Update modeling_norbert.py

modeling_norbert.py

@@ -163,7 +163,7 @@ class Attention(nn.Module):
             position_indices = torch.arange(query_len, dtype=torch.long).unsqueeze(1) \
                 - torch.arange(query_len, dtype=torch.long).unsqueeze(0)
             position_indices = self.make_log_bucket_position(position_indices, self.config.position_bucket_size, 512)
-            position_indices = self.position_bucket_size - 1 + position_indices
+            position_indices = self.config.position_bucket_size - 1 + position_indices
             self.position_indices = position_indices.to(hidden_states.device)
 
         hidden_states = self.pre_layer_norm(hidden_states)