cooper
cooper
> > AttributeError: 'NoneType' object has no attribute 'tokenize' > > 求救 > > 把bert_pretrain目录下的bert-base-chinese-vocab.txt 改名为 vocab.txt 就好了 谢谢
Me too, maybe openAI has already ban it ?
i have the same error,but my cuda version is 11.8 ``` ds_report [2024-01-10 20:06:22,681] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect) -------------------------------------------------- DeepSpeed C++/CUDA extension op report -------------------------------------------------- NOTE:...
> > 是局域网分享，不管端口号设定成什么样，都是无法生成分享的，ip:port无法分享的
same, torch2.2.0+cuda11.8: undefined symbol: _ZN2at4_ops9_pad_enum4callERKNS_6TensorEN3c108ArrayRefINS5_6SymIntEEElNS5_8optionalIdEE
我就是仅仅运行一下本地模型，为什么还报这个错误呢： 运行命令: ``` from vllm import LLM, SamplingParams llm = LLM(model="/data/share/rwq/Qwen-7B-Chat", revision="v1.1.8", trust_remote_code=True) ``` 报错: ``` 2024-01-03 17:58:31,460 - modelscope - ERROR - Authentication token does not exist, failed to...
> @ArlanCooper 我解决了，只要`unset VLLM_USE_MODELSCOPE`就行 就是不用modelscope吗？只使用transformers吧？