lucas
/
LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

made a small change to a warning about fa2 for gemma2 models.

This commit is contained in:
Amirreza A 2024-09-28 19:03:36 +03:30
parent 6b62550af1
commit 94ee105526
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/llamafactory/model/model_utils/attention.py
View File

@ -37,7 +37,10 @@ def configure_attn_implementation(
if is_flash_attn_2_available(): if is_flash_attn_2_available():
require_version("transformers>=4.42.4", "To fix: pip install transformers>=4.42.4") require_version("transformers>=4.42.4", "To fix: pip install transformers>=4.42.4")
require_version("flash_attn>=2.6.3", "To fix: pip install flash_attn>=2.6.3") require_version("flash_attn>=2.6.3", "To fix: pip install flash_attn>=2.6.3")
if model_args.flash_attn != "fa2":
logger.warning("Gemma-2 should use flash attention 2, change `flash_attn` to fa2.") logger.warning("Gemma-2 should use flash attention 2, change `flash_attn` to fa2.")
model_args.flash_attn = "fa2" model_args.flash_attn = "fa2"
else: else:
logger.warning("Gemma-2 should use eager attention, change `flash_attn` to disabled.") logger.warning("Gemma-2 should use eager attention, change `flash_attn` to disabled.")