knox revised this gist . Go to revision
1 file changed, 10 insertions
LLaMA-Factory-2.md(file created)
| @@ -0,0 +1,10 @@ | |||
| 1 | + | | Approach | Full-tuning | Freeze-tuning | LoRA | QLoRA | | |
| 2 | + | | ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ | | |
| 3 | + | | Pre-Training | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | |
| 4 | + | | Supervised Fine-Tuning | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | |
| 5 | + | | Reward Modeling | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | |
| 6 | + | | PPO Training | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | |
| 7 | + | | DPO Training | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | |
| 8 | + | | KTO Training | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | |
| 9 | + | | ORPO Training | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | |
| 10 | + | | SimPO Training | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | |
Newer
Older