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 2025-02-12 18:50:45 -08:00
commit 83a2d4282c
1 changed files with 14 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

14
unsloth/models/rl_replacements.py
View file

@ -146,3 +146,17 @@ def grpo_trainer__move_model_to_vllm(function_name, function):
return " "*function.find("def") + replacement
pass
RL_FUNCTIONS["grpo_trainer"].append(grpo_trainer__move_model_to_vllm)
# Edit _get_per_token_logps
def grpo_trainer__get_per_token_logps(function_name, function):
if function_name != "_get_per_token_logps": return function
# Set attention_mask to boolean
function = function.replace(
"attention_mask=attention_mask",
"attention_mask=attention_mask.to(torch.bool)"
)
return function
pass
RL_FUNCTIONS["grpo_trainer"].append(grpo_trainer__get_per_token_logps)