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

Handle TRL version compatibility in rl_replacements.py (#3540)

Browse source
This commit is contained in:
pluesclues 2025-11-01 08:17:27 -04:00 • committed by GitHub
commit 35f903b42d
1 changed files with 12 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

18
unsloth/models/rl_replacements.py
View file

@ -215,13 +215,19 @@ def grpo_trainer__generate_and_score_completions(function_name, function):
# The new multi-line string that will replace the line above
replacement_lines = """
batch_size = self.args.per_device_train_batch_size if mode == "train" else self.args.per_device_eval_batch_size
if not has_images:
# Left pad prompt before calculation old and ref hidden states
prompt_completion_ids = left_pack_padding(prompt_completion_ids, self.processing_class.pad_token_id)
self.model.for_training()"""
try:
#TRL 0.23.1 and below path
if not has_images:
# Left pad prompt before calculation old and ref hidden states
prompt_completion_ids = left_pack_padding(prompt_completion_ids, self.processing_class.pad_token_id)
self.model.for_training()
except:
#TRL 0.24.0 and below path
if images is None:
# Left pad prompt before calculation old and ref hidden states
prompt_completion_ids = left_pack_padding(prompt_completion_ids, self.processing_class.pad_token_id)
self.model.for_training()"""
if "has_images" not in function:
raise NotImplementedError("Unsloth: For now we support `trl<=0.23.1`. Please downgrade!")
function = function.replace(line_to_replace, replacement_lines)
pattern_to_find = re.compile(