Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0044
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000276.jsonl.zst3.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000277.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000278.jsonl.zst3.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000279.jsonl.zst2.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000280.jsonl.zst3.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000281.jsonl.zst3.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000282.jsonl.zst3.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000283.jsonl.zst3.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000284.jsonl.zst3.24 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000285.jsonl.zst3.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000286.jsonl.zst3.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000287.jsonl.zst3.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000288.jsonl.zst4.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000289.jsonl.zst3.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000290.jsonl.zst3.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000291.jsonl.zst3.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000292.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000293.jsonl.zst3.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000294.jsonl.zst3.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000295.jsonl.zst3.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000296.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000297.jsonl.zst3.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000298.jsonl.zst3.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000299.jsonl.zst3.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000300.jsonl.zst3.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000301.jsonl.zst3.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000302.jsonl.zst3.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000303.jsonl.zst3.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000304.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000305.jsonl.zst3.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000306.jsonl.zst3.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000307.jsonl.zst3.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000308.jsonl.zst3.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000309.jsonl.zst3.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000310.jsonl.zst3.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000311.jsonl.zst3.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000312.jsonl.zst3.24 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000313.jsonl.zst3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000314.jsonl.zst2.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000315.jsonl.zst1.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000316.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000317.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000318.jsonl.zst3.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000319.jsonl.zst3.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000320.jsonl.zst3.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000321.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000322.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000323.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000324.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000325.jsonl.zst3.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000326.jsonl.zst3.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000327.jsonl.zst3.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000328.jsonl.zst3.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000329.jsonl.zst3.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000330.jsonl.zst3.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000331.jsonl.zst3.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000332.jsonl.zst2.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000333.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000334.jsonl.zst3.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000335.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000336.jsonl.zst3.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000337.jsonl.zst4.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000338.jsonl.zst3.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000339.jsonl.zst3.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000340.jsonl.zst3.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000341.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000342.jsonl.zst3.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000343.jsonl.zst3.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000344.jsonl.zst3.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000345.jsonl.zst3.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000346.jsonl.zst3.18 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000347.jsonl.zst3.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000348.jsonl.zst3.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000349.jsonl.zst3.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000350.jsonl.zst3.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000351.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000352.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000353.jsonl.zst3.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000354.jsonl.zst3.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000355.jsonl.zst3.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000356.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000357.jsonl.zst4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000358.jsonl.zst2.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000359.jsonl.zst2.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000360.jsonl.zst3.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000361.jsonl.zst3.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000362.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000363.jsonl.zst3.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000364.jsonl.zst3.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000365.jsonl.zst2.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000366.jsonl.zst3.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000367.jsonl.zst2.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000368.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000369.jsonl.zst4.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000370.jsonl.zst4.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000371.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000372.jsonl.zst3.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000373.jsonl.zst3.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000374.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-literature-0018__shard_00000375.jsonl.zst3.21 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors