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 20:12:59 +11:00
commit e791db9b06
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

@ -225,7 +225,7 @@ def LlamaAttention_fast_forward_inference(
Xn = hidden_states
bsz, _, hd = hidden_states.size()
K1, V1 = past_key_value
dtype = X.dtype
dtype = Xn.dtype
n_heads = self.num_heads
n_groups = self.num_key_value_groups