Update modeling_minimonkey_chat.py

modeling_minimonkey_chat.py

@@ -280,8 +280,8 @@ class MiniMonkeyChatModel(PreTrainedModel):
             query = query.replace('<image>', image_tokens, 1)
 
         model_inputs = tokenizer(query, return_tensors='pt')
-        input_ids = model_inputs['input_ids'].cuda()
-        attention_mask = model_inputs['attention_mask'].cuda()
+        input_ids = model_inputs['input_ids'].to(self.device)
+        attention_mask = model_inputs['attention_mask'].to(self.device)
         generation_config['eos_token_id'] = eos_token_id
         generation_output = self.generate(
             pixel_values=pixel_values,