ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support full-parameter PPO

Browse Source 
Former-commit-id: 4af967d69475e1c9fdf1a7983cd6b83bd431abff
This commit is contained in:
hiyouga
2023-11-16 02:08:04 +08:00
parent 8263b2d32d
commit 7a3a0144a5
19 changed files with 280 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llmtuner/train/dpo/trainer.py
View File

@@ -43,7 +43,11 @@ class CustomDPOTrainer(DPOTrainer):
if ref_model is not None:
if self.is_deepspeed_enabled:
self.ref_model = self._prepare_deepspeed(self.ref_model)
if not (
getattr(ref_model, "is_loaded_in_8bit", False)
or getattr(ref_model, "is_loaded_in_4bit", False)
): # quantized models are already set on the correct device
self.ref_model = self._prepare_deepspeed(self.ref_model)
else:
self.ref_model = self.accelerator.prepare_model(self.ref_model, evaluation_mode=True)