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 2025-02-06 02:31:01 -08:00
commit 06811d3826
1 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

8
unsloth/models/rl.py
View file

@ -353,6 +353,13 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
source,
)
# .state_dict()
source = re.sub(
r"\.state_dict\(\)",
r"",
source,
)
# Replace self.llm.generate and self.llm.chat
lora_name = trainer_file + "_lora_model"
source = re.sub(
@ -382,6 +389,7 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
f"class {RLTrainer_name}", f"class Unsloth{RLTrainer_name}", 1
)
# Create new class in compiled cache and import it
module = create_new_function(
RLTrainer_name,
RLTrainer_source,