microsoft/phi-2
microsoft/phi-2
1
0
Overview Code Discussions Pull Requests Wiki Activity

Update modeling_phi.py

Browse Source
This commit is contained in:
Gustavo de Rosa 2024-01-16 16:06:28 +00:00 committed by system
parent 39afec137e
commit accfee56d8
No known key found for this signature in database
GPG Key ID: 6A528E38E0733467
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modeling_phi.py
View File

@ -506,7 +506,7 @@ class PhiFlashAttention2(PhiAttention):
value_states = value_states.to(target_dtype)
attn_output = self._flash_attention_forward(
query_states, key_states, value_states, attention_mask, q_len, dropout=attn_dropout, softmax_scale=1.0
query_states, key_states, value_states, attention_mask, q_len, dropout=attn_dropout, softmax_scale=None
)
attn_output = attn_output.reshape(bsz, q_len, self.hidden_size).contiguous()