v0.3.3

hiyouga/LlamaFactoryv0.3.3Dec 3, 2023by hiyouga

AI Summary

Adds ModelScope Hub integration and a reward model server for API demos and PPO training.

Key Highlights

Support for loading models from ModelScope Hub
Reward model server support in API demo

New Features

ModelScope Hub integration
Reward model server support
Adjustable shard size for exported models

Full Release Notes

### New features

- Support loading pre-trained models from ModelScope Hub by @tastelikefeet in #1700 
- Support launching a reward model server in demo API via specifying `--stage=rm` in `api_demo.py`
- Support using a reward model server in PPO training via specifying `--reward_model_type api`
- Support adjusting the shard size of exported models via the `export_size` argument

### New models

- Base models
  - DeepseekLLM-Base (7B/67B)
  - Qwen (1.8B/72B)
- Instruct/Chat models
  - DeepseekLLM-Chat (7B/67B)
  - Qwen-Chat (1.8B/72B)
  - Yi-34B-Chat

### New datasets

- Supervised fine-tuning datasets
  - Nectar dataset by @mlinmg in #1689 
- Preference datasets
  - Nectar dataset by @mlinmg in #1689 

### Bug fix

- Improve get_current_device by @billvsme in #1690 
- Improve web UI preview by @Samge0 in #1695 
- Fix #1543 #1597 #1657 #1658 #1659 #1668 #1682 #1696 #1699 #1703 #1707 #1710