metadata

license: llama3.1
datasets:
  - leftyfeep/fiction-chapters-24kmax
base_model:
  - unsloth/Llama-3.1-8B-Instruct-unsloth-bnb-4bit
tags:
  - unsloth
  - trl
  - sft

About

This is another experiment in fiction generation. It uses my Fiction Chapters dataset and finetunes Llama3.1 8B Instruct.

I used the Llama 3.1 chat format in training.

Built with Llama.

Trained using unsloth.

Thanks to gutenberg volunteers who made the dataset possible.