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 2024-01-22 04:25:37 +11:00
commit e34393f975
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

@ -108,7 +108,7 @@ def LlamaAttention_fast_forward_inference(
head_dim = self.head_dim
# assert(n_kv_heads * n_groups == n_heads)
Xn = hidden_states.view(n_heads, head_dim)
Xn = hidden_states.view(1, self.hidden_size)
K1, V1 = past_key_value
# LoRA or general matrix multiplication