Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0068
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000120.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000121.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000122.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000123.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000124.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000125.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000126.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000127.jsonl.zst2.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000128.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000129.jsonl.zst1.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000130.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000131.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000132.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000133.jsonl.zst1.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000134.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000135.jsonl.zst2.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000136.jsonl.zst1.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000137.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000138.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000139.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000140.jsonl.zst1.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000141.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000142.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000143.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000144.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000145.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000146.jsonl.zst1.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000147.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000148.jsonl.zst2.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000149.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000150.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000151.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000152.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000153.jsonl.zst2.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000154.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000155.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000156.jsonl.zst2.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000157.jsonl.zst2.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000158.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000159.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000160.jsonl.zst1.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000161.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000162.jsonl.zst1.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000163.jsonl.zst827 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000164.jsonl.zst833 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000166.jsonl.zst835 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000167.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000168.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000169.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000170.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000171.jsonl.zst2.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000172.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000173.jsonl.zst1.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000174.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000175.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000176.jsonl.zst2.18 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000177.jsonl.zst1.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000178.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000179.jsonl.zst2.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000180.jsonl.zst2.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000181.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000182.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000183.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000184.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000185.jsonl.zst2.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000186.jsonl.zst2.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000187.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000188.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000189.jsonl.zst2.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000190.jsonl.zst1.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000191.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000192.jsonl.zst2.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000193.jsonl.zst2.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000194.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000195.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000196.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000197.jsonl.zst2.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000198.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000199.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000200.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000201.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000202.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000203.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000204.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000205.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000206.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000207.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000208.jsonl.zst1.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000209.jsonl.zst2.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000210.jsonl.zst1.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000211.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000212.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000213.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000214.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000215.jsonl.zst1.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000216.jsonl.zst2.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000217.jsonl.zst1.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000218.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000219.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000220.jsonl.zst2.07 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors