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 2025-02-13 02:01:51 -08:00
commit ca8080290c
1 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

10
unsloth/models/rl_replacements.py
View file

@ -168,12 +168,12 @@ def grpo_trainer__get_per_token_logps(function_name, function):
)
if len(original) != 0:
spaces, original = original[0]
spaces = len(spaces)
spaces = len(spaces) + 4
replacer = \
"with torch.amp.autocast(device_type = 'cuda', "\
"dtype = torch.float16 if os.environ.get('ACCELERATE_MIXED_PRECISION', 'fp16') == 'fp16' else torch.bfloat16) "\
"if not torch.is_autocast_enabled('cuda') else nullcontext():\n" + \
" "*(spaces + 4) + original
"if not hasattr(self, '_autocast_dtype'):\n" + \
" "*spaces + "self._autocast_dtype = torch.float16 if os.environ.get('ACCELERATE_MIXED_PRECISION', 'fp16') == 'fp16' else torch.bfloat16\n" + \
"with torch.amp.autocast(device_type = 'cuda', dtype = self._autocast_dtype):\n" + \
" "*spaces + original
function = function.replace(original, replacer)
pass
return function