ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update mistral.py

Browse source
This commit is contained in:
Daniel Han-Chen 2024-01-23 19:28:17 +11:00
commit e184b06c4b
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
unsloth/models/mistral.py
View file

@ -69,6 +69,8 @@ def MistralAttention_fast_forward(
Q = Q.view(bsz, q_len, n_heads, head_dim).transpose(1, 2)
K = K.view(bsz, q_len, n_kv_heads, head_dim).transpose(1, 2)
V = V.view(bsz, q_len, n_kv_heads, head_dim).transpose(1, 2)
print(hidden_states.shape)
print(Q.shape, K.shape, V.shape)
kv_seq_len = K.shape[-2]
if past_key_value is not None: