Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-5000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0040
11.1 GB
56,043 files
Updated about 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000125.jsonl.zst561 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000126.jsonl.zst435 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000127.jsonl.zst512 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000128.jsonl.zst489 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000129.jsonl.zst514 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000130.jsonl.zst612 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000131.jsonl.zst381 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000132.jsonl.zst529 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000133.jsonl.zst472 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000134.jsonl.zst729 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000135.jsonl.zst454 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000136.jsonl.zst550 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000137.jsonl.zst368 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000138.jsonl.zst481 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000139.jsonl.zst365 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000140.jsonl.zst515 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000141.jsonl.zst446 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000142.jsonl.zst427 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000143.jsonl.zst499 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000144.jsonl.zst465 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000145.jsonl.zst394 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000146.jsonl.zst485 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000147.jsonl.zst468 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000148.jsonl.zst429 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000149.jsonl.zst485 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000150.jsonl.zst431 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000151.jsonl.zst433 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000152.jsonl.zst459 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000153.jsonl.zst416 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000154.jsonl.zst579 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000155.jsonl.zst462 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000156.jsonl.zst569 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000157.jsonl.zst293 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000158.jsonl.zst227 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000159.jsonl.zst532 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000160.jsonl.zst494 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000161.jsonl.zst447 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000162.jsonl.zst502 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000163.jsonl.zst537 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000164.jsonl.zst488 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000165.jsonl.zst424 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000166.jsonl.zst624 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000167.jsonl.zst511 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000168.jsonl.zst356 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000169.jsonl.zst505 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000170.jsonl.zst465 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000171.jsonl.zst278 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000172.jsonl.zst441 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000173.jsonl.zst348 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000174.jsonl.zst385 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000175.jsonl.zst597 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000176.jsonl.zst437 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000177.jsonl.zst237 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000178.jsonl.zst335 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000179.jsonl.zst639 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000180.jsonl.zst465 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000181.jsonl.zst518 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000182.jsonl.zst418 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000183.jsonl.zst448 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000184.jsonl.zst484 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000185.jsonl.zst403 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000186.jsonl.zst493 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000187.jsonl.zst452 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000188.jsonl.zst463 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000189.jsonl.zst406 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000190.jsonl.zst528 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000191.jsonl.zst423 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000192.jsonl.zst545 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000193.jsonl.zst465 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000194.jsonl.zst420 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000195.jsonl.zst450 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000196.jsonl.zst640 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000197.jsonl.zst416 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000198.jsonl.zst479 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000199.jsonl.zst651 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000200.jsonl.zst476 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000201.jsonl.zst529 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000202.jsonl.zst352 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000203.jsonl.zst478 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000204.jsonl.zst577 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000205.jsonl.zst433 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000206.jsonl.zst444 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000207.jsonl.zst467 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000208.jsonl.zst536 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000209.jsonl.zst541 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000210.jsonl.zst456 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000211.jsonl.zst416 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000212.jsonl.zst533 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000213.jsonl.zst577 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000214.jsonl.zst491 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000215.jsonl.zst487 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000216.jsonl.zst441 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000217.jsonl.zst538 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000218.jsonl.zst598 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000219.jsonl.zst502 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000220.jsonl.zst385 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000221.jsonl.zst548 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000222.jsonl.zst546 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000223.jsonl.zst371 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0019__shard_00000224.jsonl.zst557 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors