Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-5000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0037
11.1 GB
56,043 files
Updated about 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000338.jsonl.zst172 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000339.jsonl.zst192 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000340.jsonl.zst152 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000341.jsonl.zst198 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000342.jsonl.zst163 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000343.jsonl.zst170 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000344.jsonl.zst197 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000345.jsonl.zst193 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000346.jsonl.zst194 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000347.jsonl.zst225 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000348.jsonl.zst128 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000349.jsonl.zst123 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000350.jsonl.zst143 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000351.jsonl.zst157 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000352.jsonl.zst247 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000353.jsonl.zst291 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000354.jsonl.zst156 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000355.jsonl.zst168 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000356.jsonl.zst113 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000357.jsonl.zst134 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000358.jsonl.zst156 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000359.jsonl.zst168 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000360.jsonl.zst180 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000361.jsonl.zst250 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000362.jsonl.zst226 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000363.jsonl.zst98.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000364.jsonl.zst107 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000365.jsonl.zst165 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000366.jsonl.zst44.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000367.jsonl.zst39.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000368.jsonl.zst339 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000369.jsonl.zst200 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000370.jsonl.zst107 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000371.jsonl.zst141 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000372.jsonl.zst102 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000373.jsonl.zst178 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000374.jsonl.zst191 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000375.jsonl.zst215 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000376.jsonl.zst157 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000377.jsonl.zst139 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000378.jsonl.zst158 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000379.jsonl.zst242 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000380.jsonl.zst128 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000381.jsonl.zst144 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000382.jsonl.zst143 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000383.jsonl.zst172 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000384.jsonl.zst173 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000385.jsonl.zst198 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000386.jsonl.zst103 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000387.jsonl.zst188 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000388.jsonl.zst118 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000389.jsonl.zst95.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000390.jsonl.zst146 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000391.jsonl.zst184 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000392.jsonl.zst168 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000393.jsonl.zst133 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000394.jsonl.zst136 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000395.jsonl.zst173 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000396.jsonl.zst182 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000397.jsonl.zst144 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000398.jsonl.zst184 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000399.jsonl.zst137 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000400.jsonl.zst126 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000401.jsonl.zst153 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000402.jsonl.zst132 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000403.jsonl.zst125 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000404.jsonl.zst168 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000405.jsonl.zst168 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000406.jsonl.zst198 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000407.jsonl.zst233 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000408.jsonl.zst136 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000409.jsonl.zst144 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000410.jsonl.zst161 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000411.jsonl.zst143 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000412.jsonl.zst209 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000413.jsonl.zst186 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000414.jsonl.zst214 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000415.jsonl.zst114 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000416.jsonl.zst145 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000417.jsonl.zst132 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000418.jsonl.zst115 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000419.jsonl.zst196 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000420.jsonl.zst133 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000421.jsonl.zst211 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000422.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000423.jsonl.zst133 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000424.jsonl.zst178 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000425.jsonl.zst191 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000426.jsonl.zst168 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000427.jsonl.zst169 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000428.jsonl.zst157 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000429.jsonl.zst283 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000430.jsonl.zst178 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000431.jsonl.zst159 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000432.jsonl.zst84 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000433.jsonl.zst126 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000434.jsonl.zst123 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000435.jsonl.zst221 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000436.jsonl.zst128 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000437.jsonl.zst152 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors