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

Update rl_replacements.py

Browse source
This commit is contained in:
Daniel Han 2025-06-26 00:27:17 -07:00
commit ea2da65e15
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_replacements.py
View file

@ -251,8 +251,7 @@ def grpo_trainer__get_per_token_logps(function_name, function):
if function_name != "_get_per_token_logps": return function
def _get_per_token_logps(self, model, input_ids, attention_mask, logits_to_keep):
if True: #os.environ.get('UNSLOTH_USE_NEW_MODEL', '0') == '0':
print("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!")
if os.environ.get('UNSLOTH_USE_NEW_MODEL', '0') == '0':
return None # Unsloth efficient GRPO
# Otherwise, calculate normally:
if not hasattr(self, '_autocast_dtype'):