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 2024-02-01 19:07:30 +11:00
commit a2cb7a113b
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

@ -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])