--- license: apache-2.0 language: - en - fr - de - es - it - pt - ru - zh - ja pipeline_tag: text-generation tags: - chat --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/A9n8EJBDQziJWnXhOYeEE.png) This is the fourth in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of [Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407). ## Prompting Model has been Instruct tuned with the ChatML formatting. A typical input would look like this: ```py """<|im_start|>system You are a friendly assistant.<|im_end|> <|im_start|>user Hi there!<|im_end|> <|im_start|>assistant Nice to meet you!<|im_end|> <|im_start|>user Can I ask a question?<|im_end|> <|im_start|>assistant """ ``` ## Credits - Stheno dataset (filtered) - [NobodyExistsOnTheInternet/claude_3.5s_single_turn_unslop_filtered](https://huggingface.co/datasets/NobodyExistsOnTheInternet/claude_3.5s_single_turn_unslop_filtered) - [NobodyExistsOnTheInternet/PhiloGlanSharegpt](https://huggingface.co/datasets/NobodyExistsOnTheInternet/PhiloGlanSharegpt) - [NobodyExistsOnTheInternet/Magpie-Reasoning-Medium-Subset](https://huggingface.co/datasets/NobodyExistsOnTheInternet/Magpie-Reasoning-Medium-Subset) - [kalomaze/Opus_Instruct_25k](https://huggingface.co/datasets/kalomaze/Opus_Instruct_25k) - [Nopm/Opus_WritingStruct](https://huggingface.co/datasets/Nopm/Opus_WritingStruct) - [Gryphe/Sonnet3.5-SlimOrcaDedupCleaned](https://huggingface.co/datasets/Gryphe/Sonnet3.5-SlimOrcaDedupCleaned) (A ~16k rows subset) This model has been a team effort, and the credits goes to all members of Anthracite. ## Training The training was done for 2 epochs. We used 8x [NVIDIA H100 Tensor Core](https://www.nvidia.com/en-us/data-center/h100/) GPUs for the full-parameter fine-tuning of the model. [Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) ## Safety ...