This is the second 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
Qwen1.5 32B.
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"""
Three new general purpose instruction following datasets were added on top of the original Stheno dataset (which had certain low quality entries purged/removed).
The first two were designed specifically for the Magnum series, to better address prompt adherence and coherence:
This model has been a team effort, and the credits goes to all members of Anthracite.
The training was done for 2 epochs with a learning rate of 1e-05. We used 8x
NVIDIA H100 Tensor Core GPUs for the full-parameter fine-tuning of the model.
...
