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 2024-02-04 03:27:15 +11:00
commit d867b9bbdf
1 changed files with 0 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
unsloth/models/llama.py
View file

@ -309,7 +309,6 @@ def LlamaAttention_fast_forward(
V = V.transpose(1, 2)
A = flash_attn_func(Q, K, V, causal = True)
else:
print(2)
# Grouped query attention
if n_groups != 1:
K = K[:, :, None, :, :].expand(bsz, n_kv_heads, n_groups, kv_seq_len, head_dim)