从Huggingface下载数据集时添加正则表达式
from huggingface_hub import snapshot_download
snapshot_download(repo_id='bigcode/starcoderdata', allow_patterns='java/*', repo_type="dataset", cache_dir='/mnt/petrelfs/chenjingzhou/cjz/opendatalab/cjz/starcoderdata')
from huggingface_hub import snapshot_download
snapshot_download(repo_id='bigcode/starcoderdata', allow_patterns='java/*', repo_type="dataset", cache_dir='/mnt/petrelfs/chenjingzhou/cjz/opendatalab/cjz/starcoderdata')