大模型推理使用transformers 后端代码报错

1 问题

执行glm-4 Python trans-cli-demo.py报错

解决方案1：升级transformer

pip transformers==4.43.0

解决方案2：重新安装与系统匹配的torch torchvision torchaudio

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

以下为报错信息：

(LLM) E:\GLM-4\GLM-4-main\basic_demo>python trans_cli_demo.py
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████| 10/10 [00:00<00:00, 18.18it/s]
Welcome to the GLM-4-9B CLI chat. Type your messages below.

You: hell
GLM-4:Exception in thread Thread-2 (generate):

Traceback (most recent call last):
  File "E:\anaconda3\envs\LLM\Lib\threading.py", line 1045, in _bootstrap_inner
    self.ru