From a2cb7a113b3f03de5a45108cd2e2e866aabf8b1c Mon Sep 17 00:00:00 2001 From: Daniel Han-Chen Date: Thu, 1 Feb 2024 19:07:30 +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 3e15b82876..53dec892fb 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -285,7 +285,7 @@ def fast_mlp_inference(self, X): # gate = self.gate_proj(X) # up = self.up_proj(X) bsz, _, hd = X.shape - mlp_size = model.config.intermediate_size + mlp_size = self.config.intermediate_size # temp = torch.empty((2, bsz, 1, mlp_size), dtype = X.dtype, device = "cuda") gate = fast_linear_forward(self.gate_proj, X)#, out = temp[0])