Update modeling_opt.py

modeling_opt.py

@@ -1086,8 +1086,8 @@ class OPTDecoder(OPTPreTrainedModel):
                     batch_size, mask_seq_length, device=inputs_embeds.device)
             elif attention_mask.shape[1] != mask_seq_length:
                 raise ValueError(
-                    f"The provided attention mask has length {
-                        attention_mask.shape[1]}, but its length should be "
+                    f'''The provided attention mask has length {
+                        attention_mask.shape[1]}, but its length should be '''
                     f"{mask_seq_length} (sum of the lengths of current and past inputs)"
                 )
             causal_attention_mask = _prepare_4d_causal_attention_mask(
@@ -1119,8 +1119,8 @@ class OPTDecoder(OPTPreTrainedModel):
             if attn_mask is not None:
                 if attn_mask.size()[0] != (len(self.layers)):
                     raise ValueError(
-                        f"The `{mask_name}` should be specified for {
-                            len(self.layers)} layers, but it is for"
+                        f'''The `{mask_name}` should be specified for {
+                            len(self.layers)} layers, but it is for'''
                         f" {head_mask.size()[0]}."
                     )