diff --git a/src/sparseml/transformers/sparsification/modification/modifying_opt.py b/src/sparseml/transformers/sparsification/modification/modifying_opt.py
index 438b08b448a..4d2fd58c4f2 100644
--- a/src/sparseml/transformers/sparsification/modification/modifying_opt.py
+++ b/src/sparseml/transformers/sparsification/modification/modifying_opt.py
@@ -170,7 +170,7 @@ def forward(
 
         if attn_weights.size() != (bsz * self.num_heads, tgt_len, src_len):
             raise ValueError(
-                f"Attention weights should be of size {(bsz * self.num_heads, tgt_len, src_len)}, but is"
+                f"Attention weights should be of size {(bsz * self.num_heads, tgt_len, src_len)}, but is"  # noqa
                 f" {attn_weights.size()}"
             )