Wenyu Zhang c8972f7e89 sft should use pretrain model		2025-04-26 11:50:23 -04:00
..
train_distill_reason.py	250426	2025-04-26 10:05:47 +08:00
train_distillation.py	250426	2025-04-26 10:05:47 +08:00
train_dpo.py	250426	2025-04-26 10:05:47 +08:00
train_full_sft.py	sft should use pretrain model	2025-04-26 11:50:23 -04:00
train_lora.py	250426	2025-04-26 10:05:47 +08:00
train_pretrain.py	250426	2025-04-26 10:05:47 +08:00