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 2024-02-24 03:14:29 +11:00
commit 20227ba5c7
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

@ -203,7 +203,7 @@ def LlamaAttention_fast_forward_inference(
A = torch.matmul(A, Vnn, out = Qn)
A = A.transpose(1, 2)
A = A.reshape(bsz, 1, attention_size)
A = fast_linear_forward(self.o_proj, A, out = self.temp_QA[1][:,:,self.hidden_size])
A = fast_linear_forward(self.o_proj, A)#, out = self.temp_QA[1][:,:,self.hidden_size])
return A, (Kn, Vn)
pass