[BUG/Help] <title>

[jiangweiatgithub]

Is there an existing issue for this?

• [X] I have searched the existing issues

Current Behavior

python test.py Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision. Traceback (most recent call last): File "test.py", line 2, in tokenizer = AutoTokenizer.from_pretrained(".\THUDM\chatglm2-6b", trust_remote_code=True) File "C:\Users\polyt.conda\envs\ChatGLM2-6B\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 679, in from_pretrained return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, *kwargs) File "C:\Users\polyt.conda\envs\ChatGLM2-6B\lib\site-packages\transformers\tokenization_utils_base.py", line 1804, in from_pretrained return cls._from_pretrained( File "C:\Users\polyt.conda\envs\ChatGLM2-6B\lib\site-packages\transformers\tokenization_utils_base.py", line 1958, in _from_pretrained tokenizer = cls(init_inputs, **init_kwargs) File "C:\Users\polyt/.cache\huggingface\modules\transformers_modules\chatglm2-6b\tokenization_chatglm.py", line 73, in init self.tokenizer = SPTokenizer(vocab_file) File "C:\Users\polyt/.cache\huggingface\modules\transformers_modules\chatglm2-6b\tokenization_chatglm.py", line 14, in init self.sp_model = SentencePieceProcessor(model_file=model_path) File "C:\Users\polyt.conda\envs\ChatGLM2-6B\lib\site-packages\sentencepiece__init.py", line 447, in Init self.Load(model_file=model_file, model_proto=model_proto) File "C:\Users\polyt.conda\envs\ChatGLM2-6B\lib\site-packages\sentencepiece__init__.py", line 905, in Load return self.LoadFromFile(model_file) File "C:\Users\polyt.conda\envs\ChatGLM2-6B\lib\site-packages\sentencepiece\init__.py", line 310, in LoadFromFile return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) RuntimeError: Internal: D:\a\sentencepiece\sentencepiece\src\sentencepiece_processor.cc(1102) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

Expected Behavior

No response

Steps To Reproduce

On Windows 11, run this script: from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained(".\THUDM\chatglm2-6b", trust_remote_code=True) model = AutoModel.from_pretrained(".\THUDM\chatglm2-6b", trust_remote_code=True, device='cuda') model = model.eval() response, history = model.chat(tokenizer, "你好", history=[]) print(response) response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history) print(response)

Environment

- OS: Windows 11
- Python: 3.8.16
- Transformers: 4.27.1
- PyTorch: 2.0.1
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) : False

Anything else?

"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.5\bin\nvcc.exe" --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2021 NVIDIA Corporation Built on Mon_Sep_13_20:11:50_Pacific_Daylight_Time_2021 Cuda compilation tools, release 11.5, V11.5.50 Build cuda_11.5.r11.5/compiler.30411180_0

[jiangweiatgithub]

Actually, this is an issue for ChatGLM2-6B

[jiangweiatgithub]

This issue solved by the following: https://huggingface.co/anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g/discussions/27