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 2024-12-20 02:46:29 -08:00
commit 474fac2256
1 changed files with 8 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

16
unsloth/models/mistral.py
View file

@ -39,14 +39,14 @@ pass
def MistralAttention_fast_forward(
self,
hidden_states: torch.Tensor,
causal_mask: Optional[xformers.attn_bias.BlockDiagonalCausalMask] = None,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_value: Optional[Tuple[torch.Tensor]] = None,
output_attentions: bool = False,
use_cache: bool = False,
padding_mask: Optional[torch.LongTensor] = None,
hidden_states: torch.Tensor,
causal_mask: Optional[xformers.attn_bias.BlockDiagonalCausalMask] = None,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
past_key_value: Optional[Tuple[torch.Tensor]] = None,
output_attentions: bool = False,
use_cache: bool = False,
padding_mask: Optional[torch.LongTensor] = None,
position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
*args, **kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]: