Update modeling_opt.py

modeling_opt.py

@@ -41,6 +41,7 @@ from transformers.utils import (
     is_flash_attn_greater_or_equal_2_10,
     logging,
     replace_return_docstrings,
+
 )
 from .configuration_opt import OPTConfig
 
@@ -294,8 +295,8 @@ class OPTAttention(nn.Module):
 
         if attn_output.size() != (bsz * self.num_heads, tgt_len, self.head_dim):
             raise ValueError(
-                f"`attn_output` should be of size {
-                    (bsz, self.num_heads, tgt_len, self.head_dim)}, but is"
+                f'''`attn_output` should be of size {
+                    (bsz, self.num_heads, tgt_len, self.head_dim)}, but is'''
                 f" {attn_output.size()}"
             )