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-Chen 2024-01-31 19:48:33 +11:00
commit 7227de48cf
1 changed files with 1 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
unsloth/models/llama.py
View file

@ -351,7 +351,7 @@ def LlamaAttention_fast_forward(
past_key_value = (K, V) if use_cache else None
# Attention module
if (not HAS_FLASH_ATTENTION):
if False:#(not HAS_FLASH_ATTENTION):
# Xformers memory efficient attention
# Also has Flash Attention v2 dispatching
Q = Q.transpose(1, 2)
@ -574,7 +574,6 @@ def LlamaModel_fast_forward(
pass
# Ignore attention_mask
print(attention_mask)
if attention_mask is None:
padding_mask = None
elif False: