diff --git a/unsloth/models/granite.py b/unsloth/models/granite.py index 2229636e9e..9466a8d6c1 100644 --- a/unsloth/models/granite.py +++ b/unsloth/models/granite.py @@ -60,7 +60,7 @@ pass def GraniteAttention_fast_forward( self, hidden_states: torch.Tensor, - causal_mask: Optional[xformers.attn_bias.BlockDiagonalCausalMask] = None, + causal_mask: Optional[BlockDiagonalCausalMask] = None, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_value: Optional[Tuple[torch.Tensor]] = None, @@ -171,7 +171,7 @@ pass def GraniteDecoderLayer_fast_forward( self, hidden_states: torch.Tensor, - causal_mask: Optional[xformers.attn_bias.BlockDiagonalCausalMask] = None, + causal_mask: Optional[BlockDiagonalCausalMask] = None, attention_mask: Optional[torch.Tensor] = None, position_ids: Optional[torch.LongTensor] = None, past_key_value: Optional[Tuple[torch.Tensor]] = None,