423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-05 10:22:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix attn patch for kimivl (#7867)

Browse Source
This commit is contained in:
Kingsley 2025-04-27 23:12:28 +08:00 committed by GitHub
parent 4ec560df1c
commit 3e2460bb38
1 changed files with 3 additions and 0 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

@ -69,6 +69,9 @@ def configure_attn_implementation(
if getattr(config, "model_type", None) == "internlm2": # special case for custom models
setattr(config, "attn_implementation", requested_attn_implementation)
elif getattr(config, "model_type", None) == "kimi_vl":
setattr(config.vision_config, "_attn_implementation", requested_attn_implementation)
setattr(config.text_config, "_attn_implementation", requested_attn_implementation)
else:
setattr(config, "_attn_implementation", requested_attn_implementation)