Open Cyydz opened 7 months ago
同上
我也是,看显存占用量,似乎没有正确加载模型~但不知道如何debug
看一下有没有这样的error:”ImportError: InternLM2Converter requires the protobuf library but it was not found in your environment. Checkout the instructions on the installation page of its repo: https://github.com/protocolbuffers/protobuf/tree/master/python#installation and follow the ones that match your environment. Please note that you may need to restart your runtime after installation.“ 有的话pip install protobuf就可以了。
请问这个问题怎么解决?
运行代码是教程里的demo代码:
python run.py --datasets ceval_gen --hf-path /share/temp/model_repos/internlm-chat-7b/ --tokenizer-path /share/temp/model_repos/internlm-chat-7b/ --tokenizer-kwargs padding_side='left' truncation='left' trust_remote_code=True --model-kwargs trust_remote_code=True device_map='auto' --max-seq-len 2048 --max-out-len 16 --batch-size 4 --num-gpus 1 --debug
我的batch size设了1 2 4,都试过了,debug的过程一直有error。 报错图片如下