ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update rl.py

Browse source
This commit is contained in:
Daniel Han 2025-02-05 06:32:51 -08:00
commit 4b108654bd
1 changed files with 1 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
unsloth/models/rl.py
View file

@ -43,8 +43,7 @@ def PatchRL(FastLanguageModel):
FastLanguageModel.for_inference(unwrapped_model)
yield unwrapped_model
# Return back to training mode
FastLanguageModel.for_training (model)
yield model
FastLanguageModel.for_training(model)
pass
import trl.trainer