This is a fine-tuning of the LLaMa7B model in the style of the Alpaca dataset and setting but using LoRa.

This model process was copied exactly as instructed by @samwit and his original model repo is here: samwit/alpaca7B-lora This was done for my own instructive purposes.

His original code to fine-tune are here. His original youtube video is here.

For details of the data and hyper params - https://crfm.stanford.edu/2023/03/13/alpaca.html

This repo only contains the LoRa weights and not the original LLaMa weights which are research only.