added padding_side in the tokenizer _pad() method

tokenization_chatglm.py

@@ -263,6 +263,7 @@ class ChatGLM4Tokenizer(PreTrainedTokenizer):
             self,
             encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
             max_length: Optional[int] = None,
+            padding_side: str = 'left',
             padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
             pad_to_multiple_of: Optional[int] = None,
             return_attention_mask: Optional[bool] = None,