diff --git a/modeling_chatglm.py b/modeling_chatglm.py
index e2ff3f2..ef38154 100644
--- a/modeling_chatglm.py
+++ b/modeling_chatglm.py
@@ -1243,7 +1243,7 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
             for i, (old_query, response) in enumerate(history):
                 prompt += "[Round {}]\n问：{}\n答：{}\n".format(i, old_query, response)
             prompt += "[Round {}]\n问：{}\n答：".format(len(history), query)
-        inputs = tokenizer([prompt], return_tensors="pt", padding=True)
+        inputs = tokenizer([prompt], return_tensors="pt")
         inputs = inputs.to(self.device)
         outputs = self.generate(**inputs, **gen_kwargs)
         outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):]
@@ -1269,7 +1269,7 @@ class ChatGLMForConditionalGeneration(ChatGLMPreTrainedModel):
             for i, (old_query, response) in enumerate(history):
                 prompt += "[Round {}]\n问：{}\n答：{}\n".format(i, old_query, response)
             prompt += "[Round {}]\n问：{}\n答：".format(len(history), query)
-        inputs = tokenizer([prompt], return_tensors="pt", padding=True)
+        inputs = tokenizer([prompt], return_tensors="pt")
         inputs = inputs.to(self.device)
         for outputs in self.stream_generate(**inputs, **gen_kwargs):
             outputs = outputs.tolist()[0][len(inputs["input_ids"][0]):]