Dolly

This fine-tunes the GPT-J 6B model on the Alpaca dataset using a Databricks notebook. Please note that while GPT-J 6B is Apache 2.0 licensed, the Alpaca dataset is licensed under Creative Commons NonCommercial (CC BY-NC 4.0).

To use:

• Load all the files into a Databricks repo.
• Start a 12.2 LTS ML (includes Apache Spark 3.3.2, GPU, Scala 2.12) single-node cluster with node type having 8 A100 GPUs (e.g. Standard_ND96asr_v4 or p4d.24xlarge).
• Open the train_dolly notebook and run it.