We've released our memory-efficient finetuning algorithm LISA, check out [Paper][User Guide] for more details!

Changelog#

Version 0.0.1 (Mar 28, 2023)#

The first public version.

Task tuning, instruction tuning, on user defined datasets.

A simple and extensible API for developers.

Efficient finetuning with LoRA.

Simplified model inference framework.