|
train_distill_reason.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
train_distillation.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
train_dpo.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
train_full_sft.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
train_grpo.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
train_lora.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
train_ppo.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
train_pretrain.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
train_spo.py
|
[fix] model device
|
2025-10-29 10:36:28 +08:00 |
|
trainer_utils.py
|
[feat] pause-training
|
2025-10-26 18:49:52 +08:00 |