license: apache-2.0
language:
- en
- fr
- de
- es
- it
- pt
- ru
- zh
- ja
pipeline_tag: text-generation
tags:
- chat
This is the seventh (Lucky!) 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 Qwen-2 72B Instruct.
Prompting
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
"""
Credits
- anthracite-org/Stheno-Data-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 2 epochs. We used 8x AMD Instinct™ MI300X Accelerators for the full-parameter fine-tuning of the model.
We also trained with a weight decay of 0.01 to help further stabilize the loss trajectory and mitigate catastrophic forgetting, and utilize a peak learning rate of 4e-6 to prevent the 2nd epoch loss from dropping too significantly (as it is a strong indicator of overfitting).
Safety
...