fix attention mask

modeling_gptbert.py

@@ -615,9 +615,9 @@ class GptBertModel(GptBertPreTrainedModel):
             padding_info = (indices, cu_seqlens, max_seqlen_in_batch)
         else:
             if len(attention_mask.size()) == 2:
-                attention_mask = attention_mask.unsqueeze(1).unsqueeze(2)
-            elif len(attention_mask.size()) == 3:
                 attention_mask = attention_mask.unsqueeze(1)
+            if len(attention_mask.size()) != 3:
+                raise ValueError("Bare `attention_mask` med to eller tre dimensjoner støttes nå for SDPA.")
             padding_info = attention_mask
 
         static_embeddings = self.embedding(input_ids)