license: apache-2.0
language:
- en
- fr
- de
- es
- it
- pt
- ru
- zh
- ja
pipeline_tag: text-generation
tags:
- chat
This is the sixth 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-Large-Instruct-2407.
Prompting
Model has been Instruct tuned with the Mistral formatting. A typical input would look like this:
"""[INST] Hi there! [/INST]Nice to meet you!</s>[INST] Can I ask a question? [/INST]
"""
Credits
- Stheno dataset (filtered)
- anthracite-org/kalo-opus-instruct-22k-no-refusal
- anthracite-org/nopm_claude_writing_fixed
This model has been a team effort, and the credits goes to all members of Anthracite.
Training
The training was done for 1.5 epochs. We used 8x AMD Instinct™ MI300X Accelerators for the full-parameter fine-tuning of the model.
In addition to this, we noticed that Mistral Large models seemed much more sensitive to learning rate adjustments than other models:
We hypothesize this is primarily due to the particularly narrow and low variance weight distributions typical of Mistral derived models regardless of their scale. In the end, we settled on 2e-6 with an effective batch size of 64 (and a packed tokens batch size of 8192; effectively ~500,000 tokens per batch).
We also trained with a weight decay of 0.01 to help further stabilize the loss trajectory and mitigate overfitting.
Safety
...