Update modeling_mpt.py

modeling_mpt.py

@@ -182,7 +182,7 @@ class MPTModel(MPTPreTrainedModel):
             x_shrunk = x * self.embedding_fraction + x.detach() * (1 - self.embedding_fraction)
             assert isinstance(self.emb_drop, nn.Module)
             x = self.emb_drop(x_shrunk)
-        (attn_bias, attention_mask) = self._attn_bias(device=x.device, dtype=x.dtype, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id)
+        (attn_bias, attention_mask) = self._attn_bias(device=x.device, dtype=torch.float32, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id)
         if use_cache and past_key_values is None:
             past_key_values = [() for _ in range(self.config.n_layers)]
         all_hidden_states = () if output_hidden_states else None