deepseekmirror/DeepSeek-V3
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V3.git synced 2025-04-18 09:38:58 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge pull request #556 from XxAlonexX/main

Browse Source 
Fix Linear Layer Bias Initialization
This commit is contained in:
Xingkai Yu 2025-02-05 16:23:02 +08:00 committed by GitHub
commit 87a01053e4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
inference/model.py
View File

@ -185,7 +185,7 @@ class Linear(nn.Module):
else:
self.register_parameter("scale", None)
if bias:
self.bias = nn.Parameter(torch.empty(self.part_out_features))
self.bias = nn.Parameter(torch.empty(out_features))
else:
self.register_parameter("bias", None)