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

Merge branch 'main' into main

Browse Source 
Former-commit-id: 7566589b820e6030269523e9d08c312594f893ae
This commit is contained in:
Zhangchi Feng
2024-09-29 21:32:54 +08:00
committed by GitHub
parent ab5d042cd3 6050e6cff9
commit 689f5c4554
3 changed files with 26 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/llamafactory/model/model_utils/attention.py
View File

@@ -37,10 +37,11 @@ def configure_attn_implementation(
if is_flash_attn_2_available():
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")
logger.warning("Gemma-2 should use flash attention 2, change `flash_attn` to fa2.")
model_args.flash_attn = "fa2"
if model_args.flash_attn != "fa2":
logger.warning("Gemma-2 should use flash attention 2, change `flash_attn` to fa2.")
model_args.flash_attn = "fa2"
else:
logger.warning("Gemma-2 should use eager attention, change `flash_attn` to disabled.")
logger.warning("FlashAttention-2 is not installed, use eager attention.")
model_args.flash_attn = "disabled"
elif model_args.flash_attn == "sdpa":
logger.warning("Gemma-2 should use soft-capping attention, while the SDPA attention does not support it.")