Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-100000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-100000-docs / worker_0068
187 GB
58,264 files
Updated 25 days ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000125.jsonl.zst3.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000126.jsonl.zst3.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000127.jsonl.zst4.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000128.jsonl.zst3.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000129.jsonl.zst4.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000130.jsonl.zst3.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000131.jsonl.zst3.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000132.jsonl.zst4.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000133.jsonl.zst3.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000134.jsonl.zst3.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000135.jsonl.zst3.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000136.jsonl.zst3.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000137.jsonl.zst3.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000138.jsonl.zst3.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000139.jsonl.zst3.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000140.jsonl.zst3.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000141.jsonl.zst3.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000142.jsonl.zst3.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000143.jsonl.zst3.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000144.jsonl.zst3.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000145.jsonl.zst3.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000146.jsonl.zst3.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000147.jsonl.zst3.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000148.jsonl.zst3.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000149.jsonl.zst3.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000150.jsonl.zst3.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000151.jsonl.zst3.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000152.jsonl.zst3.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000153.jsonl.zst4.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000154.jsonl.zst3.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000155.jsonl.zst3.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000156.jsonl.zst3.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000157.jsonl.zst3.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000158.jsonl.zst3.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000159.jsonl.zst3.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000160.jsonl.zst3.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000161.jsonl.zst3.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000162.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000163.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000164.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000166.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000167.jsonl.zst4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000168.jsonl.zst3.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000169.jsonl.zst3.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000170.jsonl.zst3.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000171.jsonl.zst3.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000172.jsonl.zst3.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000173.jsonl.zst3.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000174.jsonl.zst3.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000175.jsonl.zst3.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000176.jsonl.zst4.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000177.jsonl.zst3.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000178.jsonl.zst3.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000179.jsonl.zst3.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000180.jsonl.zst4.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000181.jsonl.zst3.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000182.jsonl.zst3.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000183.jsonl.zst3.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000184.jsonl.zst3.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000185.jsonl.zst3.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000186.jsonl.zst3.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000187.jsonl.zst3.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000188.jsonl.zst3.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000189.jsonl.zst3.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000190.jsonl.zst3.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000191.jsonl.zst3.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000192.jsonl.zst3.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000193.jsonl.zst3.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000194.jsonl.zst3.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000195.jsonl.zst3.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000196.jsonl.zst3.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000197.jsonl.zst3.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000198.jsonl.zst3.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000199.jsonl.zst3.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000200.jsonl.zst3.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000201.jsonl.zst3.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000202.jsonl.zst3.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000203.jsonl.zst3.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000204.jsonl.zst3.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000205.jsonl.zst3.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000206.jsonl.zst3.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000207.jsonl.zst3.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000208.jsonl.zst3.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000209.jsonl.zst3.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000210.jsonl.zst3.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000211.jsonl.zst3.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000212.jsonl.zst3.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000213.jsonl.zst3.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000214.jsonl.zst3.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000215.jsonl.zst3.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000216.jsonl.zst3.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000217.jsonl.zst3.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000218.jsonl.zst3.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000219.jsonl.zst3.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000220.jsonl.zst3.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000221.jsonl.zst3.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000222.jsonl.zst3.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000223.jsonl.zst3.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000224.jsonl.zst3.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000225.jsonl.zst3.88 MB
xet
Total size
187 GB
Files
58,264
Last updated
Mar 25
Pre-warmed CDN
US EU US EU

Contributors