v0.3.2

hiyouga/LlamaFactoryv0.3.2Nov 21, 2023by hiyouga

AI Summary

A patch release adding support for training GPTQ quantized models and resuming reward model training.

Key Highlights

Support for training GPTQ quantized models
Resume support for reward model training

New Features

GPTQ quantized model training support
Resume reward model training support

Full Release Notes

### New features

- Support training GPTQ quantized model #729 #1481 #1545 
- Support resuming reward model training #1567 

### Bug fix

- Change default PPO parameters by @hannlp in #1553 
- Fix ChatGLM2&3 templates #1453 #1480 
- Fix #1548 by @Outsider565 in #1544 
- Fix #1263 #1550 #1558