huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Set qkv attention layer bias to True

Browse Source
This commit is contained in:
Jason Cheng 2024-02-21 21:38:43 +08:00
parent bb57cb34e0
commit 605e0369c4
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/custom_modeling/flash_qwen2_modeling.py
View File

@ -26,7 +26,7 @@ def load_attention(config, prefix, weights):
prefixes=[f"{prefix}.q_proj", f"{prefix}.k_proj", f"{prefix}.v_proj"], prefixes=[f"{prefix}.q_proj", f"{prefix}.k_proj", f"{prefix}.v_proj"],
dim=0, dim=0,
weights=weights, weights=weights,
bias=False, bias=True,
) )