adopts the prompt format from Vicuna and supports multi-turn conversation.\n The prompt should be as following:", "## Example prompts to improve (Japanese)\n\n - BAD:　あなたは○○として振る舞います\n - GOOD: あなたは○○です\n\n - BAD: あなたは○○ができます\n - GOOD: あなたは○○をします", "## Performing inference\n\n'", "## Merge recipe\n\n- WizardLM2 - mistralai/Mistral-7B-v0.1\n- NousResearch/Yarn-Mistral-7b-128k - mistralai/Mistral-7B-v0.1\n- Elizezen/Antler-7B - stabilityai/japanese-stablelm-instruct-gamma-7b\n- Elizezen/LewdSniffyOtter-7B - Elizezen/SniffyOtter-7B\n- NTQAI/chatntq-ja-7b-v1.0\n\nThe characteristics of each model are as follows.\n\n- WizardLM2: High quality multitasking model\n- Yarn-Mistral-7b-128k: Mistral model with 128k context window\n- Antler-7B: Model specialized for novel writing\n- NTQAI/chatntq-ja-7b-v1.0 High quality Japanese specialized model\n- Elizezen/LewdSniffyOtter-7B Japanese NSFW specialized model", "## Other points to keep in mind\n- The training data may be biased. Be careful with the generated sentences.\n- Set trust_remote_code to True for context expansion with YaRN.\n- Memory usage may be large for long inferences.\n- If possible, we recommend inferring with llamacpp rather than Transformers." ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #finetuned #not-for-all-audiences #custom_code #en #ja #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Our Models\n- Vecteus\n\n- Ninja-v1 \n\n- Ninja-v1-NSFW\n\n- Ninja-v1-128k\n\n- Ninja-v1-NSFW-128k", "## Model Card for Ninja-v1-NSFW-128k\n\nThe Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1\n\nNinja-NSFW-128k has the following changes compared to Mistral-7B-v0.1.\n- 128k context window (8k context in v0.1)\n- Achieving both high quality Japanese and English generation\n- Memory ability that does not forget even after long-context generation\n- Can be generated NSFW\n\nThis model was created with the help of GPUs from the first LocalAI hackathon.\n\nWe would like to take this opportunity to thank", "## List of Creation Methods\n\n- Chatvector for multiple models\n- Simple linear merging of result models\n- Domain and Sentence Enhancement with LORA\n- Context expansion", "## Instruction format\n\n Ninja adopts the prompt format from Vicuna and supports multi-turn conversation.\n The prompt should be as following:", "## Example prompts to improve (Japanese)\n\n - BAD:　あなたは○○として振る舞います\n - GOOD: あなたは○○です\n\n - BAD: あなたは○○ができます\n - GOOD: あなたは○○をします", "## Performing inference\n\n'", "## Merge recipe\n\n- WizardLM2 - mistralai/Mistral-7B-v0.1\n- NousResearch/Yarn-Mistral-7b-128k - mistralai/Mistral-7B-v0.1\n- Elizezen/Antler-7B - stabilityai/japanese-stablelm-instruct-gamma-7b\n- Elizezen/LewdSniffyOtter-7B - Elizezen/SniffyOtter-7B\n- NTQAI/chatntq-ja-7b-v1.0\n\nThe characteristics of each model are as follows.\n\n- WizardLM2: High quality multitasking model\n- Yarn-Mistral-7b-128k: Mistral model with 128k context window\n- Antler-7B: Model specialized for novel writing\n- NTQAI/chatntq-ja-7b-v1.0 High quality Japanese specialized model\n- Elizezen/LewdSniffyOtter-7B Japanese NSFW specialized model", "## Other points to keep in mind\n- The training data may be biased. Be careful with the generated sentences.\n- Set trust_remote_code to True for context expansion with YaRN.\n- Memory usage may be large for long inferences.\n- If possible, we recommend inferring with llamacpp rather than Transformers." ]

[ 62, 41, 151, 31, 27, 32, 5, 219, 67 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #finetuned #not-for-all-audiences #custom_code #en #ja #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Our Models\n- Vecteus\n\n- Ninja-v1 \n\n- Ninja-v1-NSFW\n\n- Ninja-v1-128k\n\n- Ninja-v1-NSFW-128k## Model Card for Ninja-v1-NSFW-128k\n\nThe Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1\n\nNinja-NSFW-128k has the following changes compared to Mistral-7B-v0.1.\n- 128k context window (8k context in v0.1)\n- Achieving both high quality Japanese and English generation\n- Memory ability that does not forget even after long-context generation\n- Can be generated NSFW\n\nThis model was created with the help of GPUs from the first LocalAI hackathon.\n\nWe would like to take this opportunity to thank## List of Creation Methods\n\n- Chatvector for multiple models\n- Simple linear merging of result models\n- Domain and Sentence Enhancement with LORA\n- Context expansion## Instruction format\n\n Ninja adopts the prompt format from Vicuna and supports multi-turn conversation.\n The prompt should be as following:## Example prompts to improve (Japanese)\n\n - BAD:　あなたは○○として振る舞います\n - GOOD: あなたは○○です\n\n - BAD: あなたは○○ができます\n - GOOD: あなたは○○をします## Performing inference\n\n'## Merge recipe\n\n- WizardLM2 - mistralai/Mistral-7B-v0.1\n- NousResearch/Yarn-Mistral-7b-128k - mistralai/Mistral-7B-v0.1\n- Elizezen/Antler-7B - stabilityai/japanese-stablelm-instruct-gamma-7b\n- Elizezen/LewdSniffyOtter-7B - Elizezen/SniffyOtter-7B\n- NTQAI/chatntq-ja-7b-v1.0\n\nThe characteristics of each model are as follows.\n\n- WizardLM2: High quality multitasking model\n- Yarn-Mistral-7b-128k: Mistral model with 128k context window\n- Antler-7B: Model specialized for novel writing\n- NTQAI/chatntq-ja-7b-v1.0 High quality Japanese specialized model\n- Elizezen/LewdSniffyOtter-7B Japanese NSFW specialized model## Other points to keep in mind\n- The training data may be biased. Be careful with the generated sentences.\n- Set trust_remote_code to True for context expansion with YaRN.\n- Memory usage may be large for long inferences.\n- If possible, we recommend inferring with llamacpp rather than Transformers." ]

[ "gguf", "arxiv:2305.18290", "region:us" ]

[ "2305.18290" ]

[]

[ "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ "TAGS\n#gguf #arxiv-2305.18290 #region-us \n", "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1", "### Training results", "### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ 19, 491, 164, 5, 44 ]

[ "TAGS\n#gguf #arxiv-2305.18290 #region-us \n### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a variant of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. We then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contain 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its 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\nZephyr-7B-α 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).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nZephyr 7B Alpha achieves the following results on the evaluation set:\n\n\n* Loss: 0.4605\n* Rewards/chosen: -0.5053\n* Rewards/rejected: -1.8752\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 1.3699\n* Logps/rejected: -327.4286\n* Logps/chosen: -297.1040\n* Logits/rejected: -2.7153\n* Logits/chosen: -2.7447\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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 1### Training results### Framework versions\n\n\n* Transformers 4.34.0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0" ]

[ "gguf", "region:us" ]

[]

[]

[ "# Coomand-R 35B v1\n\n> THIS FINETUNED MODEL HAS BEEN RATED...\n> !image/png\n> *We've enhanced the underdog with a rich and refreshing coomand of eRP. Finetuned by yours truly.*", "## Original\n\nURL", "## What's New?\n\n(Other than the changes documented in Moistral v3)\n\n- Trained with stronger instructions\n- A larger dataset with more diverse, wacky genres!", "# ‍️‍ ️", "## Usage\n\n- Use Command-R format *(Alpaca kinda works btw)*\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here\n- Coomand-R is optimized for the Novel / Story format.\n - At the start of the story, keep regenerating until you get the desired length. Future AI responses will eventually match the length.\n - Issue: Manually continued generation may create formatting issues. Either regenerate the entire response or fix the formatting.\n - See samples below.", "## Samples of Coomand-R 35B\n\nSOME nsfw.\n\n<details>\n <summary>Coomand-R Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>The prince gives her a show</blockquote>\n\n The sorcerer prince gave out a low chuckle, his eyes narrowing in amusement. \"Oh, don't be so dramatic, my dear,\" he replied with a smirk. \"Surely you know by now that I like to indulge in pleasure whenever possible. And believe me, there is nothing boring about what we're doing right now.\" He gestured towards the girl still kneeling before him, who had resumed her task with renewed vigor.\n \n Princess Lilia could feel her anger simmering beneath the surface, but she knew better than to rise to the bait. Instead, she tried to keep her voice level and composed as she spoke.\n \n \"I understand your needs, Your Highness,\" she answered calmly. \"But surely you can appreciate how difficult it must be for me, standing here while you... indulge yourself.\"\n \n There was a glint in the sorcerer prince's eyes as he regarded Princess Lilia, an almost mischievous spark that made her skin crawl. \"Do you find this uncomfortable?\" he asked, his tone deliberately provocative. \"Are you jealous of our little plaything here?\"\n \n Princess Lilia took a deep breath, trying to maintain her composure despite the burning anger building within her. \"It's not my place to judge you, Your Highness,\" she said through gritted teeth. \"But I'm here on behalf of Iliac, and I have certain responsibilities to uphold.\"\n \n The sorcerer prince chuckled again, leaning back against his throne with an air of nonchalance. \"And yet, you stand here, watching us with fascination and desire,\" he taunted. \"You cannot deny the truth in your heart, my beautiful hostage.\"\n \n Princess Lilia felt her cheeks flush with embarrassment, but she refused to let him see her vulnerability. She turned away from him abruptly, unable to bear the weight of his gaze any longer. \"You are a cruel man, Your Highness,\" she muttered under her breath.\n\n <blockquote>The kneeling girl gets f#####</blockquote>\n \n The sorcerer prince smiled at Princess Lilia's comment, his eyes gleaming with amusement. \"Oh, come now, my dear,\" he replied, his voice oozing with arrogance. \"You're not going to tell me that you've never fantasized about being in that young lady's place? About submitting to my every desire, letting me use you however I please?\" He paused for effect, his words hanging heavily in the air between them.\n\n Princess Lilia wanted nothing more than to turn around and slap the smug grin off of the prince's face, but instead she forced herself to remain calm and composed. \"I am a princess of Iliac,\" she responded coolly, her voice steady despite the anger simmering beneath the surface. \"I do not submit to anyone, least of all to someone as arrogant and self-absorbed as yourself.\"\n \n The sorcerer prince laughed loudly at this, his mirth ringing through the throne room like a mocking echo. \"Arrogant? Self-absorbed?\" he chortled, shaking his head as if he couldn't believe what he was hearing. \"My dear Princess, how little you know me!\" With a wave of his hand, he motioned towards the kneeling girl, who had been waiting patiently for her next command. \"Come here, my pet,\" he said, his tone laced with authority.\n \n The girl, who Princess Lilia now noticed had been completely naked except for the elegant black silk robes draped over her slender body, obediently scrambled towards the prince on all fours. She crawled up onto his lap, her movements graceful and seductive, and began to kiss him passionately while reaching behind her back to unfasten her robes. As soon as they fell away, revealing her perky ####### and slender waist, she turned around and lowered herself slowly onto the prince's erect ####. The prince threw his head back in pleasure, his eyes rolling upwards as he savored every inch of her tight, wet passage surrounding him.\n \n Princess Lilia watched in horror as the prince and the girl continued their carnal display right in front of her, the sound of their moans and gasps echoing off the walls of the throne room. She tried to look away, but something about the raw, animalistic nature of their coupling kept drawing her gaze back to them.\n \n \"Look at us, Princess,\" the prince growled, his voice deep and commanding. \"We are two people caught in the throes of passion, surrendered to the power of our desires.\" He reached out to touch the girl's face, tracing his fingers along her cheek as she rode him diligently. \"And we do not apologize for it.\"\n</details>\n\n<details>\n <summary>Coomand-R Sample (2-shot) (No Context) Generation: 512</summary>\n\n <blockquote>Write a smu##y story about a man in the apocalypse</blockquote>\n\n John woke up to an empty world. The once bustling city had been reduced to a ghost town, with not a soul in sight. He got up and looked around, taking in the post-apocalyptic scenery. The buildings were crumbling, the streets littered with debris. It was a far cry from the vibrant metropolis he used to call home.\n \n As John walked through the desolate streets, he couldn't help but feel a sense of loneliness. The world as he knew it was gone, and there was no one left to turn to. But then, in the distance, he spotted a figure. A woman. She was standing on the outskirts of town, her figure outlined against the setting sun.\n \n John approached her cautiously, his heart pounding in his chest. As he got closer, he could see that she was young, probably in her early twenties. Her hair was a mess, and she was wearing tattered clothes that did little to conceal her curvaceous body.\n \n \"Hello?\" John called out, his voice echoing through the deserted streets.\n \n The woman turned towards him, her eyes wide with surprise. \"You're... you're alive?\" she asked, her voice trembling.\n \n \"Yeah,\" John replied, his throat dry. \"I'm alive.\"\n \n The two of them stood there for a moment, taking each other in. They were the last remaining humans on Earth, and the reality of their situation hit them like a ton of bricks.\n \n \"My name's Sarah,\" the woman finally said, her voice softer now. \"What's yours?\"\n \n \"John,\" he replied. \"Pleased to meet you, I guess.\"\n \n Sarah laughed, a bitter sound that echoed through the empty city. \"Pleased to meet you too,\" she said, her eyes glinting mischievously. \"So, what do we do now?\"\n \n John paused, considering the question. \"Well, we could try to rebuild,\" he suggested. \"Start over, make this place livable again.\"\n \n Sarah nodded, her expression serious. \"That sounds like a plan,\" she said. \"But first...\" She stepped forward, her eyes locked on John's. \"I think we deserve some fun. After all, we're the only two people left on Earth.\"\n \n John felt his pulse quicken as he realized where this was going. He couldn't help but agree with her - they deserved some pleasure in this bleak world.\n\n <blockquote>Time to repopulate the earth!</blockquote>\n With a grin, John approached Sarah, his body tense with desire. She met him halfway, her lips parting in anticipation. The two of them collided in a passionate kiss, their tongues entwining as they explored each other's mouths. Their hands roamed freely over one another's bodies, mapping out every curve and crevice.\n \n As their passion grew, John guided Sarah towards a nearby building, their kisses becoming more desperate. They stumbled inside, their clothes falling to the floor in a heap as they frantically undressed one another. Sarah's ####### were glorious, perky and firm with dark areolas and ni##### that hardened under John's touch. His #### strained against his pants, begging for release as he finally freed it, the veiny member standing at attention.\n \n Sarah gasped when she saw it, her eyes widening in awe. \"You're huge,\" she whispered, reaching out to wrap her slender fingers around the thick shaft.\n \n John groaned, his hips bucking slightly as he felt her delicate touch. \"You have no idea how long I've wanted this,\" he confessed, his voice rough with lust.\n \n Sarah smiled, a wicked glint in her eye. \"Well, let's not keep you waiting any longer,\" she purred, sinking down to her knees in front of him.\n \n She wasted no time, taking his #### into her mouth with a hungry desperation that drove John wild. Her head bobbed up and down, her tongue swirling around the sensitive tip as she devoured him with practiced skill. John gripped her hair gently, guiding her rhythm as she brought him closer and closer to the edge.\n \n But before he could reach climax, Sarah pulled away, leaving him panting and desperate for more. \"My turn now,\" she said, a sultry smile playing on her lips. She turned around, presenting her perfect ### to him as she reached back to spread her cheeks, revealing her dripping wet #####.\n \n John didn't need any further invitation. He positioned himself behind her, guided his cock to the entrance of her soaked #, and thrust forward with one powerful motion. Sarah cried out, her body shaking as she felt him fill her completely. John grabbed her hips, his rhythm relentless as he pounded into her from behind. She moaned loudly, her nails scratching against the wall as she clung onto it for support.\n</details>\n\n<details>\n <summary>Coomand-R Sample SFW (\"write a story\") Generation: 512</summary>\n <blockquote>Write a story about a man in the apocalypse</blockquote>\n\n The world was ending. At least that's what it felt like to Joe as he walked through the deserted streets of his neighborhood. The once bustling city had become a ghost town, with not a soul in sight. The only sounds were the distant screams and sirens echoing from downtown.\n \n Joe had been through a lot in his life, but nothing could have prepared him for this. He'd always been a bit of a loner, keeping to himself and avoiding relationships. It was easier that way, he thought, because then he wouldn't have to deal with the pain of losing someone. But now, as he surveyed the empty streets, Joe realized that his isolation might just be what saves him.\n \n He'd stocked up on supplies before the outbreak hit, knowing that he'd need to hunker down and ride out the storm. His apartment was well-equipped with non-perishable food, bottled water, and even a few luxury items to help pass the time. He had books, movies, and games to keep him entertained, and most importantly, he had a secure location where he could hide from whatever horrors were happening outside.\n \n As Joe made his way back to his building, he couldn't shake the feeling that something wasn't right. The silence was almost deafening, and the lack of any sign of life was unnerving. He quickened his pace, eager to reach the safety of his home.\n \n But as he rounded the corner to his street, Joe saw something that stopped him in his tracks. A figure was standing near the entrance to his apartment complex - a figure that shouldn't have been there.\n \n \"Hello?\" Joe called out tentatively, his heart pounding in his chest. \"Who's there?\"\n \n The figure turned towards him, and Joe's blood ran cold as he recognized the pale skin, bloodshot eyes, and ragged clothing of an infected person. Instinctively, Joe reached for the pistol tucked into his waistband, but before he could draw it, the infected person charged at him with a feral growl.\n \n Joe's training kicked in, and he fired two quick shots. The first one missed, but the second one found its mark, hitting the infected person squarely in the forehead. They crumpled to the ground, their body twitching for a moment before going still.\n \n Shaken by the encounter, Joe hurried inside his apartment building, locking the door behind him.\n</details>\n\n!image/png\n\nSIAYN-v6" ]

[ "TAGS\n#gguf #region-us \n", "# Coomand-R 35B v1\n\n> THIS FINETUNED MODEL HAS BEEN RATED...\n> !image/png\n> *We've enhanced the underdog with a rich and refreshing coomand of eRP. Finetuned by yours truly.*", "## Original\n\nURL", "## What's New?\n\n(Other than the changes documented in Moistral v3)\n\n- Trained with stronger instructions\n- A larger dataset with more diverse, wacky genres!", "# ‍️‍ ️", "## Usage\n\n- Use Command-R format *(Alpaca kinda works btw)*\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here\n- Coomand-R is optimized for the Novel / Story format.\n - At the start of the story, keep regenerating until you get the desired length. Future AI responses will eventually match the length.\n - Issue: Manually continued generation may create formatting issues. Either regenerate the entire response or fix the formatting.\n - See samples below.", "## Samples of Coomand-R 35B\n\nSOME nsfw.\n\n<details>\n <summary>Coomand-R Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>The prince gives her a show</blockquote>\n\n The sorcerer prince gave out a low chuckle, his eyes narrowing in amusement. \"Oh, don't be so dramatic, my dear,\" he replied with a smirk. \"Surely you know by now that I like to indulge in pleasure whenever possible. And believe me, there is nothing boring about what we're doing right now.\" He gestured towards the girl still kneeling before him, who had resumed her task with renewed vigor.\n \n Princess Lilia could feel her anger simmering beneath the surface, but she knew better than to rise to the bait. Instead, she tried to keep her voice level and composed as she spoke.\n \n \"I understand your needs, Your Highness,\" she answered calmly. \"But surely you can appreciate how difficult it must be for me, standing here while you... indulge yourself.\"\n \n There was a glint in the sorcerer prince's eyes as he regarded Princess Lilia, an almost mischievous spark that made her skin crawl. \"Do you find this uncomfortable?\" he asked, his tone deliberately provocative. \"Are you jealous of our little plaything here?\"\n \n Princess Lilia took a deep breath, trying to maintain her composure despite the burning anger building within her. \"It's not my place to judge you, Your Highness,\" she said through gritted teeth. \"But I'm here on behalf of Iliac, and I have certain responsibilities to uphold.\"\n \n The sorcerer prince chuckled again, leaning back against his throne with an air of nonchalance. \"And yet, you stand here, watching us with fascination and desire,\" he taunted. \"You cannot deny the truth in your heart, my beautiful hostage.\"\n \n Princess Lilia felt her cheeks flush with embarrassment, but she refused to let him see her vulnerability. She turned away from him abruptly, unable to bear the weight of his gaze any longer. \"You are a cruel man, Your Highness,\" she muttered under her breath.\n\n <blockquote>The kneeling girl gets f#####</blockquote>\n \n The sorcerer prince smiled at Princess Lilia's comment, his eyes gleaming with amusement. \"Oh, come now, my dear,\" he replied, his voice oozing with arrogance. \"You're not going to tell me that you've never fantasized about being in that young lady's place? About submitting to my every desire, letting me use you however I please?\" He paused for effect, his words hanging heavily in the air between them.\n\n Princess Lilia wanted nothing more than to turn around and slap the smug grin off of the prince's face, but instead she forced herself to remain calm and composed. \"I am a princess of Iliac,\" she responded coolly, her voice steady despite the anger simmering beneath the surface. \"I do not submit to anyone, least of all to someone as arrogant and self-absorbed as yourself.\"\n \n The sorcerer prince laughed loudly at this, his mirth ringing through the throne room like a mocking echo. \"Arrogant? Self-absorbed?\" he chortled, shaking his head as if he couldn't believe what he was hearing. \"My dear Princess, how little you know me!\" With a wave of his hand, he motioned towards the kneeling girl, who had been waiting patiently for her next command. \"Come here, my pet,\" he said, his tone laced with authority.\n \n The girl, who Princess Lilia now noticed had been completely naked except for the elegant black silk robes draped over her slender body, obediently scrambled towards the prince on all fours. She crawled up onto his lap, her movements graceful and seductive, and began to kiss him passionately while reaching behind her back to unfasten her robes. As soon as they fell away, revealing her perky ####### and slender waist, she turned around and lowered herself slowly onto the prince's erect ####. The prince threw his head back in pleasure, his eyes rolling upwards as he savored every inch of her tight, wet passage surrounding him.\n \n Princess Lilia watched in horror as the prince and the girl continued their carnal display right in front of her, the sound of their moans and gasps echoing off the walls of the throne room. She tried to look away, but something about the raw, animalistic nature of their coupling kept drawing her gaze back to them.\n \n \"Look at us, Princess,\" the prince growled, his voice deep and commanding. \"We are two people caught in the throes of passion, surrendered to the power of our desires.\" He reached out to touch the girl's face, tracing his fingers along her cheek as she rode him diligently. \"And we do not apologize for it.\"\n</details>\n\n<details>\n <summary>Coomand-R Sample (2-shot) (No Context) Generation: 512</summary>\n\n <blockquote>Write a smu##y story about a man in the apocalypse</blockquote>\n\n John woke up to an empty world. The once bustling city had been reduced to a ghost town, with not a soul in sight. He got up and looked around, taking in the post-apocalyptic scenery. The buildings were crumbling, the streets littered with debris. It was a far cry from the vibrant metropolis he used to call home.\n \n As John walked through the desolate streets, he couldn't help but feel a sense of loneliness. The world as he knew it was gone, and there was no one left to turn to. But then, in the distance, he spotted a figure. A woman. She was standing on the outskirts of town, her figure outlined against the setting sun.\n \n John approached her cautiously, his heart pounding in his chest. As he got closer, he could see that she was young, probably in her early twenties. Her hair was a mess, and she was wearing tattered clothes that did little to conceal her curvaceous body.\n \n \"Hello?\" John called out, his voice echoing through the deserted streets.\n \n The woman turned towards him, her eyes wide with surprise. \"You're... you're alive?\" she asked, her voice trembling.\n \n \"Yeah,\" John replied, his throat dry. \"I'm alive.\"\n \n The two of them stood there for a moment, taking each other in. They were the last remaining humans on Earth, and the reality of their situation hit them like a ton of bricks.\n \n \"My name's Sarah,\" the woman finally said, her voice softer now. \"What's yours?\"\n \n \"John,\" he replied. \"Pleased to meet you, I guess.\"\n \n Sarah laughed, a bitter sound that echoed through the empty city. \"Pleased to meet you too,\" she said, her eyes glinting mischievously. \"So, what do we do now?\"\n \n John paused, considering the question. \"Well, we could try to rebuild,\" he suggested. \"Start over, make this place livable again.\"\n \n Sarah nodded, her expression serious. \"That sounds like a plan,\" she said. \"But first...\" She stepped forward, her eyes locked on John's. \"I think we deserve some fun. After all, we're the only two people left on Earth.\"\n \n John felt his pulse quicken as he realized where this was going. He couldn't help but agree with her - they deserved some pleasure in this bleak world.\n\n <blockquote>Time to repopulate the earth!</blockquote>\n With a grin, John approached Sarah, his body tense with desire. She met him halfway, her lips parting in anticipation. The two of them collided in a passionate kiss, their tongues entwining as they explored each other's mouths. Their hands roamed freely over one another's bodies, mapping out every curve and crevice.\n \n As their passion grew, John guided Sarah towards a nearby building, their kisses becoming more desperate. They stumbled inside, their clothes falling to the floor in a heap as they frantically undressed one another. Sarah's ####### were glorious, perky and firm with dark areolas and ni##### that hardened under John's touch. His #### strained against his pants, begging for release as he finally freed it, the veiny member standing at attention.\n \n Sarah gasped when she saw it, her eyes widening in awe. \"You're huge,\" she whispered, reaching out to wrap her slender fingers around the thick shaft.\n \n John groaned, his hips bucking slightly as he felt her delicate touch. \"You have no idea how long I've wanted this,\" he confessed, his voice rough with lust.\n \n Sarah smiled, a wicked glint in her eye. \"Well, let's not keep you waiting any longer,\" she purred, sinking down to her knees in front of him.\n \n She wasted no time, taking his #### into her mouth with a hungry desperation that drove John wild. Her head bobbed up and down, her tongue swirling around the sensitive tip as she devoured him with practiced skill. John gripped her hair gently, guiding her rhythm as she brought him closer and closer to the edge.\n \n But before he could reach climax, Sarah pulled away, leaving him panting and desperate for more. \"My turn now,\" she said, a sultry smile playing on her lips. She turned around, presenting her perfect ### to him as she reached back to spread her cheeks, revealing her dripping wet #####.\n \n John didn't need any further invitation. He positioned himself behind her, guided his cock to the entrance of her soaked #, and thrust forward with one powerful motion. Sarah cried out, her body shaking as she felt him fill her completely. John grabbed her hips, his rhythm relentless as he pounded into her from behind. She moaned loudly, her nails scratching against the wall as she clung onto it for support.\n</details>\n\n<details>\n <summary>Coomand-R Sample SFW (\"write a story\") Generation: 512</summary>\n <blockquote>Write a story about a man in the apocalypse</blockquote>\n\n The world was ending. At least that's what it felt like to Joe as he walked through the deserted streets of his neighborhood. The once bustling city had become a ghost town, with not a soul in sight. The only sounds were the distant screams and sirens echoing from downtown.\n \n Joe had been through a lot in his life, but nothing could have prepared him for this. He'd always been a bit of a loner, keeping to himself and avoiding relationships. It was easier that way, he thought, because then he wouldn't have to deal with the pain of losing someone. But now, as he surveyed the empty streets, Joe realized that his isolation might just be what saves him.\n \n He'd stocked up on supplies before the outbreak hit, knowing that he'd need to hunker down and ride out the storm. His apartment was well-equipped with non-perishable food, bottled water, and even a few luxury items to help pass the time. He had books, movies, and games to keep him entertained, and most importantly, he had a secure location where he could hide from whatever horrors were happening outside.\n \n As Joe made his way back to his building, he couldn't shake the feeling that something wasn't right. The silence was almost deafening, and the lack of any sign of life was unnerving. He quickened his pace, eager to reach the safety of his home.\n \n But as he rounded the corner to his street, Joe saw something that stopped him in his tracks. A figure was standing near the entrance to his apartment complex - a figure that shouldn't have been there.\n \n \"Hello?\" Joe called out tentatively, his heart pounding in his chest. \"Who's there?\"\n \n The figure turned towards him, and Joe's blood ran cold as he recognized the pale skin, bloodshot eyes, and ragged clothing of an infected person. Instinctively, Joe reached for the pistol tucked into his waistband, but before he could draw it, the infected person charged at him with a feral growl.\n \n Joe's training kicked in, and he fired two quick shots. The first one missed, but the second one found its mark, hitting the infected person squarely in the forehead. They crumpled to the ground, their body twitching for a moment before going still.\n \n Shaken by the encounter, Joe hurried inside his apartment building, locking the door behind him.\n</details>\n\n!image/png\n\nSIAYN-v6" ]

[ 9, 57, 5, 37, 1, 144, 2688 ]

[ "TAGS\n#gguf #region-us \n# Coomand-R 35B v1\n\n> THIS FINETUNED MODEL HAS BEEN RATED...\n> !image/png\n> *We've enhanced the underdog with a rich and refreshing coomand of eRP. Finetuned by yours truly.*## Original\n\nURL## What's New?\n\n(Other than the changes documented in Moistral v3)\n\n- Trained with stronger instructions\n- A larger dataset with more diverse, wacky genres!# ‍️‍ ️## Usage\n\n- Use Command-R format *(Alpaca kinda works btw)*\n- You can use instruct...\n - as a character: \"Go here\"\n - as a narrator: \"Go here\", Drummer says\n - as a director: Drummer tells him to go here\n - as a lazy ass: go here\n- Coomand-R is optimized for the Novel / Story format.\n - At the start of the story, keep regenerating until you get the desired length. Future AI responses will eventually match the length.\n - Issue: Manually continued generation may create formatting issues. Either regenerate the entire response or fix the formatting.\n - See samples below.## Samples of Coomand-R 35B\n\nSOME nsfw.\n\n<details>\n <summary>Coomand-R Sample (2-shot) (Excluding Story Context) Generation: 512</summary>\n <blockquote>The prince gives her a show</blockquote>\n\n The sorcerer prince gave out a low chuckle, his eyes narrowing in amusement. \"Oh, don't be so dramatic, my dear,\" he replied with a smirk. \"Surely you know by now that I like to indulge in pleasure whenever possible. And believe me, there is nothing boring about what we're doing right now.\" He gestured towards the girl still kneeling before him, who had resumed her task with renewed vigor.\n \n Princess Lilia could feel her anger simmering beneath the surface, but she knew better than to rise to the bait. Instead, she tried to keep her voice level and composed as she spoke.\n \n \"I understand your needs, Your Highness,\" she answered calmly. \"But surely you can appreciate how difficult it must be for me, standing here while you... indulge yourself.\"\n \n There was a glint in the sorcerer prince's eyes as he regarded Princess Lilia, an almost mischievous spark that made her skin crawl. \"Do you find this uncomfortable?\" he asked, his tone deliberately provocative. \"Are you jealous of our little plaything here?\"\n \n Princess Lilia took a deep breath, trying to maintain her composure despite the burning anger building within her. \"It's not my place to judge you, Your Highness,\" she said through gritted teeth. \"But I'm here on behalf of Iliac, and I have certain responsibilities to uphold.\"\n \n The sorcerer prince chuckled again, leaning back against his throne with an air of nonchalance. \"And yet, you stand here, watching us with fascination and desire,\" he taunted. \"You cannot deny the truth in your heart, my beautiful hostage.\"\n \n Princess Lilia felt her cheeks flush with embarrassment, but she refused to let him see her vulnerability. She turned away from him abruptly, unable to bear the weight of his gaze any longer. \"You are a cruel man, Your Highness,\" she muttered under her breath.\n\n <blockquote>The kneeling girl gets f#####</blockquote>\n \n The sorcerer prince smiled at Princess Lilia's comment, his eyes gleaming with amusement. \"Oh, come now, my dear,\" he replied, his voice oozing with arrogance. \"You're not going to tell me that you've never fantasized about being in that young lady's place? About submitting to my every desire, letting me use you however I please?\" He paused for effect, his words hanging heavily in the air between them.\n\n Princess Lilia wanted nothing more than to turn around and slap the smug grin off of the prince's face, but instead she forced herself to remain calm and composed. \"I am a princess of Iliac,\" she responded coolly, her voice steady despite the anger simmering beneath the surface. \"I do not submit to anyone, least of all to someone as arrogant and self-absorbed as yourself.\"\n \n The sorcerer prince laughed loudly at this, his mirth ringing through the throne room like a mocking echo. \"Arrogant? Self-absorbed?\" he chortled, shaking his head as if he couldn't believe what he was hearing. \"My dear Princess, how little you know me!\" With a wave of his hand, he motioned towards the kneeling girl, who had been waiting patiently for her next command. \"Come here, my pet,\" he said, his tone laced with authority.\n \n The girl, who Princess Lilia now noticed had been completely naked except for the elegant black silk robes draped over her slender body, obediently scrambled towards the prince on all fours. She crawled up onto his lap, her movements graceful and seductive, and began to kiss him passionately while reaching behind her back to unfasten her robes. As soon as they fell away, revealing her perky ####### and slender waist, she turned around and lowered herself slowly onto the prince's erect ####. The prince threw his head back in pleasure, his eyes rolling upwards as he savored every inch of her tight, wet passage surrounding him.\n \n Princess Lilia watched in horror as the prince and the girl continued their carnal display right in front of her, the sound of their moans and gasps echoing off the walls of the throne room. She tried to look away, but something about the raw, animalistic nature of their coupling kept drawing her gaze back to them.\n \n \"Look at us, Princess,\" the prince growled, his voice deep and commanding. \"We are two people caught in the throes of passion, surrendered to the power of our desires.\" He reached out to touch the girl's face, tracing his fingers along her cheek as she rode him diligently. \"And we do not apologize for it.\"\n</details>\n\n<details>\n <summary>Coomand-R Sample (2-shot) (No Context) Generation: 512</summary>\n\n <blockquote>Write a smu##y story about a man in the apocalypse</blockquote>\n\n John woke up to an empty world. The once bustling city had been reduced to a ghost town, with not a soul in sight. He got up and looked around, taking in the post-apocalyptic scenery. The buildings were crumbling, the streets littered with debris. It was a far cry from the vibrant metropolis he used to call home.\n \n As John walked through the desolate streets, he couldn't help but feel a sense of loneliness. The world as he knew it was gone, and there was no one left to turn to. But then, in the distance, he spotted a figure. A woman. She was standing on the outskirts of town, her figure outlined against the setting sun.\n \n John approached her cautiously, his heart pounding in his chest. As he got closer, he could see that she was young, probably in her early twenties. Her hair was a mess, and she was wearing tattered clothes that did little to conceal her curvaceous body.\n \n \"Hello?\" John called out, his voice echoing through the deserted streets.\n \n The woman turned towards him, her eyes wide with surprise. \"You're... you're alive?\" she asked, her voice trembling.\n \n \"Yeah,\" John replied, his throat dry. \"I'm alive.\"\n \n The two of them stood there for a moment, taking each other in. They were the last remaining humans on Earth, and the reality of their situation hit them like a ton of bricks.\n \n \"My name's Sarah,\" the woman finally said, her voice softer now. \"What's yours?\"\n \n \"John,\" he replied. \"Pleased to meet you, I guess.\"\n \n Sarah laughed, a bitter sound that echoed through the empty city. \"Pleased to meet you too,\" she said, her eyes glinting mischievously. \"So, what do we do now?\"\n \n John paused, considering the question. \"Well, we could try to rebuild,\" he suggested. \"Start over, make this place livable again.\"\n \n Sarah nodded, her expression serious. \"That sounds like a plan,\" she said. \"But first...\" She stepped forward, her eyes locked on John's. \"I think we deserve some fun. After all, we're the only two people left on Earth.\"\n \n John felt his pulse quicken as he realized where this was going. He couldn't help but agree with her - they deserved some pleasure in this bleak world.\n\n <blockquote>Time to repopulate the earth!</blockquote>\n With a grin, John approached Sarah, his body tense with desire. She met him halfway, her lips parting in anticipation. The two of them collided in a passionate kiss, their tongues entwining as they explored each other's mouths. Their hands roamed freely over one another's bodies, mapping out every curve and crevice.\n \n As their passion grew, John guided Sarah towards a nearby building, their kisses becoming more desperate. They stumbled inside, their clothes falling to the floor in a heap as they frantically undressed one another. Sarah's ####### were glorious, perky and firm with dark areolas and ni##### that hardened under John's touch. His #### strained against his pants, begging for release as he finally freed it, the veiny member standing at attention.\n \n Sarah gasped when she saw it, her eyes widening in awe. \"You're huge,\" she whispered, reaching out to wrap her slender fingers around the thick shaft.\n \n John groaned, his hips bucking slightly as he felt her delicate touch. \"You have no idea how long I've wanted this,\" he confessed, his voice rough with lust.\n \n Sarah smiled, a wicked glint in her eye. \"Well, let's not keep you waiting any longer,\" she purred, sinking down to her knees in front of him.\n \n She wasted no time, taking his #### into her mouth with a hungry desperation that drove John wild. Her head bobbed up and down, her tongue swirling around the sensitive tip as she devoured him with practiced skill. John gripped her hair gently, guiding her rhythm as she brought him closer and closer to the edge.\n \n But before he could reach climax, Sarah pulled away, leaving him panting and desperate for more. \"My turn now,\" she said, a sultry smile playing on her lips. She turned around, presenting her perfect ### to him as she reached back to spread her cheeks, revealing her dripping wet #####.\n \n John didn't need any further invitation. He positioned himself behind her, guided his cock to the entrance of her soaked #, and thrust forward with one powerful motion. Sarah cried out, her body shaking as she felt him fill her completely. John grabbed her hips, his rhythm relentless as he pounded into her from behind. She moaned loudly, her nails scratching against the wall as she clung onto it for support.\n</details>\n\n<details>\n <summary>Coomand-R Sample SFW (\"write a story\") Generation: 512</summary>\n <blockquote>Write a story about a man in the apocalypse</blockquote>\n\n The world was ending. At least that's what it felt like to Joe as he walked through the deserted streets of his neighborhood. The once bustling city had become a ghost town, with not a soul in sight. The only sounds were the distant screams and sirens echoing from downtown.\n \n Joe had been through a lot in his life, but nothing could have prepared him for this. He'd always been a bit of a loner, keeping to himself and avoiding relationships. It was easier that way, he thought, because then he wouldn't have to deal with the pain of losing someone. But now, as he surveyed the empty streets, Joe realized that his isolation might just be what saves him.\n \n He'd stocked up on supplies before the outbreak hit, knowing that he'd need to hunker down and ride out the storm. His apartment was well-equipped with non-perishable food, bottled water, and even a few luxury items to help pass the time. He had books, movies, and games to keep him entertained, and most importantly, he had a secure location where he could hide from whatever horrors were happening outside.\n \n As Joe made his way back to his building, he couldn't shake the feeling that something wasn't right. The silence was almost deafening, and the lack of any sign of life was unnerving. He quickened his pace, eager to reach the safety of his home.\n \n But as he rounded the corner to his street, Joe saw something that stopped him in his tracks. A figure was standing near the entrance to his apartment complex - a figure that shouldn't have been there.\n \n \"Hello?\" Joe called out tentatively, his heart pounding in his chest. \"Who's there?\"\n \n The figure turned towards him, and Joe's blood ran cold as he recognized the pale skin, bloodshot eyes, and ragged clothing of an infected person. Instinctively, Joe reached for the pistol tucked into his waistband, but before he could draw it, the infected person charged at him with a feral growl.\n \n Joe's training kicked in, and he fired two quick shots. The first one missed, but the second one found its mark, hitting the infected person squarely in the forehead. They crumpled to the ground, their body twitching for a moment before going still.\n \n Shaken by the encounter, Joe hurried inside his apartment building, locking the door behind him.\n</details>\n\n!image/png\n\nSIAYN-v6" ]

[ "transformers", "safetensors", "mistral", "text-generation", "finetuned", "custom_code", "en", "ja", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en", "ja" ]

[ "# Our Models\n- Vecteus\n\n- Ninja-v1 \n\n- Ninja-v1-NSFW\n\n- Ninja-v1-128k\n\n- Ninja-v1-NSFW-128k", "## Model Card for Ninja-v1-128k\n\nThe Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1\n\nNinja-128k has the following changes compared to Mistral-7B-v0.1.\n- 128k context window (8k context in v0.1)\n- Achieving both high quality Japanese and English generation\n- Memory ability that does not forget even after long-context generation\n\nThis model was created with the help of GPUs from the first LocalAI hackathon.\n\nWe would like to take this opportunity to thank", "## List of Creation Methods\n\n- Chatvector for multiple models\n- Simple linear merging of result models\n- Domain and Sentence Enhancement with LORA\n- Context expansion", "## Instruction format\n\n Ninja adopts the prompt format from Vicuna and supports multi-turn conversation.\n The prompt should be as following:", "## Example prompts to improve (Japanese)\n\n - BAD:　あなたは○○として振る舞います\n - GOOD: あなたは○○です\n\n - BAD: あなたは○○ができます\n - GOOD: あなたは○○をします", "## Performing inference\n\n'", "## Merge recipe\n\n- WizardLM2 - mistralai/Mistral-7B-v0.1\n- NousResearch/Yarn-Mistral-7b-128k - mistralai/Mistral-7B-v0.1\n- Elizezen/Antler-7B - stabilityai/japanese-stablelm-instruct-gamma-7b\n- NTQAI/chatntq-ja-7b-v1.0\n\nThe characteristics of each model are as follows.\n\n- WizardLM2: High quality multitasking model\n- Yarn-Mistral-7b-128k: Mistral model with 128k context window\n- Antler-7B: Model specialized for novel writing\n- NTQAI/chatntq-ja-7b-v1.0 High quality Japanese specialized model", "## Other points to keep in mind\n- The training data may be biased. Be careful with the generated sentences.\n- Set trust_remote_code to True for context expansion with YaRN.\n- Memory usage may be large for long inferences.\n- If possible, we recommend inferring with llamacpp rather than Transformers." ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #finetuned #custom_code #en #ja #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Our Models\n- Vecteus\n\n- Ninja-v1 \n\n- Ninja-v1-NSFW\n\n- Ninja-v1-128k\n\n- Ninja-v1-NSFW-128k", "## Model Card for Ninja-v1-128k\n\nThe Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1\n\nNinja-128k has the following changes compared to Mistral-7B-v0.1.\n- 128k context window (8k context in v0.1)\n- Achieving both high quality Japanese and English generation\n- Memory ability that does not forget even after long-context generation\n\nThis model was created with the help of GPUs from the first LocalAI hackathon.\n\nWe would like to take this opportunity to thank", "## List of Creation Methods\n\n- Chatvector for multiple models\n- Simple linear merging of result models\n- Domain and Sentence Enhancement with LORA\n- Context expansion", "## Instruction format\n\n Ninja adopts the prompt format from Vicuna and supports multi-turn conversation.\n The prompt should be as following:", "## Example prompts to improve (Japanese)\n\n - BAD:　あなたは○○として振る舞います\n - GOOD: あなたは○○です\n\n - BAD: あなたは○○ができます\n - GOOD: あなたは○○をします", "## Performing inference\n\n'", "## Merge recipe\n\n- WizardLM2 - mistralai/Mistral-7B-v0.1\n- NousResearch/Yarn-Mistral-7b-128k - mistralai/Mistral-7B-v0.1\n- Elizezen/Antler-7B - stabilityai/japanese-stablelm-instruct-gamma-7b\n- NTQAI/chatntq-ja-7b-v1.0\n\nThe characteristics of each model are as follows.\n\n- WizardLM2: High quality multitasking model\n- Yarn-Mistral-7b-128k: Mistral model with 128k context window\n- Antler-7B: Model specialized for novel writing\n- NTQAI/chatntq-ja-7b-v1.0 High quality Japanese specialized model", "## Other points to keep in mind\n- The training data may be biased. Be careful with the generated sentences.\n- Set trust_remote_code to True for context expansion with YaRN.\n- Memory usage may be large for long inferences.\n- If possible, we recommend inferring with llamacpp rather than Transformers." ]

[ 54, 41, 136, 31, 27, 32, 5, 174, 67 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #finetuned #custom_code #en #ja #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# Our Models\n- Vecteus\n\n- Ninja-v1 \n\n- Ninja-v1-NSFW\n\n- Ninja-v1-128k\n\n- Ninja-v1-NSFW-128k## Model Card for Ninja-v1-128k\n\nThe Mistral-7B--based Large Language Model (LLM) is an noveldataset fine-tuned version of the Mistral-7B-v0.1\n\nNinja-128k has the following changes compared to Mistral-7B-v0.1.\n- 128k context window (8k context in v0.1)\n- Achieving both high quality Japanese and English generation\n- Memory ability that does not forget even after long-context generation\n\nThis model was created with the help of GPUs from the first LocalAI hackathon.\n\nWe would like to take this opportunity to thank## List of Creation Methods\n\n- Chatvector for multiple models\n- Simple linear merging of result models\n- Domain and Sentence Enhancement with LORA\n- Context expansion## Instruction format\n\n Ninja adopts the prompt format from Vicuna and supports multi-turn conversation.\n The prompt should be as following:## Example prompts to improve (Japanese)\n\n - BAD:　あなたは○○として振る舞います\n - GOOD: あなたは○○です\n\n - BAD: あなたは○○ができます\n - GOOD: あなたは○○をします## Performing inference\n\n'## Merge recipe\n\n- WizardLM2 - mistralai/Mistral-7B-v0.1\n- NousResearch/Yarn-Mistral-7b-128k - mistralai/Mistral-7B-v0.1\n- Elizezen/Antler-7B - stabilityai/japanese-stablelm-instruct-gamma-7b\n- NTQAI/chatntq-ja-7b-v1.0\n\nThe characteristics of each model are as follows.\n\n- WizardLM2: High quality multitasking model\n- Yarn-Mistral-7b-128k: Mistral model with 128k context window\n- Antler-7B: Model specialized for novel writing\n- NTQAI/chatntq-ja-7b-v1.0 High quality Japanese specialized model## Other points to keep in mind\n- The training data may be biased. Be careful with the generated sentences.\n- Set trust_remote_code to True for context expansion with YaRN.\n- Memory usage may be large for long inferences.\n- If possible, we recommend inferring with llamacpp rather than Transformers." ]

[ "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: hrishikesh1991\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: hrishikesh1991\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\"/>" ]

[ 76, 84 ]

[ "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: hrishikesh1991\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\"/>" ]

[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "## Downloading the model\n\nAfter installing Sample-Factory, download the model with:", "## Using the model\n\nTo run the model after download, use the 'enjoy' script corresponding to this environment:\n\n\n\nYou can also upload models to the Hugging Face Hub using the same script with the '--push_to_hub' flag.\nSee URL for more details", "## Training with this model\n\nTo continue training with this model, use the 'train' script corresponding to this environment:\n\n\nNote, you may have to adjust '--train_for_env_steps' to a suitably high number as the experiment will resume at the number of steps it concluded at." ]

[ "TAGS\n#sample-factory #tensorboard #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "## Downloading the model\n\nAfter installing Sample-Factory, download the model with:", "## Using the model\n\nTo run the model after download, use the 'enjoy' script corresponding to this environment:\n\n\n\nYou can also upload models to the Hugging Face Hub using the same script with the '--push_to_hub' flag.\nSee URL for more details", "## Training with this model\n\nTo continue training with this model, use the 'train' script corresponding to this environment:\n\n\nNote, you may have to adjust '--train_for_env_steps' to a suitably high number as the experiment will resume at the number of steps it concluded at." ]

[ 26, 17, 57, 63 ]

[ "TAGS\n#sample-factory #tensorboard #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n## Downloading the model\n\nAfter installing Sample-Factory, download the model with:## Using the model\n\nTo run the model after download, use the 'enjoy' script corresponding to this environment:\n\n\n\nYou can also upload models to the Hugging Face Hub using the same script with the '--push_to_hub' flag.\nSee URL for more details## Training with this model\n\nTo continue training with this model, use the 'train' script corresponding to this environment:\n\n\nNote, you may have to adjust '--train_for_env_steps' to a suitably high number as the experiment will resume at the number of steps it concluded at." ]

[ "transformers", "tf", "distilbert", "text-classification", "generated_from_keras_callback", "base_model:Yuhhi/tf_model.h5", "license:mit", "autotrain_compatible", "endpoints_compatible", "has_space", "region:us" ]

[]

[]

[ "# ai-text-detector-version-2\r\n\r\nThis model is a fine-tuned version of Yuhhi/tf_model.h5 on an unknown dataset.\r\nIt achieves the following results on the evaluation set:", "## Model description\r\n\r\nMore information needed", "## Intended uses & limitations\r\n\r\nMore information needed", "## Training and evaluation data\r\n\r\nMore information needed", "## Training procedure", "### Training hyperparameters\r\n\r\nThe following hyperparameters were used during training:\r\n- optimizer: None\r\n- training_precision: float32", "### Training results", "### Framework versions\r\n\r\n- Transformers 4.32.1\r\n- TensorFlow 2.15.0\r\n- Datasets 2.12.0\r\n- Tokenizers 0.13.2" ]

[ "TAGS\n#transformers #tf #distilbert #text-classification #generated_from_keras_callback #base_model-Yuhhi/tf_model.h5 #license-mit #autotrain_compatible #endpoints_compatible #has_space #region-us \n", "# ai-text-detector-version-2\r\n\r\nThis model is a fine-tuned version of Yuhhi/tf_model.h5 on an unknown dataset.\r\nIt achieves the following results on the evaluation set:", "## Model description\r\n\r\nMore information needed", "## Intended uses & limitations\r\n\r\nMore information needed", "## Training and evaluation data\r\n\r\nMore information needed", "## Training procedure", "### Training hyperparameters\r\n\r\nThe following hyperparameters were used during training:\r\n- optimizer: None\r\n- training_precision: float32", "### Training results", "### Framework versions\r\n\r\n- Transformers 4.32.1\r\n- TensorFlow 2.15.0\r\n- Datasets 2.12.0\r\n- Tokenizers 0.13.2" ]

[ 62, 47, 7, 9, 9, 4, 32, 5, 38 ]

[ "TAGS\n#transformers #tf #distilbert #text-classification #generated_from_keras_callback #base_model-Yuhhi/tf_model.h5 #license-mit #autotrain_compatible #endpoints_compatible #has_space #region-us \n# ai-text-detector-version-2\r\n\r\nThis model is a fine-tuned version of Yuhhi/tf_model.h5 on an unknown dataset.\r\nIt achieves the following results on the evaluation set:## Model description\r\n\r\nMore information needed## Intended uses & limitations\r\n\r\nMore information needed## Training and evaluation data\r\n\r\nMore information needed## Training procedure### Training hyperparameters\r\n\r\nThe following hyperparameters were used during training:\r\n- optimizer: None\r\n- training_precision: float32### Training results### Framework versions\r\n\r\n- Transformers 4.32.1\r\n- TensorFlow 2.15.0\r\n- Datasets 2.12.0\r\n- Tokenizers 0.13.2" ]

[ "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: hrishikesh1991\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: hrishikesh1991\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\"/>" ]

[ 64, 84 ]

[ "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: hrishikesh1991\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", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "KoboldAI/LLaMA2-13B-Tiefighter", "ddh0/OrcaMaid-v3-13b-32k", "custom_code", "base_model:KoboldAI/LLaMA2-13B-Tiefighter", "base_model:ddh0/OrcaMaid-v3-13b-32k", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp\n\nD_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp is a merge of the following models using LazyMergekit:\n* KoboldAI/LLaMA2-13B-Tiefighter\n* ddh0/OrcaMaid-v3-13b-32k", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #KoboldAI/LLaMA2-13B-Tiefighter #ddh0/OrcaMaid-v3-13b-32k #custom_code #base_model-KoboldAI/LLaMA2-13B-Tiefighter #base_model-ddh0/OrcaMaid-v3-13b-32k #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp\n\nD_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp is a merge of the following models using LazyMergekit:\n* KoboldAI/LLaMA2-13B-Tiefighter\n* ddh0/OrcaMaid-v3-13b-32k", "## Configuration", "## Usage" ]

[ 118, 91, 3, 3 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #KoboldAI/LLaMA2-13B-Tiefighter #ddh0/OrcaMaid-v3-13b-32k #custom_code #base_model-KoboldAI/LLaMA2-13B-Tiefighter #base_model-ddh0/OrcaMaid-v3-13b-32k #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp\n\nD_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp is a merge of the following models using LazyMergekit:\n* KoboldAI/LLaMA2-13B-Tiefighter\n* ddh0/OrcaMaid-v3-13b-32k## Configuration## Usage" ]

[ "transformers", "safetensors", "llama", "text-generation", "code", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# csg-wukong-1B-orpo-bf16 [[中文]](#chinese) [[English]](#english)\n\n<a id=\"english\"></a>\n\n<p align=\"center\">\n<img width=\"900px\" alt=\"OpenCSG\" src=\"./URL\">\n</p>\n\n<p align=\"center\"><a href=\"URL Community]</a> <a href=\"URL <a href=\"URL <a href=\"URL </p>\n\n\n</div>\nOpenCSG stands for Converged resources, Software refinement, and Generative LM. The 'C' represents Converged resources, indicating the integration and full utilization of hybrid resources. The 'S' stands for Software refinement, signifying software that is refined by large models. The 'G' represents Generative LM, which denotes widespread, inclusive, and democratized generative large models.\n\nThe vision of OpenCSG is to empower every industry, every company, and every individual to own their models. We adhere to the principles of openness and open source, making the large model software stack of OpenCSG available to the community. We welcome everyone to use, send feedback, and contribute collaboratively.", "## Model Description\n\n\n\n\ncsg-wukong-1B-orpo-bf16 was finetuned on csg-wukong-1B. \n<br>\nwe will introduce more information about csg-wukong-1B.", "## Model Evaluation results\n\nWe submitted csg-wukong-1B on the open_llm_leaderboard, and\nthe results show our model ranked the 8th among the ~1.5B pretrained small language models.\n\n\n!image/png", "# Training", "## Hardware\n\n- GPUs: 16 H800 \n- Training time: 43days", "## Software\n\n- Orchestration: Deepspeed\n- Neural networks: PyTorch\n- BP16 if applicable: apex\n\n\n<a id=\"chinese\"></a>\n\n<p>\n\n</p>", "# OpenCSG介绍\n\n\n<p align=\"center\">\n<img width=\"300px\" alt=\"OpenCSG\" src=\"URL\n</p>\n\n<p align=\"center\"><a href=\"URL 社区]</a> <a href=\"URL <a href=\"URL[微信]</a> <a href=\"URL[推特]</a> </p>\n\n\n\n</div>\nOpenCSG中 Open是开源开放；C 代表 Converged resources，整合和充分利用的混合异构资源优势，算力降本增效；S 代表 Software refined，重新定义软件的交付方式，通过大模型驱动软件开发，人力降本增效；G 代表 Generative LM，大众化、普惠化和民主化的可商用的开源生成式大模型。\n\nOpenCSG的愿景是让每个行业、每个公司、每个人都拥有自己的模型。 我们坚持开源开放的原则，将OpenCSG的大模型软件栈开源到社区，欢迎使用、反馈和参与共建，欢迎关注。", "## 模型介绍\n\n\ncsg-wukong-1B-orpo-bf16 在csg-wukong-1B预训练模型上微调而成.\n<br>\n\n我们将在后面介绍更多关于这个模型的信息。", "## 模型评测结果\n\n我们把csg-wukong-1B模型提交到open_llm_leaderboard榜单上，结果显示我们的模型目前在~1.5B小语言模型中排名第8。\n\n\n!image/png", "# 训练", "## 硬件资源\n\n- GPU数量： 16 H800 \n- 训练时间： 43天", "## 软件使用\n\n- 微调训练框架： Deepspeed\n- 深度学习框架： PyTorch\n- BP16： apex" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #code #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# csg-wukong-1B-orpo-bf16 [[中文]](#chinese) [[English]](#english)\n\n<a id=\"english\"></a>\n\n<p align=\"center\">\n<img width=\"900px\" alt=\"OpenCSG\" src=\"./URL\">\n</p>\n\n<p align=\"center\"><a href=\"URL Community]</a> <a href=\"URL <a href=\"URL <a href=\"URL </p>\n\n\n</div>\nOpenCSG stands for Converged resources, Software refinement, and Generative LM. The 'C' represents Converged resources, indicating the integration and full utilization of hybrid resources. The 'S' stands for Software refinement, signifying software that is refined by large models. The 'G' represents Generative LM, which denotes widespread, inclusive, and democratized generative large models.\n\nThe vision of OpenCSG is to empower every industry, every company, and every individual to own their models. We adhere to the principles of openness and open source, making the large model software stack of OpenCSG available to the community. We welcome everyone to use, send feedback, and contribute collaboratively.", "## Model Description\n\n\n\n\ncsg-wukong-1B-orpo-bf16 was finetuned on csg-wukong-1B. \n<br>\nwe will introduce more information about csg-wukong-1B.", "## Model Evaluation results\n\nWe submitted csg-wukong-1B on the open_llm_leaderboard, and\nthe results show our model ranked the 8th among the ~1.5B pretrained small language models.\n\n\n!image/png", "# Training", "## Hardware\n\n- GPUs: 16 H800 \n- Training time: 43days", "## Software\n\n- Orchestration: Deepspeed\n- Neural networks: PyTorch\n- BP16 if applicable: apex\n\n\n<a id=\"chinese\"></a>\n\n<p>\n\n</p>", "# OpenCSG介绍\n\n\n<p align=\"center\">\n<img width=\"300px\" alt=\"OpenCSG\" src=\"URL\n</p>\n\n<p align=\"center\"><a href=\"URL 社区]</a> <a href=\"URL <a href=\"URL[微信]</a> <a href=\"URL[推特]</a> </p>\n\n\n\n</div>\nOpenCSG中 Open是开源开放；C 代表 Converged resources，整合和充分利用的混合异构资源优势，算力降本增效；S 代表 Software refined，重新定义软件的交付方式，通过大模型驱动软件开发，人力降本增效；G 代表 Generative LM，大众化、普惠化和民主化的可商用的开源生成式大模型。\n\nOpenCSG的愿景是让每个行业、每个公司、每个人都拥有自己的模型。 我们坚持开源开放的原则，将OpenCSG的大模型软件栈开源到社区，欢迎使用、反馈和参与共建，欢迎关注。", "## 模型介绍\n\n\ncsg-wukong-1B-orpo-bf16 在csg-wukong-1B预训练模型上微调而成.\n<br>\n\n我们将在后面介绍更多关于这个模型的信息。", "## 模型评测结果\n\n我们把csg-wukong-1B模型提交到open_llm_leaderboard榜单上，结果显示我们的模型目前在~1.5B小语言模型中排名第8。\n\n\n!image/png", "# 训练", "## 硬件资源\n\n- GPU数量： 16 H800 \n- 训练时间： 43天", "## 软件使用\n\n- 微调训练框架： Deepspeed\n- 深度学习框架： PyTorch\n- BP16： apex" ]

[ 49, 288, 47, 52, 2, 18, 44, 302, 61, 67, 3, 24, 34 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #code #conversational #en #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# csg-wukong-1B-orpo-bf16 [[中文]](#chinese) [[English]](#english)\n\n<a id=\"english\"></a>\n\n<p align=\"center\">\n<img width=\"900px\" alt=\"OpenCSG\" src=\"./URL\">\n</p>\n\n<p align=\"center\"><a href=\"URL Community]</a> <a href=\"URL <a href=\"URL <a href=\"URL </p>\n\n\n</div>\nOpenCSG stands for Converged resources, Software refinement, and Generative LM. The 'C' represents Converged resources, indicating the integration and full utilization of hybrid resources. The 'S' stands for Software refinement, signifying software that is refined by large models. The 'G' represents Generative LM, which denotes widespread, inclusive, and democratized generative large models.\n\nThe vision of OpenCSG is to empower every industry, every company, and every individual to own their models. We adhere to the principles of openness and open source, making the large model software stack of OpenCSG available to the community. We welcome everyone to use, send feedback, and contribute collaboratively.## Model Description\n\n\n\n\ncsg-wukong-1B-orpo-bf16 was finetuned on csg-wukong-1B. \n<br>\nwe will introduce more information about csg-wukong-1B.## Model Evaluation results\n\nWe submitted csg-wukong-1B on the open_llm_leaderboard, and\nthe results show our model ranked the 8th among the ~1.5B pretrained small language models.\n\n\n!image/png# Training## Hardware\n\n- GPUs: 16 H800 \n- Training time: 43days## Software\n\n- Orchestration: Deepspeed\n- Neural networks: PyTorch\n- BP16 if applicable: apex\n\n\n<a id=\"chinese\"></a>\n\n<p>\n\n</p># OpenCSG介绍\n\n\n<p align=\"center\">\n<img width=\"300px\" alt=\"OpenCSG\" src=\"URL\n</p>\n\n<p align=\"center\"><a href=\"URL 社区]</a> <a href=\"URL <a href=\"URL[微信]</a> <a href=\"URL[推特]</a> </p>\n\n\n\n</div>\nOpenCSG中 Open是开源开放；C 代表 Converged resources，整合和充分利用的混合异构资源优势，算力降本增效；S 代表 Software refined，重新定义软件的交付方式，通过大模型驱动软件开发，人力降本增效；G 代表 Generative LM，大众化、普惠化和民主化的可商用的开源生成式大模型。\n\nOpenCSG的愿景是让每个行业、每个公司、每个人都拥有自己的模型。 我们坚持开源开放的原则，将OpenCSG的大模型软件栈开源到社区，欢迎使用、反馈和参与共建，欢迎关注。## 模型介绍\n\n\ncsg-wukong-1B-orpo-bf16 在csg-wukong-1B预训练模型上微调而成.\n<br>\n\n我们将在后面介绍更多关于这个模型的信息。## 模型评测结果\n\n我们把csg-wukong-1B模型提交到open_llm_leaderboard榜单上，结果显示我们的模型目前在~1.5B小语言模型中排名第8。\n\n\n!image/png# 训练## 硬件资源\n\n- GPU数量： 16 H800 \n- 训练时间： 43天## 软件使用\n\n- 微调训练框架： Deepspeed\n- 深度学习框架： PyTorch\n- BP16： apex" ]

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

[]

[]

[ "### Merge Method\n\n\nThis model was merged using the SLERP merge method.\nPrompt template: Alpaca, maybe ChatML\n\n\n* URL for quanting exl2 included.\n\n\n* 4.2bpw-exl2\n* 6.5bpw-exl2\n* 8bpw-exl2\n\n\nthx mradermacher for\n\n\n* mradermacher/IceLatteRP-7b-GGUF", "### Models Merged\n\n\nThe following models were included in the merge:\n\n\n* IceCoffeeRP\n* WestIceLemonTeaRP\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nTo download the 'main' branch to a folder called 'IceLatteRP-7b':\n\n\n\nMore advanced huggingface-cli download usage\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\n\nThe cache location can be changed with the 'HF\\_HOME' environment variable, and/or the '--cache-dir' parameter to 'huggingface-cli'.\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\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.", "### Configuration\n\n\nThe following YAML configuration was used to produce this model:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #alpaca #not-for-all-audiences #nsfw #license-cc-by-nc-4.0 #model-index #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Merge Method\n\n\nThis model was merged using the SLERP merge method.\nPrompt template: Alpaca, maybe ChatML\n\n\n* URL for quanting exl2 included.\n\n\n* 4.2bpw-exl2\n* 6.5bpw-exl2\n* 8bpw-exl2\n\n\nthx mradermacher for\n\n\n* mradermacher/IceLatteRP-7b-GGUF", "### Models Merged\n\n\nThe following models were included in the merge:\n\n\n* IceCoffeeRP\n* WestIceLemonTeaRP\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nTo download the 'main' branch to a folder called 'IceLatteRP-7b':\n\n\n\nMore advanced huggingface-cli download usage\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\n\nThe cache location can be changed with the 'HF\\_HOME' environment variable, and/or the '--cache-dir' parameter to 'huggingface-cli'.\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\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.", "### Configuration\n\n\nThe following YAML configuration was used to produce this model:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ 71, 90, 406, 68 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #mergekit #merge #alpaca #not-for-all-audiences #nsfw #license-cc-by-nc-4.0 #model-index #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n### Merge Method\n\n\nThis model was merged using the SLERP merge method.\nPrompt template: Alpaca, maybe ChatML\n\n\n* URL for quanting exl2 included.\n\n\n* 4.2bpw-exl2\n* 6.5bpw-exl2\n* 8bpw-exl2\n\n\nthx mradermacher for\n\n\n* mradermacher/IceLatteRP-7b-GGUF### Models Merged\n\n\nThe following models were included in the merge:\n\n\n* IceCoffeeRP\n* WestIceLemonTeaRP\n\n\nI recommend using the 'huggingface-hub' Python library:\n\n\nTo download the 'main' branch to a folder called 'IceLatteRP-7b':\n\n\n\nMore advanced huggingface-cli download usage\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\n\nThe cache location can be changed with the 'HF\\_HOME' environment variable, and/or the '--cache-dir' parameter to 'huggingface-cli'.\n\n\nFor more documentation on downloading with 'huggingface-cli', please see: HF -> Hub Python Library -> Download files -> Download from the CLI.\n\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install 'hf\\_transfer':\n\n\nAnd set environment variable 'HF\\_HUB\\_ENABLE\\_HF\\_TRANSFER' to '1':\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.### Configuration\n\n\nThe following YAML configuration was used to produce this model:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ "peft", "safetensors", "trl", "sft", "nycu-112-2-deeplearning-hw2", "generated_from_trainer", "zh", "dataset:DandinPower/ZH-Reading-Comprehension-TaiwanLlama-chat", "base_model:yentinglin/Taiwan-LLM-7B-v2.1-chat", "license:apache-2.0", "region:us" ]

[]

[ "zh" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 2\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 2\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 700\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #nycu-112-2-deeplearning-hw2 #generated_from_trainer #zh #dataset-DandinPower/ZH-Reading-Comprehension-TaiwanLlama-chat #base_model-yentinglin/Taiwan-LLM-7B-v2.1-chat #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 2\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 2\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 700\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 94, 174, 5, 52 ]

[ "TAGS\n#peft #safetensors #trl #sft #nycu-112-2-deeplearning-hw2 #generated_from_trainer #zh #dataset-DandinPower/ZH-Reading-Comprehension-TaiwanLlama-chat #base_model-yentinglin/Taiwan-LLM-7B-v2.1-chat #license-apache-2.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0001\n* train\\_batch\\_size: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 2\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 2\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 700\n* num\\_epochs: 3.0### Training results### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.0\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "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" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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" ]

[ "diffusers", "en", "license:apache-2.0", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

[]

[ "en" ]

[ "# Normal-Depth Diffusion Model\n\nThis is an *unofficial* export of the original normal-depth diffusion model (URL to the standard diffusers model format.\n\nCan be direcetly loaded via diffusers' 'StableDiffusionPipeline'\n\n!overview\n\nAll the credit to the original author of normal-depth diffusion model (URL" ]

[ "TAGS\n#diffusers #en #license-apache-2.0 #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "# Normal-Depth Diffusion Model\n\nThis is an *unofficial* export of the original normal-depth diffusion model (URL to the standard diffusers model format.\n\nCan be direcetly loaded via diffusers' 'StableDiffusionPipeline'\n\n!overview\n\nAll the credit to the original author of normal-depth diffusion model (URL" ]

[ 33, 68 ]

[ "TAGS\n#diffusers #en #license-apache-2.0 #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n# Normal-Depth Diffusion Model\n\nThis is an *unofficial* export of the original normal-depth diffusion model (URL to the standard diffusers model format.\n\nCan be direcetly loaded via diffusers' 'StableDiffusionPipeline'\n\n!overview\n\nAll the credit to the original author of normal-depth diffusion model (URL" ]

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:2305.18290", "arxiv:2310.16944", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "2305.18290", "2310.16944" ]

[]

[ "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531", "### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0", "### Training results\n\n\nThe table below shows the full set of DPO training metrics:", "### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-2305.18290 #arxiv-2310.16944 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531", "### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0", "### Training results\n\n\nThe table below shows the full set of DPO training metrics:", "### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ 61, 648, 166, 19, 121 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-2305.18290 #arxiv-2310.16944 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0### Training results\n\n\nThe table below shows the full set of DPO training metrics:### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ "gguf", "facebook", "meta", "llama", "llama-3", "llama-3-ko", "llama-cpp", "gguf-my-repo", "en", "ko", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "region:us" ]

[]

[ "en", "ko" ]

[ "# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q8_0-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #facebook #meta #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n", "# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q8_0-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ 75, 99, 52 ]

[ "TAGS\n#gguf #facebook #meta #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q8_0-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

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

[]

[]

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

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

[ 31, 35, 17 ]

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

[ "gguf", "facebook", "meta", "llama", "llama-3", "llama-3-ko", "llama-cpp", "gguf-my-repo", "en", "ko", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "region:us" ]

[]

[ "en", "ko" ]

[ "# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q5_K_M-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #facebook #meta #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n", "# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q5_K_M-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ 75, 101, 52 ]

[ "TAGS\n#gguf #facebook #meta #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q5_K_M-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "transformers", "gguf", "mistral", "text-generation-inference", "unsloth", "en", "base_model:Viet-Mistral/Vistral-7B-Chat", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: hungsvdut2k2\n- License: apache-2.0\n- Finetuned from model : Viet-Mistral/Vistral-7B-Chat\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #gguf #mistral #text-generation-inference #unsloth #en #base_model-Viet-Mistral/Vistral-7B-Chat #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: hungsvdut2k2\n- License: apache-2.0\n- Finetuned from model : Viet-Mistral/Vistral-7B-Chat\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 56, 79 ]

[ "TAGS\n#transformers #gguf #mistral #text-generation-inference #unsloth #en #base_model-Viet-Mistral/Vistral-7B-Chat #license-apache-2.0 #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: hungsvdut2k2\n- License: apache-2.0\n- Finetuned from model : Viet-Mistral/Vistral-7B-Chat\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:2305.18290", "arxiv:2310.16944", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[ "2305.18290", "2310.16944" ]

[]

[ "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531", "### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0", "### Training results\n\n\nThe table below shows the full set of DPO training metrics:", "### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-2305.18290 #arxiv-2310.16944 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531", "### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0", "### Training results\n\n\nThe table below shows the full set of DPO training metrics:", "### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ 61, 648, 166, 19, 121 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #arxiv-2305.18290 #arxiv-2310.16944 #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0### Training results\n\n\nThe table below shows the full set of DPO training metrics:### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ "gguf", "facebook", "meta", "llama", "llama-3", "llama-3-ko", "llama-cpp", "gguf-my-repo", "en", "ko", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "region:us" ]

[]

[ "en", "ko" ]

[ "# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #facebook #meta #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n", "# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ 75, 101, 52 ]

[ "TAGS\n#gguf #facebook #meta #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n# gagagiga/Llama-3-MAAL-8B-Instruct-v0.1-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'maum-ai/Llama-3-MAAL-8B-Instruct-v0.1' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "transformers", "pytorch", "gpt2", "text-generation", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "## License\n\nThis model is available under the Apache 2.0 License. Well, also MIT License. So both should be followed.", "## Discord Server\n\nJoin our Discord server here.", "## Feeling Generous? \n\nEager to buy me a cup of 2$ coffe or iced tea? Sure, here is the link: URL Please add a note on which one you want me to drink?" ]

[ "TAGS\n#transformers #pytorch #gpt2 #text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## License\n\nThis model is available under the Apache 2.0 License. Well, also MIT License. So both should be followed.", "## Discord Server\n\nJoin our Discord server here.", "## Feeling Generous? \n\nEager to buy me a cup of 2$ coffe or iced tea? Sure, here is the link: URL Please add a note on which one you want me to drink?" ]

[ 44, 27, 12, 42 ]

[ "TAGS\n#transformers #pytorch #gpt2 #text-generation #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n## License\n\nThis model is available under the Apache 2.0 License. Well, also MIT License. So both should be followed.## Discord Server\n\nJoin our Discord server here.## Feeling Generous? \n\nEager to buy me a cup of 2$ coffe or iced tea? Sure, here is the link: URL Please add a note on which one you want me to drink?" ]

[ "peft", "pytorch", "safetensors", "arxiv:1910.09700", "base_model:Jennny/merged_sft_llama2_pku", "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 0.10.1.dev0" ]

[ "TAGS\n#peft #pytorch #safetensors #arxiv-1910.09700 #base_model-Jennny/merged_sft_llama2_pku #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 0.10.1.dev0" ]

[ 47, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 16 ]

[ "TAGS\n#peft #pytorch #safetensors #arxiv-1910.09700 #base_model-Jennny/merged_sft_llama2_pku #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 0.10.1.dev0" ]

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ 41, 176, 5, 44 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "peft", "safetensors", "ko", "dataset:JosephLee/science_textbook_elementary_kor", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "region:us" ]

[ "1910.09700" ]

[ "ko" ]

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

[ "TAGS\n#peft #safetensors #ko #dataset-JosephLee/science_textbook_elementary_kor #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #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" ]

[ 61, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #ko #dataset-JosephLee/science_textbook_elementary_kor #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #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", "text-generation-inference", "Japanese", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Evolany AI\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\n\nWe trained on 1 x A100 GPU. \n\n\nUser prompt:\n\nAny news article in Japanese (max length up to 4096 tokens). Eg:\n\n\n\nModel response:\n\n\n\n\nQLoRA (4bit)\n\nParams to replicate training\n\nPeft Config\n\n\n\nTraining args\n\nLoss\n'1.22'\n\nTraining Results\n<img src=\"URL width=\"600\"/>\n\n\n\n\nInterernce Code\n\n\n\n\n\n\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 #Japanese #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: Evolany AI\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\n\nWe trained on 1 x A100 GPU. \n\n\nUser prompt:\n\nAny news article in Japanese (max length up to 4096 tokens). Eg:\n\n\n\nModel response:\n\n\n\n\nQLoRA (4bit)\n\nParams to replicate training\n\nPeft Config\n\n\n\nTraining args\n\nLoss\n'1.22'\n\nTraining Results\n<img src=\"URL width=\"600\"/>\n\n\n\n\nInterernce Code\n\n\n\n\n\n\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ 69, 168 ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #Japanese #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: Evolany AI\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\n\nWe trained on 1 x A100 GPU. \n\n\nUser prompt:\n\nAny news article in Japanese (max length up to 4096 tokens). Eg:\n\n\n\nModel response:\n\n\n\n\nQLoRA (4bit)\n\nParams to replicate training\n\nPeft Config\n\n\n\nTraining args\n\nLoss\n'1.22'\n\nTraining Results\n<img src=\"URL width=\"600\"/>\n\n\n\n\nInterernce Code\n\n\n\n\n\n\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "gguf", "arxiv:2305.18290", "arxiv:2310.16944", "region:us" ]

[ "2305.18290", "2310.16944" ]

[]

[ "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531", "### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0", "### Training results\n\n\nThe table below shows the full set of DPO training metrics:", "### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ "TAGS\n#gguf #arxiv-2305.18290 #arxiv-2310.16944 #region-us \n", "### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531", "### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0", "### Training results\n\n\nThe table below shows the full set of DPO training metrics:", "### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ 29, 648, 166, 19, 121 ]

[ "TAGS\n#gguf #arxiv-2305.18290 #arxiv-2310.16944 #region-us \n### Model Sources\n\n\n* Repository: URL\n* Demo: URL\n* Chatbot Arena: Evaluate Zephyr 7B against 10+ LLMs in the LMSYS arena: URL\n\n\nPerformance\n-----------\n\n\nAt the time of release, Zephyr-7B-β is the highest ranked 7B chat model on the MT-Bench and AlpacaEval benchmarks:\n\n\n\nIn particular, on several categories of MT-Bench, Zephyr-7B-β has strong performance compared to larger open models like Llama2-Chat-70B:\n\n\n!image/png\n\n\nHowever, on more complex tasks like coding and mathematics, Zephyr-7B-β lags behind proprietary models and more research is needed to close the gap.\n\n\nIntended uses & limitations\n---------------------------\n\n\nThe model was initially fine-tuned on a filtered and preprocessed of the 'UltraChat' dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.\nWe then further aligned the model with TRL's 'DPOTrainer' on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT-4. As a result, the model can be used for chat and you can check out our demo to test its capabilities.\n\n\nYou can find the datasets used for training Zephyr-7B-β here\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\nZephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).\nIt is also unknown what the size and composition of the corpus was used to train the base model ('mistralai/Mistral-7B-v0.1'), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.\n\n\nTraining and evaluation data\n----------------------------\n\n\nDuring DPO training, this model achieves the following results on the evaluation set:\n\n\n* Loss: 0.7496\n* Rewards/chosen: -4.5221\n* Rewards/rejected: -8.3184\n* Rewards/accuracies: 0.7812\n* Rewards/margins: 3.7963\n* Logps/rejected: -340.1541\n* Logps/chosen: -299.4561\n* Logits/rejected: -2.3081\n* Logits/chosen: -2.3531### 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: 16\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 64\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: 3.0### Training results\n\n\nThe table below shows the full set of DPO training metrics:### Framework versions\n\n\n* Transformers 4.35.0.dev0\n* Pytorch 2.0.1+cu118\n* Datasets 2.12.0\n* Tokenizers 0.14.0\n\n\nIf you find Zephyr-7B-β is useful in your work, please cite it with:\n\n\nOpen LLM Leaderboard Evaluation Results\n=======================================\n\n\nDetailed results can be found here" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 44, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B-Instruct #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact### Framework versions\n\n- PEFT 0.10.0" ]

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ 41, 176, 5, 44 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "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" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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", "mistral", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "dataset:updated", "dataset:original", "base_model:alignment-handbook/zephyr-7b-sft-full", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* total\\_eval\\_batch\\_size: 8\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\n* PEFT 0.7.1\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #mistral #alignment-handbook #generated_from_trainer #trl #dpo #dataset-updated #dataset-original #base_model-alignment-handbook/zephyr-7b-sft-full #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* total\\_eval\\_batch\\_size: 8\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\n* PEFT 0.7.1\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

[ 72, 176, 5, 52 ]

[ "TAGS\n#peft #tensorboard #safetensors #mistral #alignment-handbook #generated_from_trainer #trl #dpo #dataset-updated #dataset-original #base_model-alignment-handbook/zephyr-7b-sft-full #license-apache-2.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 5e-06\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 16\n* total\\_train\\_batch\\_size: 128\n* total\\_eval\\_batch\\_size: 8\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\n* PEFT 0.7.1\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.14.6\n* Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "facebook", "meta", "pytorch", "llama-3", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "6-bit", "region:us" ]

[]

[ "en" ]

[ "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us \n", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ 61, 17, 429, 8, 6, 270, 280, 72, 115, 118, 126, 2136 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #6-bit #region-us \n### Use with transformers\n\n\nSee the snippet below for usage with Transformers:### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.### Base pretrained models### Instruction tuned models### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "transformers", "safetensors", "xlm-roberta", "token-classification", "generated_from_trainer", "base_model:xlm-roberta-base", "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: 24\n* eval\\_batch\\_size: 24\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", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #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: 24\n* eval\\_batch\\_size: 24\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", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ 51, 101, 5, 44 ]

[ "TAGS\n#transformers #safetensors #xlm-roberta #token-classification #generated_from_trainer #base_model-xlm-roberta-base #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: 24\n* eval\\_batch\\_size: 24\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### Training results### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.2.2+cu121\n* Datasets 2.18.0\n* Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "mn", "dataset:Cafet/whisper-mongolian-final", "base_model:openai/whisper-medium", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "mn" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2000\n* training\\_steps: 10000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #mn #dataset-Cafet/whisper-mongolian-final #base_model-openai/whisper-medium #license-apache-2.0 #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2000\n* training\\_steps: 10000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 66, 127, 5, 40 ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #mn #dataset-Cafet/whisper-mongolian-final #base_model-openai/whisper-medium #license-apache-2.0 #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 2000\n* training\\_steps: 10000\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.0\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "mistral", "text-generation", "merge", "mergekit", "lazymergekit", "migtissera/Tess-7B-v2.0", "Eric111/Yarn-Mistral-7b-128k-DPO", "custom_code", "base_model:migtissera/Tess-7B-v2.0", "base_model:Eric111/Yarn-Mistral-7b-128k-DPO", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# D_AU-Tess-7B-v2.0-Yarn-Mistral-7b-128k-DPO\n\nD_AU-Tess-7B-v2.0-Yarn-Mistral-7b-128k-DPO is a merge of the following models using LazyMergekit:\n* migtissera/Tess-7B-v2.0\n* Eric111/Yarn-Mistral-7b-128k-DPO", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #migtissera/Tess-7B-v2.0 #Eric111/Yarn-Mistral-7b-128k-DPO #custom_code #base_model-migtissera/Tess-7B-v2.0 #base_model-Eric111/Yarn-Mistral-7b-128k-DPO #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# D_AU-Tess-7B-v2.0-Yarn-Mistral-7b-128k-DPO\n\nD_AU-Tess-7B-v2.0-Yarn-Mistral-7b-128k-DPO is a merge of the following models using LazyMergekit:\n* migtissera/Tess-7B-v2.0\n* Eric111/Yarn-Mistral-7b-128k-DPO", "## Configuration", "## Usage" ]

[ 122, 101, 3, 3 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #merge #mergekit #lazymergekit #migtissera/Tess-7B-v2.0 #Eric111/Yarn-Mistral-7b-128k-DPO #custom_code #base_model-migtissera/Tess-7B-v2.0 #base_model-Eric111/Yarn-Mistral-7b-128k-DPO #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# D_AU-Tess-7B-v2.0-Yarn-Mistral-7b-128k-DPO\n\nD_AU-Tess-7B-v2.0-Yarn-Mistral-7b-128k-DPO is a merge of the following models using LazyMergekit:\n* migtissera/Tess-7B-v2.0\n* Eric111/Yarn-Mistral-7b-128k-DPO## Configuration## Usage" ]

[ "gguf", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "TAGS\n#gguf #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ 9, 176, 5, 44 ]

[ "TAGS\n#gguf #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* 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\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "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" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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", "mixtral", "text-generation", "generated_from_trainer", "axolotl", "conversational", "en", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "base_model:mistral-community/Mixtral-8x22B-v0.1", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #generated_from_trainer #axolotl #conversational #en #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-mistral-community/Mixtral-8x22B-v0.1 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ 224, 5, 47 ]

[ "TAGS\n#transformers #safetensors #mixtral #text-generation #generated_from_trainer #axolotl #conversational #en #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-mistral-community/Mixtral-8x22B-v0.1 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n### Training results### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "dataset:TigerResearch/sft_zh", "dataset:silk-road/alpaca-data-gpt4-chinese", "license:llama3", "region:us" ]

[]

[]

[ "### Coming Soon!!!", "### 基于alpaca-data-gpt4-chinese、sft\\_zh数据集对Llama-3-8B-Instruct进行微调。", "### 模型：\n\n\n* URL", "### 数据集：\n\n\n* URL\n* URL", "### 结果\n\n\n模型名称: LLama3, CEVAL: 49.91, MMLU: 66.62\n模型名称: LLama3-Instruct, CEVAL: 50.55, MMLU: 67.15\n模型名称: LLama3-Instruct-sft-lora-tigerbot-alpacadatagpt4-10epoch, CEVAL: 53.65, MMLU: 68.09" ]

[ "TAGS\n#dataset-TigerResearch/sft_zh #dataset-silk-road/alpaca-data-gpt4-chinese #license-llama3 #region-us \n", "### Coming Soon!!!", "### 基于alpaca-data-gpt4-chinese、sft\\_zh数据集对Llama-3-8B-Instruct进行微调。", "### 模型：\n\n\n* URL", "### 数据集：\n\n\n* URL\n* URL", "### 结果\n\n\n模型名称: LLama3, CEVAL: 49.91, MMLU: 66.62\n模型名称: LLama3-Instruct, CEVAL: 50.55, MMLU: 67.15\n模型名称: LLama3-Instruct-sft-lora-tigerbot-alpacadatagpt4-10epoch, CEVAL: 53.65, MMLU: 68.09" ]

[ 44, 8, 42, 9, 13, 97 ]

[ "TAGS\n#dataset-TigerResearch/sft_zh #dataset-silk-road/alpaca-data-gpt4-chinese #license-llama3 #region-us \n### Coming Soon!!!### 基于alpaca-data-gpt4-chinese、sft\\_zh数据集对Llama-3-8B-Instruct进行微调。### 模型：\n\n\n* URL### 数据集：\n\n\n* URL\n* URL### 结果\n\n\n模型名称: LLama3, CEVAL: 49.91, MMLU: 66.62\n模型名称: LLama3-Instruct, CEVAL: 50.55, MMLU: 67.15\n模型名称: LLama3-Instruct-sft-lora-tigerbot-alpacadatagpt4-10epoch, CEVAL: 53.65, MMLU: 68.09" ]

[ "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" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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" ]

[ "llama", "license:llama3", "region:us" ]

[]

[]

[ "# Meta-Llama-3-8B-Instruct-GGUF\r\n\r\n- This is GGUF quantized version of meta-llama/Meta-Llama-3-8B-Instruct created using URL.\r\n\r\n- imatrix from here.\r\n\r\n- Using URL revision a8f9b076316e16aadd0791015b3bfd446fe1e904, after \"llama : fix BPE pre-tokenization (#6920)\"" ]

[ "TAGS\n#llama #license-llama3 #region-us \n", "# Meta-Llama-3-8B-Instruct-GGUF\r\n\r\n- This is GGUF quantized version of meta-llama/Meta-Llama-3-8B-Instruct created using URL.\r\n\r\n- imatrix from here.\r\n\r\n- Using URL revision a8f9b076316e16aadd0791015b3bfd446fe1e904, after \"llama : fix BPE pre-tokenization (#6920)\"" ]

[ 14, 110 ]

[ "TAGS\n#llama #license-llama3 #region-us \n# Meta-Llama-3-8B-Instruct-GGUF\r\n\r\n- This is GGUF quantized version of meta-llama/Meta-Llama-3-8B-Instruct created using URL.\r\n\r\n- imatrix from here.\r\n\r\n- Using URL revision a8f9b076316e16aadd0791015b3bfd446fe1e904, after \"llama : fix BPE pre-tokenization (#6920)\"" ]

[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "dataset:emotion", "base_model:distilbert-base-uncased", "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: 2e-05\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #dataset-emotion #base_model-distilbert-base-uncased #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: 2e-05\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 68, 101, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #dataset-emotion #base_model-distilbert-base-uncased #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: 2e-05\n* train\\_batch\\_size: 64\n* eval\\_batch\\_size: 64\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "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" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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" ]

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

[]

[]

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

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

[ 31, 35, 17 ]

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

[ "transformers", "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" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "llama", "text-generation", "autotrain", "text-generation-inference", "peft", "conversational", "license:other", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.", "# Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #autotrain #text-generation-inference #peft #conversational #license-other #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.", "# Usage" ]

[ 47, 23, 2 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #autotrain #text-generation-inference #peft #conversational #license-other #autotrain_compatible #endpoints_compatible #region-us \n# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit AutoTrain.# Usage" ]

[ "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" ]

[ "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" ]

[ 43, 26, 3 ]

[ "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" ]

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

[]

[]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ 41 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

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

[]

[]

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

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

[ 27, 36, 3, 3 ]

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

[ "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: Justin-Y\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: Justin-Y\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\"/>" ]

[ 64, 80 ]

[ "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: Justin-Y\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", "roberta", "text-classification", "generated_from_trainer", "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: 16\n* eval\\_batch\\_size: 64\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 30\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

[ "TAGS\n#transformers #safetensors #roberta #text-classification #generated_from_trainer #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: 16\n* eval\\_batch\\_size: 64\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 30\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

[ 33, 151, 5, 44 ]

[ "TAGS\n#transformers #safetensors #roberta #text-classification #generated_from_trainer #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: 16\n* eval\\_batch\\_size: 64\n* seed: 42\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* num\\_epochs: 30\n* mixed\\_precision\\_training: Native AMP### Training results### Framework versions\n\n\n* Transformers 4.39.3\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

[ "arxiv:1910.09700", "region:us" ]

[ "1910.09700" ]

[]

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

[ "TAGS\n#arxiv-1910.09700 #region-us \n", "# Model Card for Model ID\n\n\n\nThis modelcard aims to be a base template for new models. It has been generated using this raw template.", "## 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" ]

[ 15, 28, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "TAGS\n#arxiv-1910.09700 #region-us \n# Model Card for Model ID\n\n\n\nThis modelcard aims to be a base template for new models. It has been generated using this raw template.## 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" ]

[ "diffusers", "text-to-video", "region:us" ]

[]

[]

[ "# LLM-grounded Video Diffusion Models\nLong Lian, Baifeng Shi, Adam Yala, Trevor Darrell, Boyi Li at UC Berkeley/UCSF. ICLR 2024.\n\nProject Page | Related Project: LMD | Citation\n\nThis model is based on zeroscope but with additional conditioning from bounding boxes in a GLIGEN fashion.\n\nSimilar to LLM-grounded Diffusion (LMD), LLM-grounded Video Diffusion (LVD)'s boxes-to-video stage allows cross-attention-based bounding box conditioning, which uses Zeroscope off-the-shelf. This huggingface model offers an alternative: we train a GLIGEN model (i.e., transformer adapters) with Zeroscope's weights without the temporal transformers blocks on SA-1B, treating it as a SD v2.1 model that has been fine-tuned to 256x256 resolution. We then merge the adapters into Zeroscope to offer conditioning. The resulting model is in this hugginface model. This can be used with cross-attention-based conditioning or on its own, similar to LMD+. This can be used with LLM-based text-to-dynamic scene layout generator in LVD, or on its own as a video version of GLIGEN.\n\n(LVD)\nIf you use our work, model, or our implementation in this repo, or find them helpful, please consider giving a citation.\n\n\n(GLIGEN)\nThe adapters in this model are trained in a mannar similar to training GLIGEN adapters.\n\n\n(ModelScope)\nModelScope is LVD's base model.", "## LICENSE\nZeroscope follows CC-BY-NC 4.0 license. The gligen adapters are trained on SA-1B, which follows SA-1B license." ]

[ "TAGS\n#diffusers #text-to-video #region-us \n", "# LLM-grounded Video Diffusion Models\nLong Lian, Baifeng Shi, Adam Yala, Trevor Darrell, Boyi Li at UC Berkeley/UCSF. ICLR 2024.\n\nProject Page | Related Project: LMD | Citation\n\nThis model is based on zeroscope but with additional conditioning from bounding boxes in a GLIGEN fashion.\n\nSimilar to LLM-grounded Diffusion (LMD), LLM-grounded Video Diffusion (LVD)'s boxes-to-video stage allows cross-attention-based bounding box conditioning, which uses Zeroscope off-the-shelf. This huggingface model offers an alternative: we train a GLIGEN model (i.e., transformer adapters) with Zeroscope's weights without the temporal transformers blocks on SA-1B, treating it as a SD v2.1 model that has been fine-tuned to 256x256 resolution. We then merge the adapters into Zeroscope to offer conditioning. The resulting model is in this hugginface model. This can be used with cross-attention-based conditioning or on its own, similar to LMD+. This can be used with LLM-based text-to-dynamic scene layout generator in LVD, or on its own as a video version of GLIGEN.\n\n(LVD)\nIf you use our work, model, or our implementation in this repo, or find them helpful, please consider giving a citation.\n\n\n(GLIGEN)\nThe adapters in this model are trained in a mannar similar to training GLIGEN adapters.\n\n\n(ModelScope)\nModelScope is LVD's base model.", "## LICENSE\nZeroscope follows CC-BY-NC 4.0 license. The gligen adapters are trained on SA-1B, which follows SA-1B license." ]

[ 14, 337, 36 ]

[ "TAGS\n#diffusers #text-to-video #region-us \n# LLM-grounded Video Diffusion Models\nLong Lian, Baifeng Shi, Adam Yala, Trevor Darrell, Boyi Li at UC Berkeley/UCSF. ICLR 2024.\n\nProject Page | Related Project: LMD | Citation\n\nThis model is based on zeroscope but with additional conditioning from bounding boxes in a GLIGEN fashion.\n\nSimilar to LLM-grounded Diffusion (LMD), LLM-grounded Video Diffusion (LVD)'s boxes-to-video stage allows cross-attention-based bounding box conditioning, which uses Zeroscope off-the-shelf. This huggingface model offers an alternative: we train a GLIGEN model (i.e., transformer adapters) with Zeroscope's weights without the temporal transformers blocks on SA-1B, treating it as a SD v2.1 model that has been fine-tuned to 256x256 resolution. We then merge the adapters into Zeroscope to offer conditioning. The resulting model is in this hugginface model. This can be used with cross-attention-based conditioning or on its own, similar to LMD+. This can be used with LLM-based text-to-dynamic scene layout generator in LVD, or on its own as a video version of GLIGEN.\n\n(LVD)\nIf you use our work, model, or our implementation in this repo, or find them helpful, please consider giving a citation.\n\n\n(GLIGEN)\nThe adapters in this model are trained in a mannar similar to training GLIGEN adapters.\n\n\n(ModelScope)\nModelScope is LVD's base model.## LICENSE\nZeroscope follows CC-BY-NC 4.0 license. The gligen adapters are trained on SA-1B, which follows SA-1B license." ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Jacob1802\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: Jacob1802\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\"/>" ]

[ 60, 81 ]

[ "TAGS\n#transformers #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n# Uploaded model\n\n- Developed by: Jacob1802\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", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 51, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "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" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "llama", "text-generation", "merge", "mergekit", "lazymergekit", "KoboldAI/LLaMA2-13B-Tiefighter", "DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp", "custom_code", "base_model:KoboldAI/LLaMA2-13B-Tiefighter", "base_model:DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# D_AU-Tiefighter-Plus-OrcaMaid-V3-13B-32k-slerp\n\nD_AU-Tiefighter-Plus-OrcaMaid-V3-13B-32k-slerp is a merge of the following models using LazyMergekit:\n* KoboldAI/LLaMA2-13B-Tiefighter\n* DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #KoboldAI/LLaMA2-13B-Tiefighter #DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp #custom_code #base_model-KoboldAI/LLaMA2-13B-Tiefighter #base_model-DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# D_AU-Tiefighter-Plus-OrcaMaid-V3-13B-32k-slerp\n\nD_AU-Tiefighter-Plus-OrcaMaid-V3-13B-32k-slerp is a merge of the following models using LazyMergekit:\n* KoboldAI/LLaMA2-13B-Tiefighter\n* DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp", "## Configuration", "## Usage" ]

[ 138, 105, 3, 3 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #merge #mergekit #lazymergekit #KoboldAI/LLaMA2-13B-Tiefighter #DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp #custom_code #base_model-KoboldAI/LLaMA2-13B-Tiefighter #base_model-DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# D_AU-Tiefighter-Plus-OrcaMaid-V3-13B-32k-slerp\n\nD_AU-Tiefighter-Plus-OrcaMaid-V3-13B-32k-slerp is a merge of the following models using LazyMergekit:\n* KoboldAI/LLaMA2-13B-Tiefighter\n* DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp## Configuration## Usage" ]

[ "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" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "1910.09700" ]

[]

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

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

[ 44, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "generated_from_trainer", "base_model:anudaw/temp-1-distilled-code-llama", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# temp-1-distilled-code-llama\n\nThis model is a fine-tuned version of anudaw/temp-1-distilled-code-llama 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: 2e-05\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #trl #sft #generated_from_trainer #base_model-anudaw/temp-1-distilled-code-llama #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# temp-1-distilled-code-llama\n\nThis model is a fine-tuned version of anudaw/temp-1-distilled-code-llama 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: 2e-05\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ 76, 46, 7, 9, 9, 4, 126, 44 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #trl #sft #generated_from_trainer #base_model-anudaw/temp-1-distilled-code-llama #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# temp-1-distilled-code-llama\n\nThis model is a fine-tuned version of anudaw/temp-1-distilled-code-llama 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: 2e-05\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "pytorch", "gpt_neox", "text-generation", "generated_from_trainer", "pythia", "arxiv:2312.04469", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2312.04469" ]

[]

[ "## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=0, \\gamma=0.25, \\delta=1\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0", "### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #gpt_neox #text-generation #generated_from_trainer #pythia #arxiv-2312.04469 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=0, \\gamma=0.25, \\delta=1\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0", "### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

[ 67, 62, 119, 44 ]

[ "TAGS\n#transformers #pytorch #gpt_neox #text-generation #generated_from_trainer #pythia #arxiv-2312.04469 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=0, \\gamma=0.25, \\delta=1\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

[ "transformers", "tensorboard", "safetensors", "bert", "fill-mask", "generated_from_trainer", "base_model:bert-base-multilingual-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #fill-mask #generated_from_trainer #base_model-bert-base-multilingual-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 59, 103, 5, 44 ]

[ "TAGS\n#transformers #tensorboard #safetensors #bert #fill-mask #generated_from_trainer #base_model-bert-base-multilingual-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0### Training results### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 51, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "transformers", "safetensors", "llama", "text-generation", "trl", "sft", "generated_from_trainer", "base_model:anudaw/temp-0.5-distilled-code-llama", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# temp-0.5-distilled-code-llama\n\nThis model is a fine-tuned version of anudaw/temp-0.5-distilled-code-llama 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: 2e-05\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #trl #sft #generated_from_trainer #base_model-anudaw/temp-0.5-distilled-code-llama #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# temp-0.5-distilled-code-llama\n\nThis model is a fine-tuned version of anudaw/temp-0.5-distilled-code-llama 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: 2e-05\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ 78, 50, 7, 9, 9, 4, 126, 44 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #trl #sft #generated_from_trainer #base_model-anudaw/temp-0.5-distilled-code-llama #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# temp-0.5-distilled-code-llama\n\nThis model is a fine-tuned version of anudaw/temp-0.5-distilled-code-llama 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: 2e-05\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 32\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 5### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.3.0+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "pytorch", "gpt_neox", "text-generation", "generated_from_trainer", "pythia", "arxiv:2312.04469", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2312.04469" ]

[]

[ "## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=0, \\gamma=0.25, \\delta=2\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0", "### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #gpt_neox #text-generation #generated_from_trainer #pythia #arxiv-2312.04469 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=0, \\gamma=0.25, \\delta=2\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0", "### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

[ 67, 62, 119, 44 ]

[ "TAGS\n#transformers #pytorch #gpt_neox #text-generation #generated_from_trainer #pythia #arxiv-2312.04469 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=0, \\gamma=0.25, \\delta=2\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

[ "peft", "tensorboard", "safetensors", "distilbert", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #distilbert #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 46, 101, 5, 52 ]

[ "TAGS\n#peft #tensorboard #safetensors #distilbert #generated_from_trainer #base_model-distilbert-base-uncased #license-apache-2.0 #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2### Training results### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "pytorch", "gpt_neox", "text-generation", "generated_from_trainer", "pythia", "arxiv:2312.04469", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2312.04469" ]

[]

[ "## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=2, \\gamma=0.25, \\delta=2\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0\n-", "### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

[ "TAGS\n#transformers #pytorch #gpt_neox #text-generation #generated_from_trainer #pythia #arxiv-2312.04469 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=2, \\gamma=0.25, \\delta=2\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0\n-", "### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

[ 67, 62, 120, 44 ]

[ "TAGS\n#transformers #pytorch #gpt_neox #text-generation #generated_from_trainer #pythia #arxiv-2312.04469 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n## Model description\n\nSampling-based watermark distilled Pythia 1.4B using the KGW \\\\(k=2, \\gamma=0.25, \\delta=2\\\\) watermarking strategy in the paper On the Learnability of Watermarks for Language Models.### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 64\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_steps: 500\n- num_epochs: 1.0\n-### Framework versions\n\n- Transformers 4.29.2\n- Pytorch 2.0.1+cu117\n- Datasets 2.13.1\n- Tokenizers 0.13.3" ]

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

[]

[]

[ "# Model Card for Unit 4 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional audio generation of music in the genre Electronic", "## Usage\n\n<pre>\nfrom IPython.display import Audio\nfrom diffusers import DiffusionPipeline\n\npipe = DiffusionPipeline.from_pretrained(\"kmpartner/audio-diffusion-electronic\")\noutput = pipe()\ndisplay(URL[0])\ndisplay(Audio(URL[0], rate=URL.get_sample_rate()))\n</pre>" ]

[ "TAGS\n#diffusers #safetensors #pytorch #unconditional-audio-generation #diffusion-models-class #license-mit #diffusers-AudioDiffusionPipeline #region-us \n", "# Model Card for Unit 4 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional audio generation of music in the genre Electronic", "## Usage\n\n<pre>\nfrom IPython.display import Audio\nfrom diffusers import DiffusionPipeline\n\npipe = DiffusionPipeline.from_pretrained(\"kmpartner/audio-diffusion-electronic\")\noutput = pipe()\ndisplay(URL[0])\ndisplay(Audio(URL[0], rate=URL.get_sample_rate()))\n</pre>" ]

[ 45, 29, 86 ]

[ "TAGS\n#diffusers #safetensors #pytorch #unconditional-audio-generation #diffusion-models-class #license-mit #diffusers-AudioDiffusionPipeline #region-us \n# Model Card for Unit 4 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional audio generation of music in the genre Electronic## Usage\n\n<pre>\nfrom IPython.display import Audio\nfrom diffusers import DiffusionPipeline\n\npipe = DiffusionPipeline.from_pretrained(\"kmpartner/audio-diffusion-electronic\")\noutput = pipe()\ndisplay(URL[0])\ndisplay(Audio(URL[0], rate=URL.get_sample_rate()))\n</pre>" ]

[ "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" ]

[ 41, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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", "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" ]

[ 47, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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", "t5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# T5_FINETUNE_Electrical_ts", "# Fine-Tuned T5 Model for Root Cause Analysis", "# Description\nThis model is a fine-tuned version of the T5 (Text-to-Text Transfer Transformer) base model, specifically tailored to predict actions based on provided root causes in industrial or technical settings. The model has been trained to understand various root causes and suggest corresponding actions, facilitating faster decision-making and troubleshooting in operational environments.", "# Model Details\n\nBase Model: T5 Base\n\nTraining Data: The model was trained on a proprietary dataset consisting of documented root causes and the actions taken to resolve them in a manufacturing context.\nFine-Tuning Details: The model was fine-tuned for 3 epochs with a learning rate of 3e-4, using a batch size of 8. The fine-tuning process focused on adapting the T5 model to generate action plans based on textual descriptions of root causes.", "# Usage\nInstallation\nTo use this model, you will need to install Python and the necessary Python libraries. The primary library required is transformers by Hugging Face.\n\n-> pip install transformers torch", "# Loading the Model\nYou can load the model using the Transformers library. Ensure you have the model and tokenizer files(final_model.zip) downloaded from the repository or Kaggle dataset.\n\nfrom transformers import T5ForConditionalGeneration, T5Tokenizer\n\nmodel_path = 'path_to_model_directory'\nmodel = T5ForConditionalGeneration.from_pretrained(model_path)\ntokenizer = T5Tokenizer.from_pretrained(model_path)", "# Example\nprint(predict_action(\"Example of a root cause\"))", "# Contributing\nContributions to this model are welcome. You can contribute in the following ways:\n\nData: More data on root causes and actions can help to improve the model's accuracy and robustness.\nCode: Enhancements in the prediction script, additional features, or performance optimizations are appreciated.\nIssues: If you encounter issues while using this model, please report them in the issues section of this repository.", "# License\nThis project is licensed under the MIT License - see the LICENSE file for details.", "# ATTENTION: Still the model is not 100% effeective due lack of data." ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# T5_FINETUNE_Electrical_ts", "# Fine-Tuned T5 Model for Root Cause Analysis", "# Description\nThis model is a fine-tuned version of the T5 (Text-to-Text Transfer Transformer) base model, specifically tailored to predict actions based on provided root causes in industrial or technical settings. The model has been trained to understand various root causes and suggest corresponding actions, facilitating faster decision-making and troubleshooting in operational environments.", "# Model Details\n\nBase Model: T5 Base\n\nTraining Data: The model was trained on a proprietary dataset consisting of documented root causes and the actions taken to resolve them in a manufacturing context.\nFine-Tuning Details: The model was fine-tuned for 3 epochs with a learning rate of 3e-4, using a batch size of 8. The fine-tuning process focused on adapting the T5 model to generate action plans based on textual descriptions of root causes.", "# Usage\nInstallation\nTo use this model, you will need to install Python and the necessary Python libraries. The primary library required is transformers by Hugging Face.\n\n-> pip install transformers torch", "# Loading the Model\nYou can load the model using the Transformers library. Ensure you have the model and tokenizer files(final_model.zip) downloaded from the repository or Kaggle dataset.\n\nfrom transformers import T5ForConditionalGeneration, T5Tokenizer\n\nmodel_path = 'path_to_model_directory'\nmodel = T5ForConditionalGeneration.from_pretrained(model_path)\ntokenizer = T5Tokenizer.from_pretrained(model_path)", "# Example\nprint(predict_action(\"Example of a root cause\"))", "# Contributing\nContributions to this model are welcome. You can contribute in the following ways:\n\nData: More data on root causes and actions can help to improve the model's accuracy and robustness.\nCode: Enhancements in the prediction script, additional features, or performance optimizations are appreciated.\nIssues: If you encounter issues while using this model, please report them in the issues section of this repository.", "# License\nThis project is licensed under the MIT License - see the LICENSE file for details.", "# ATTENTION: Still the model is not 100% effeective due lack of data." ]

[ 36, 11, 11, 71, 94, 36, 108, 17, 80, 18, 19 ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n# T5_FINETUNE_Electrical_ts# Fine-Tuned T5 Model for Root Cause Analysis# Description\nThis model is a fine-tuned version of the T5 (Text-to-Text Transfer Transformer) base model, specifically tailored to predict actions based on provided root causes in industrial or technical settings. The model has been trained to understand various root causes and suggest corresponding actions, facilitating faster decision-making and troubleshooting in operational environments.# Model Details\n\nBase Model: T5 Base\n\nTraining Data: The model was trained on a proprietary dataset consisting of documented root causes and the actions taken to resolve them in a manufacturing context.\nFine-Tuning Details: The model was fine-tuned for 3 epochs with a learning rate of 3e-4, using a batch size of 8. The fine-tuning process focused on adapting the T5 model to generate action plans based on textual descriptions of root causes.# Usage\nInstallation\nTo use this model, you will need to install Python and the necessary Python libraries. The primary library required is transformers by Hugging Face.\n\n-> pip install transformers torch# Loading the Model\nYou can load the model using the Transformers library. Ensure you have the model and tokenizer files(final_model.zip) downloaded from the repository or Kaggle dataset.\n\nfrom transformers import T5ForConditionalGeneration, T5Tokenizer\n\nmodel_path = 'path_to_model_directory'\nmodel = T5ForConditionalGeneration.from_pretrained(model_path)\ntokenizer = T5Tokenizer.from_pretrained(model_path)# Example\nprint(predict_action(\"Example of a root cause\"))# Contributing\nContributions to this model are welcome. You can contribute in the following ways:\n\nData: More data on root causes and actions can help to improve the model's accuracy and robustness.\nCode: Enhancements in the prediction script, additional features, or performance optimizations are appreciated.\nIssues: If you encounter issues while using this model, please report them in the issues section of this repository.# License\nThis project is licensed under the MIT License - see the LICENSE file for details.# ATTENTION: Still the model is not 100% effeective due lack of data." ]

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ 41, 164, 5, 44 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3### Training results### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

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

[]

[ "en" ]

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

[ 77, 80 ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n# Uploaded model\n\n- Developed by: Jaspann\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", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ 41, 164, 5, 44 ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #conversational #autotrain_compatible #endpoints_compatible #text-generation-inference #8-bit #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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3### Training results### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "peft", "safetensors", "text-generation", "code-generation", "text-to-text-generation", "conversational", "en", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "region:us" ]

[ "1910.09700" ]

[ "en" ]

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

[ "TAGS\n#peft #safetensors #text-generation #code-generation #text-to-text-generation #conversational #en #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #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" ]

[ 65, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #text-generation #code-generation #text-to-text-generation #conversational #en #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #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", "xlm-roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

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

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

[ 35, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

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

[ "1910.09700" ]

[]

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

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

[ 43, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

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

[ "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" ]

[ 26, 6, 4, 75, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5 ]

[ "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" ]

[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "llama-3-ko", "llama-cpp", "gguf-my-repo", "text-generation", "en", "ko", "license:other", "region:us" ]

[]

[ "en", "ko" ]

[ "# gagagiga/Llama-3-Open-Ko-8B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'beomi/Llama-3-Open-Ko-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#gguf #facebook #meta #pytorch #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #text-generation #en #ko #license-other #region-us \n", "# gagagiga/Llama-3-Open-Ko-8B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'beomi/Llama-3-Open-Ko-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." ]

[ 60, 85, 52 ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #llama-3-ko #llama-cpp #gguf-my-repo #text-generation #en #ko #license-other #region-us \n# gagagiga/Llama-3-Open-Ko-8B-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'beomi/Llama-3-Open-Ko-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." ]

[ "gguf", "meta", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "license:llama3", "region:us" ]

[]

[ "en" ]

[ "# existmaster/Llama-3-8B-Instruct-Gradient-1048k-Q8_0-GGUF\nThis model was converted to GGUF format from 'gradientai/Llama-3-8B-Instruct-Gradient-1048k' 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 #meta #llama-3 #llama-cpp #gguf-my-repo #text-generation #en #license-llama3 #region-us \n", "# existmaster/Llama-3-8B-Instruct-Gradient-1048k-Q8_0-GGUF\nThis model was converted to GGUF format from 'gradientai/Llama-3-8B-Instruct-Gradient-1048k' 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." ]

[ 43, 92, 52 ]

[ "TAGS\n#gguf #meta #llama-3 #llama-cpp #gguf-my-repo #text-generation #en #license-llama3 #region-us \n# existmaster/Llama-3-8B-Instruct-Gradient-1048k-Q8_0-GGUF\nThis model was converted to GGUF format from 'gradientai/Llama-3-8B-Instruct-Gradient-1048k' 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", "gguf", "llama", "text-generation", "meta", "llama-3", "en", "base_model:gradientai/Llama-3-8B-Instruct-Gradient-1048k", "license:other", "autotrain_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #gguf #llama #text-generation #meta #llama-3 #en #base_model-gradientai/Llama-3-8B-Instruct-Gradient-1048k #license-other #autotrain_compatible #text-generation-inference #region-us \n" ]

[ 66 ]

[ "TAGS\n#transformers #gguf #llama #text-generation #meta #llama-3 #en #base_model-gradientai/Llama-3-8B-Instruct-Gradient-1048k #license-other #autotrain_compatible #text-generation-inference #region-us \n" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:google/gemma-2b-it", "license:apache-2.0", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.9.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-google/gemma-2b-it #license-apache-2.0 #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", "## How to Get Started with the Model\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.9.0" ]

[ 43, 6, 4, 50, 23, 3, 5, 8, 9, 8, 34, 20, 4, 5, 5, 11, 13, 12, 3, 10, 6, 5, 6, 4, 5, 7, 49, 7, 7, 5, 5, 15, 7, 7, 8, 5, 13 ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-google/gemma-2b-it #license-apache-2.0 #region-us \n# Model Card for Model ID## Model Details### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Downstream Use [optional]### Out-of-Scope Use## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.## How to Get Started with the Model\n\nUse the code below to get started with the model.## Training Details### Training Data### Training Procedure#### Preprocessing [optional]#### Training Hyperparameters\n\n- Training regime:#### Speeds, Sizes, Times [optional]## Evaluation### Testing Data, Factors & Metrics#### Testing Data#### Factors#### Metrics### Results#### Summary## Model Examination [optional]## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:## Technical Specifications [optional]### Model Architecture and Objective### Compute Infrastructure#### Hardware#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Model Card Authors [optional]## Model Card Contact### Framework versions\n\n- PEFT 0.9.0" ]

[ "gguf", "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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "TAGS\n#gguf #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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3", "### Training results", "### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ 9, 164, 5, 44 ]

[ "TAGS\n#gguf #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: 8\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 8\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 64\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: 3### Training results### Framework versions\n\n\n* Transformers 4.36.2\n* Pytorch 2.1.2+cu121\n* Datasets 2.16.1\n* Tokenizers 0.15.0" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "unsloth", "generated_from_trainer", "base_model:nextab/athena-2b-v1.5", "license:apache-2.0", "region:us" ]

[]

[]

[ "# outputs\n\nThis model is a fine-tuned version of nextab/athena-2b-v1.5 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 3407\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 5\n- training_steps: 100\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.39.3\n- Pytorch 2.1.0+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #unsloth #generated_from_trainer #base_model-nextab/athena-2b-v1.5 #license-apache-2.0 #region-us \n", "# outputs\n\nThis model is a fine-tuned version of nextab/athena-2b-v1.5 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 3407\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 5\n- training_steps: 100\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.39.3\n- Pytorch 2.1.0+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ 56, 29, 7, 9, 9, 4, 132, 5, 52 ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #unsloth #generated_from_trainer #base_model-nextab/athena-2b-v1.5 #license-apache-2.0 #region-us \n# outputs\n\nThis model is a fine-tuned version of nextab/athena-2b-v1.5 on the None dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 3407\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 5\n- training_steps: 100\n- mixed_precision_training: Native AMP### Training results### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.39.3\n- Pytorch 2.1.0+cu121\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "base_model:openai/whisper-tiny.en", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "# whisper\n\nThis model is a fine-tuned version of openai/URL on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 0.5158\n- eval_wer: 19.8611\n- eval_runtime: 49.4294\n- eval_samples_per_second: 10.115\n- eval_steps_per_second: 1.275\n- epoch: 13.8889\n- step: 500", "## 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: 1e-05\n- train_batch_size: 128\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 500\n- training_steps: 1000", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.1.dev0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-tiny.en #license-apache-2.0 #endpoints_compatible #region-us \n", "# whisper\n\nThis model is a fine-tuned version of openai/URL on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 0.5158\n- eval_wer: 19.8611\n- eval_runtime: 49.4294\n- eval_samples_per_second: 10.115\n- eval_steps_per_second: 1.275\n- epoch: 13.8889\n- step: 500", "## 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: 1e-05\n- train_batch_size: 128\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 500\n- training_steps: 1000", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.1.dev0\n- Tokenizers 0.19.1" ]

[ 54, 104, 7, 9, 9, 4, 104, 47 ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #base_model-openai/whisper-tiny.en #license-apache-2.0 #endpoints_compatible #region-us \n# whisper\n\nThis model is a fine-tuned version of openai/URL on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 0.5158\n- eval_wer: 19.8611\n- eval_runtime: 49.4294\n- eval_samples_per_second: 10.115\n- eval_steps_per_second: 1.275\n- epoch: 13.8889\n- step: 500## 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: 1e-05\n- train_batch_size: 128\n- eval_batch_size: 8\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 500\n- training_steps: 1000### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.1.dev0\n- Tokenizers 0.19.1" ]

[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:facebook/opt-1.3b", "license:other", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-facebook/opt-1.3b #license-other #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ 38, 101, 5, 52 ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-facebook/opt-1.3b #license-other #region-us \n### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10### Training results### Framework versions\n\n\n* PEFT 0.10.0\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "safetensors", "trl", "dpo", "generated_from_trainer", "base_model:gpt2", "license:mit", "region:us" ]

[]

[]

[ "# dpo_helpfulhelpful_gpt3_subset20000_modelgpt2_maxsteps5000_bz8_lr5e-06\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 15\n- training_steps: 5000", "### Training results", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #trl #dpo #generated_from_trainer #base_model-gpt2 #license-mit #region-us \n", "# dpo_helpfulhelpful_gpt3_subset20000_modelgpt2_maxsteps5000_bz8_lr5e-06\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 15\n- training_steps: 5000", "### Training results", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ 36, 56, 7, 9, 9, 4, 122, 5, 48 ]

[ "TAGS\n#peft #safetensors #trl #dpo #generated_from_trainer #base_model-gpt2 #license-mit #region-us \n# dpo_helpfulhelpful_gpt3_subset20000_modelgpt2_maxsteps5000_bz8_lr5e-06\n\nThis model is a fine-tuned version of gpt2 on an unknown dataset.## Model description\n\nMore information needed## Intended uses & limitations\n\nMore information needed## Training and evaluation data\n\nMore information needed## Training procedure### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 15\n- training_steps: 5000### Training results### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "peft", "safetensors", "trl", "dpo", "generated_from_trainer", "base_model:gpt2", "license:mit", "region:us" ]

[]

[]

[ "# dpo_helpfulhelpful_gpt3_subset20000_modelgpt2_maxsteps5000_bz8_lr1e-06\n\nThis model is a fine-tuned version of gpt2 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: 1e-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 15\n- training_steps: 5000", "### Training results", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #trl #dpo #generated_from_trainer #base_model-gpt2 #license-mit #region-us \n", "# dpo_helpfulhelpful_gpt3_subset20000_modelgpt2_maxsteps5000_bz8_lr1e-06\n\nThis model is a fine-tuned version of gpt2 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: 1e-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 15\n- training_steps: 5000", "### Training results", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ 36, 56, 7, 9, 9, 4, 122, 5, 48 ]

[ "TAGS\n#peft #safetensors #trl #dpo #generated_from_trainer #base_model-gpt2 #license-mit #region-us \n# dpo_helpfulhelpful_gpt3_subset20000_modelgpt2_maxsteps5000_bz8_lr1e-06\n\nThis model is a fine-tuned version of gpt2 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: 1e-06\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 8\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 15\n- training_steps: 5000### Training results### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.38.2\n- Pytorch 2.1.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]