A Step-by-Step Guide to Fine-Tuning Your Dolly Model (tutorial)

Fine tuning Dolly Colab: https://colab.research.google.com/drive/1pJ3wV49OmrspwAfg52_Y6f5B7MILWTxR?usp=sharing

How to finetune your own Dolly model
In this video we go through how to finetune a Dolly model using low rank adaption (LoRa). We use the cleaned alpaca dataset and the PEFT library to create a finetuned version which we can push to HuggingFace hub.

alpaca dataset dolly fine-tuning guide hub huggingface library lora low through tutorial video