Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-50000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0046
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000333.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000334.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000335.jsonl.zst2.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000336.jsonl.zst2.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000337.jsonl.zst3.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000338.jsonl.zst3.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000339.jsonl.zst3.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000340.jsonl.zst2.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000341.jsonl.zst3.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000342.jsonl.zst3.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000343.jsonl.zst3.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000344.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000345.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000346.jsonl.zst2.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000347.jsonl.zst3.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000348.jsonl.zst3.18 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000349.jsonl.zst2.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000350.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000351.jsonl.zst2.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000352.jsonl.zst2.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000353.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000354.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000355.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000356.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000357.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000358.jsonl.zst2.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000359.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000360.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000361.jsonl.zst3.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000362.jsonl.zst2.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000363.jsonl.zst3.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000364.jsonl.zst3.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000365.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000366.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000367.jsonl.zst2.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000368.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000369.jsonl.zst2.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000370.jsonl.zst3.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000371.jsonl.zst3.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000372.jsonl.zst3.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000373.jsonl.zst2.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000374.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000375.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000376.jsonl.zst2.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000377.jsonl.zst2.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000378.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000379.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000380.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000381.jsonl.zst2.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000382.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000383.jsonl.zst3.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000384.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000385.jsonl.zst1.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000386.jsonl.zst3.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000387.jsonl.zst3.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000388.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000389.jsonl.zst3.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000390.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000391.jsonl.zst1.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000392.jsonl.zst3.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000393.jsonl.zst2.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000394.jsonl.zst3.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000395.jsonl.zst3.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000396.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000397.jsonl.zst3.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000398.jsonl.zst1.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000399.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000400.jsonl.zst2.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000401.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000402.jsonl.zst3.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000403.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000404.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000405.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000406.jsonl.zst2.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000407.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000408.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000409.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000410.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000411.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000412.jsonl.zst2.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000413.jsonl.zst2.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000414.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000415.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000416.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000417.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000418.jsonl.zst3.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000419.jsonl.zst2.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000420.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000421.jsonl.zst2.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000422.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000423.jsonl.zst2.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000424.jsonl.zst3.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000425.jsonl.zst2.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000426.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000427.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000428.jsonl.zst2.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000429.jsonl.zst2.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000430.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000431.jsonl.zst3.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0019__shard_00000432.jsonl.zst2.67 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors