ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama.py

Browse source
This commit is contained in:
Daniel Han 2025-03-04 19:39:49 -08:00
commit 79146518b6
1 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

14
unsloth/models/llama.py
View file

@ -1554,10 +1554,10 @@ def unsloth_fast_generate(
pass
# Must patch accelerate for Xformers
if accelerate_new_send_to_device is not None:
import accelerate.utils.operations
accelerate.utils.operations.send_to_device = accelerate_new_send_to_device
pass
# if accelerate_new_send_to_device is not None:
# import accelerate.utils.operations
# accelerate.utils.operations.send_to_device = accelerate_new_send_to_device
# pass
# For newer HF
kwargs["cache_implementation"] = "dynamic"
@ -1580,9 +1580,9 @@ def unsloth_fast_generate(
pass
# Return accelerate back
if accelerate_new_send_to_device is not None:
accelerate.utils.operations.send_to_device = accelerate_old_send_to_device
pass
# if accelerate_new_send_to_device is not None:
# accelerate.utils.operations.send_to_device = accelerate_old_send_to_device
# pass
FastLlamaModel.for_training(self)