ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama.py

Browse source
This commit is contained in:
Daniel Han-Chen 2024-01-23 02:44:52 +11:00
commit 24c7a67556
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
unsloth/models/llama.py
View file

@ -180,7 +180,7 @@ def LlamaAttention_fast_forward_inference(
A = fast_linear_forward(self.o_proj, A)
A = A.reshape(1, 1, self.hidden_size)
return A, (Kn, Vn)
return A, (Kn.unsqueeze(0), Vn.unsqueeze(0))
pass