mirror of
https://github.com/hiyouga/LlamaFactory.git
synced 2026-01-31 06:42:05 +00:00
6 lines
101 B
Markdown
6 lines
101 B
Markdown
Usage:
|
|
|
|
- `pretrain.sh`
|
|
- `sft.sh` -> `reward.sh` -> `ppo.sh`
|
|
- `sft.sh` -> `dpo.sh` -> `predict.sh`
|