Update mistral.py

This commit is contained in:
Daniel Han-Chen 2024-01-23 19:28:17 +11:00
commit e184b06c4b

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: