This is the first 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.
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
1"""<|im_start|>user
2Hi there!<|im_end|>
3<|im_start|>assistant
4Nice to meet you!<|im_end|>
5<|im_start|>user
6Can I ask a question?<|im_end|>
7<|im_start|>assistant
8"""
And last but not least, we'd like to thank
Kearm for sponsoring the compute needed to train this model.
The training was done with 55 million tokens of high-quality RP data, over 1.5 epochs. We used 8x
AMD Instinct™ MI300X Accelerators for the full-parameter fine-tuning of the model.
...
