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 20:18:07 -08:00
commit 7816f7e9ac
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
unsloth/models/rl_replacements.py
View file

@ -153,10 +153,10 @@ 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)"
)
# 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)