magnum-v2
Collection
12 items
•
Updated
•
7
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.
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
"""<|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
"""
This model has been a team effort, and the credits goes to all members of Anthracite.
The training was done for 2 epochs. We used 8x NVIDIA H100 Tensor Core GPUs for the full-parameter fine-tuning of the model.
...
Base model
mistralai/Mistral-Nemo-Base-2407