TypeError: ChatGLM4Tokenizer._pad() got an unexpected keyword argument 'padding_side'
File "/cpfs01/user/xiaolinchen/opencompass_fork/opencompass/openicl/icl_inferencer/icl_ppl_inferencer.py", line 113, in inference
prompt_token_num = self.model.get_token_len_from_template(prompt, mode='ppl')
File "/cpfs01/user/xiaolinchen/opencompass_fork/opencompass/models/base.py", line 225, in get_token_len_from_template
token_lens = [self.get_token_len(prompt) for prompt in prompts]
File "/cpfs01/user/xiaolinchen/opencompass_fork/opencompass/models/base.py", line 225, in
token_lens = [self.get_token_len(prompt) for prompt in prompts]
File "/cpfs01/user/xiaolinchen/opencompass_fork/opencompass/models/huggingface_above_v4_33.py", line 638, in get_token_len
t = self.tokenizer(m, add_special_tokens=add_special_tokens)
File "/cpfs01/user/xiaolinchen/miniconda3/envs/oc_lmdeploy/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 3016, in call
encodings = self._call_one(text=text, text_pair=text_pair, **all_kwargs)
File "/cpfs01/user/xiaolinchen/miniconda3/envs/oc_lmdeploy/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 3126, in _call_one
return self.encode_plus(
File "/cpfs01/user/xiaolinchen/miniconda3/envs/oc_lmdeploy/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 3202, in encode_plus
return self._encode_plus(
File "/cpfs01/user/xiaolinchen/miniconda3/envs/oc_lmdeploy/lib/python3.10/site-packages/transformers/tokenization_utils.py", line 801, in _encode_plus
return self.prepare_for_model(
File "/cpfs01/user/xiaolinchen/miniconda3/envs/oc_lmdeploy/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 3698, in prepare_for_model
encoded_inputs = self.pad(
File "/cpfs01/user/xiaolinchen/miniconda3/envs/oc_lmdeploy/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 3500, in pad
encoded_inputs = self._pad(
TypeError: ChatGLM4Tokenizer._pad() got an unexpected keyword argument 'padding_side'
两种解决方案：一是删除padding_side观察会不会出错，二是可以修改tokenizer实现
我也出现了这样的问题，在tokenization_chatglm.py文件262行的_pad()方法中添加padding_side="left"，就可以运行了。