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 06:37:32 -08:00
commit 7423783462
1 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

11
unsloth/models/rl.py
View file

@ -39,11 +39,14 @@ def PatchRL(FastLanguageModel):
@contextmanager
def unsloth_unwrap_model_for_generation(model, *args, **kwargs):
# Must use for_inference to allow inference in Unsloth
with unwrap_model_for_generation(model, *args, **kwargs) as unwrapped_model:
FastLanguageModel.for_inference(unwrapped_model)
FastLanguageModel.for_inference(model)
try:
unwrapped_model = unwrap_model_for_generation(model, *args, **kwargs)
yield unwrapped_model
# Return back to training mode
FastLanguageModel.for_training(model)
finally:
# Finally return back training
FastLanguageModel.for_training(model)
pass
pass
import trl.trainer