Fix #7331 (#7732)

src/transformers/modeling_gpt2.py

@@ -584,7 +584,7 @@ class GPT2Model(GPT2PreTrainedModel):
             # positions we want to attend and -10000.0 for masked positions.
             # Since we are adding it to the raw scores before the softmax, this is
             # effectively the same as removing these entirely.
-            attention_mask = attention_mask.to(dtype=next(self.parameters()).dtype)  # fp16 compatibility
+            attention_mask = attention_mask.to(dtype=self.dtype)  # fp16 compatibility
             attention_mask = (1.0 - attention_mask) * -10000.0
 
         # If a 2D ou 3D attention mask is provided for the cross-attention