This Llama 3.2 model was fine tuned on two combined data sets, one full of writing coach conversations, the other containing actual creative writing samples. Both data sets used were synthetic.

The model was fine-tuned for 2 epochs.

You can find a more in-depth description of this model and its intended use in this blog post.

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.