[BUG/Help] <title>在colab运行时 实例代码是报错

ValueError                                Traceback (most recent call last)
[<ipython-input-4-d0416a7bae87>](https://localhost:8080/#) in <cell line: 0>()
----> 1 response, history = model.chat(tokenizer, "你好", history=[])
      2 print(response)
      3 
      4 
      5 response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)

5 frames
[~/.cache/huggingface/modules/transformers_modules/THUDM/chatglm2-6b-int4/a954550736dda16d022a7019b9ffecd753aa1b84/modeling_chatglm.py](https://localhost:8080/#) in _update_model_kwargs_for_generation(self, outputs, model_kwargs, is_encoder_decoder)
    868     ) -> Dict[str, Any]:
    869         # update past_key_values
--> 870         cache_name, cache = self._extract_past_from_model_output(outputs)
    871         model_kwargs[cache_name] = cache
    872 

ValueError: too many values to unpack (expected 2)

!pip install protobuf
!pip install transformers==4.30.2
!pip install cpm_kernels
!pip install torch>=2.0
!pip install gradio
!pip install mdtex2html
!pip install sentencepiece
!pip install accelerate
!pip install sse-starlette
!pip install streamlit>=1.24.0

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True).half().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)

- OS: colab
- Python: 3.11
- Transformers: 4.30.2
- PyTorch: 2.6.0+cu124
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) : True