ChatLLaMA 0.0.4
Pre-release
Pre-release
·
177 commits
to main
since this release
Release Notes - ChatLLaMA 0.0.4
Major release of ChatLLaMA adding support to efficient training using LoRA.
New Features
- HF-based models can now be trained on both actor and RLHF using LoRA. This will help users in reducing the memory needed for training.