GPRM's picture
Create README.md
f613d06 verified

A straightforward implementation of the final Self-Alignment model, inspired by the paper "Self-Alignment with Instruction Backtranslation."

This model was fine-tuned on LLaMA-2-hf using self-curation LIMA dataset with high-quality sythetic (Instruction, Answer) pairs.

The fine-tuning process was conducted using LoRA, and the uploaded model is provided in its merged form.