mkdir -p owt/txt cd owt/txt # wget https://huggingface.co/datasets/stanford-cs336/owt-sample/resolve/main/owt_train.txt.gz # wget https://huggingface.co/datasets/stanford-cs336/owt-sample/resolve/main/owt_valid.txt.gz # 如果你链接huggingface.co失败,可以尝试使用hf-mirror.com,具体操作如下: wget https://hf-mirror.com/datasets/stanford-cs336/owt-sample/resolve/main/owt_train.txt.gz wget https://hf-mirror.com/datasets/stanford-cs336/owt-sample/resolve/main/owt_valid.txt.gz # 解压 gunzip owt_train.txt.gz gunzip owt_valid.txt.gz mv owt_train.txt train.txt mv owt_valid.txt valid.txt