created windows_download_dataset.sh, deleted original changes in download_dataset.sh

This commit is contained in:
MengYue-MK2000
2025-06-19 17:52:24 +08:00
parent 18ff1a73a8
commit b1ac936d36
2 changed files with 35 additions and 37 deletions

View File

@@ -0,0 +1,35 @@
# Windows下载方式
# 使用PowerShell下载
# 暂时为当前PowerShell界面设置环境关闭Powershell环境自动消失
$env:HF_ENDPOINT = "https://hf-mirror.com"
# 将\path\to\your\dataset替换成想要下载dataset目录地址
$dataset_dir = "\path\to\your\dataset"
# 需要预先安装modelscope使用pip install modelscope安装
modelscope download --dataset ddzhu123/seq-monkey mobvoi_seq_monkey_general_open_corpus.jsonl.tar.bz2 --local_dir "$dataset_dir"
tar -xvf "$dataset_dir\mobvoi_seq_monkey_general_open_corpus.jsonl.tar.bz2" -C "$dataset_dir"
huggingface-cli download `
--repo-type dataset `
--resume-download `
BelleGroup/train_3.5M_CN `
--local-dir "$dataset_dir\BelleGroup"
# 使用CMD下载
# 暂时为当前CMD界面设置环境关闭CMD环境自动消失
set HF_ENDPOINT=https://hf-mirror.com
# 将\path\to\your\dataset替换成想要下载dataset目录地址
set dataset_dir=\path\to\your\dataset
modelscope download --dataset ddzhu123/seq-monkey mobvoi_seq_monkey_general_open_corpus.jsonl.tar.bz2 --local_dir %dataset_dir%
tar -xvf "%dataset_dir%\mobvoi_seq_monkey_general_open_corpus.jsonl.tar.bz2" -C "%dataset_dir%"
huggingface-cli download ^
--repo-type dataset ^
--resume-download ^
BelleGroup/train_3.5M_CN ^
--local-dir "%dataset_dir%\BelleGroup"