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 2025-02-18 00:05:40 -08:00
commit fa831423b3
1 changed files with 2 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

10
unsloth/models/rl.py
View file

@ -442,12 +442,6 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
# Selective log softmax
selective_log_softmax_code = inspect.getsource(selective_log_softmax)
# Trainer kwargs
comma = "" if RLTrainer_call_args.endswith(",") else ","
unsloth_extra_args = comma + \
"vllm_sampling_params = vllm_sampling_params,\n"\
"unsloth_num_chunks = unsloth_num_chunks, **kwargs"
# Get final source code
RLTrainer_source = RLTrainer_replacement.format(
RLTrainer_name = RLTrainer_name,
@ -455,14 +449,14 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
RLTrainer_arguments = RLTrainer_arguments,
RLTrainer_extra_args = RLTrainer_extra_args,
RLTrainer_call_args = RLTrainer_call_args,
RLTrainer_kwargs = ",**kwargs"[1 if RLTrainer_call_args .endswith(",") else 0:],
RLTrainer_kwargs = ",**kwargs"[1 if RLTrainer_call_args.endswith(",") else 0:],
RLConfig_name = RLConfig_name,
__RLConfig_doc__ = __RLConfig_doc__,
RLConfig_arguments = RLConfig_arguments,
RLConfig_extra_args = RLConfig_extra_args,
RLConfig_call_args = RLConfig_call_args,
RLConfig_kwargs = unsloth_extra_args,
RLConfig_kwargs = ",**kwargs"[1 if RLConfig_call_args .endswith(",") else 0:],
RLTrainer_extras = RLTrainer_extras,
RLTrainer_post = RLTrainer_post,