Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0032
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001101.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001102.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001103.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001104.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001105.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001107.jsonl.zst1.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001109.jsonl.zst1.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001111.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001112.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001114.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001115.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001116.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001117.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001121.jsonl.zst1.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001122.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001123.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001124.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001126.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001127.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001132.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001133.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001135.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001137.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001138.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001139.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001140.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001141.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001143.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001145.jsonl.zst1.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001146.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001147.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001148.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001149.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001151.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001153.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001154.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001158.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001159.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001162.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001166.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001168.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001169.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001170.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001171.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001174.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001175.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001176.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001177.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001179.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001181.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001183.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001184.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001185.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001189.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001190.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001191.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001194.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001195.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001196.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001197.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001199.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001201.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001203.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001204.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001205.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001206.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001207.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001208.jsonl.zst1.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001209.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001215.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001216.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001218.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001220.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00001221.jsonl.zst728 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000000.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000001.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000002.jsonl.zst1.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000003.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000004.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000005.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000006.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000007.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000008.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000009.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000010.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000011.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000012.jsonl.zst1.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000013.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000014.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000015.jsonl.zst1.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000016.jsonl.zst1.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000017.jsonl.zst850 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000018.jsonl.zst625 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000019.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000020.jsonl.zst1.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000021.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000022.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000023.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000024.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000025.jsonl.zst925 kB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors