Support for PT2C

modeling_mpt.py

@@ -152,7 +152,7 @@ class MPTModel(MPTPreTrainedModel):
         if output_attentions:
             if self.attn_impl != 'torch':
                 raise NotImplementedError('output_attentions is not implemented for MPT when using attn_impl `flash` or `triton`.')
-        if attention_mask is not None and attention_mask[:, 0].sum() != attention_mask.shape[0] and self.training:
+        if self.training and attention_mask is not None and attention_mask[:, 0].sum() != attention_mask.shape[0]:
             raise NotImplementedError('MPT does not support training with left padding.')
         if self.prefix_lm and prefix_mask is None:
             raise ValueError('prefix_mask is a required argument when MPT is configured with prefix_lm=True.')