metadata
license: apache-2.0
language:
- en
- fr
- de
- es
- it
- pt
- ru
- zh
- ja
pipeline_tag: text-generation
tags:
- chat
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.
Prompting
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
"""<|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
- NobodyExistsOnTheInternet/PhiloGlanSharegpt
- NobodyExistsOnTheInternet/Magpie-Reasoning-Medium-Subset
- kalomaze/Opus_Instruct_25k
- Nopm/Opus_WritingStruct
- 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 GPUs for the full-parameter fine-tuning of the model.
Safety
...