From 20227ba5c774dea025eacee4c922606465957636 Mon Sep 17 00:00:00 2001 From: Daniel Han-Chen Date: Sat, 24 Feb 2024 03:14:29 +1100 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 05b52e5439..623855d290 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -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