[Question] 推理调用AutoModelForCausalLM时报错没有安装configuration_baichuan怎么办

[WEI-6]

Required prerequisites

• [X] I have read the documentation https://github.com/baichuan-inc/baichuan-7B/blob/HEAD/README.md.
• [X] I have searched the Issue Tracker and Discussions that this hasn't already been reported. (+1 or comment there if it has.)
• [ ] Consider asking first in a Discussion.

Questions

原代码： from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/baichuan-7B", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("baichuan-inc/baichuan-7B", device_map="auto", trust_remote_code=True) inputs = tokenizer('登鹳雀楼->王之涣\n夜雨寄北->', return_tensors='pt') inputs = inputs.to('cuda:0') pred = model.generate(**inputs, max_new_tokens=64,repetition_penalty=1.1) print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True)) 报错图如下： 提示去pip install configuration_baichuan，但是各大网站都找不到这个package的版本

Checklist

• [X] I have provided all relevant and necessary information above.
• [X] I have chosen a suitable title for this issue.

[70557dzqc]

在项目的models文件夹下

[BigBen7]

请问我下载或启动模型一致报 ConnectionResetError: [Errno 104] Connection reset by peer 代码和你的是一样的，你有碰到吗

[WEI-6]

在项目的models文件夹下

可我调试是能进入到configuration_baichuan.py去运行，这个模块会被自动下载到/users/.cache/huggingface/.../文件夹里，但运行到78行**kwargs的时候仍然报找不到configuration_baichuan这个错 是因为自动下载的文件configuration_baichuan.py的问题吗？

[WEI-6]

Connection reset by peer

没有呢

[EircYangQiXin]

使用model space 下载之后启动模型也会报这个错

[EircYangQiXin]

该怎么解决呢