Open HaomingX opened 7 months ago
基模型推理,任何问题都会在回答问题之后输出训练数据 温度低时输出完数据还会一直重复某些句子
No response
response, _history = model.chat(tokenizer, request, history=history, max_length= 512, num_beams=1, do_sample=True, top_p=0.8, temperature=0.1)
- OS:Ubuntu 20.04 - Python:3.10 - Transformers:4.33.2 - PyTorch: - CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) :True
Is there an existing issue for this?
Current Behavior
基模型推理,任何问题都会在回答问题之后输出训练数据
温度低时输出完数据还会一直重复某些句子
![image](https://github.com/THUDM/ChatGLM2-6B/assets/92592276/eda680ef-33ad-439c-9721-11bab42412d6)
Expected Behavior
No response
Steps To Reproduce
response, _history = model.chat(tokenizer, request, history=history, max_length= 512, num_beams=1, do_sample=True, top_p=0.8, temperature=0.1)
Environment
Anything else?
No response