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 19:44:45 +11:00
commit f186fe9bc9
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/mistral.py
View file

@ -69,8 +69,7 @@ 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)
print(hidden_states.shape, Q.shape, K.shape, V.shape, type(past_key_value))
kv_seq_len = K.shape[-2]
if past_key_value is not None:
@ -98,6 +97,7 @@ def MistralAttention_fast_forward(
Q = Q.transpose(1, 2)
K = K.transpose(1, 2)
V = V.transpose(1, 2)
print(Q.shape, K.shape, V.shape)
M = bsz * q_len
has_swa = isinstance(causal_mask, xformers.attn_bias.BlockDiagonalCausalMask)