Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0039
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-0018__shard_00000094.jsonl.zst367 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000095.jsonl.zst722 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000096.jsonl.zst635 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000097.jsonl.zst515 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000098.jsonl.zst441 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000099.jsonl.zst539 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000100.jsonl.zst344 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000101.jsonl.zst407 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000102.jsonl.zst633 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000103.jsonl.zst223 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000104.jsonl.zst674 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000105.jsonl.zst490 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000106.jsonl.zst581 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000107.jsonl.zst492 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000108.jsonl.zst414 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000109.jsonl.zst594 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000110.jsonl.zst557 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000111.jsonl.zst446 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000112.jsonl.zst297 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000113.jsonl.zst546 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000114.jsonl.zst563 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000115.jsonl.zst607 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000116.jsonl.zst564 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000117.jsonl.zst394 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000118.jsonl.zst447 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000119.jsonl.zst449 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000120.jsonl.zst464 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000121.jsonl.zst329 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000122.jsonl.zst318 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000123.jsonl.zst592 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000124.jsonl.zst494 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000125.jsonl.zst662 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000126.jsonl.zst481 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000127.jsonl.zst407 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000128.jsonl.zst400 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000129.jsonl.zst629 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000130.jsonl.zst745 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000131.jsonl.zst501 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000132.jsonl.zst465 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000133.jsonl.zst404 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000134.jsonl.zst531 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000135.jsonl.zst776 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000136.jsonl.zst401 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000137.jsonl.zst654 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000138.jsonl.zst843 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000139.jsonl.zst679 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000140.jsonl.zst494 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000141.jsonl.zst461 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000142.jsonl.zst466 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000143.jsonl.zst684 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000144.jsonl.zst457 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000145.jsonl.zst791 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000146.jsonl.zst334 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000147.jsonl.zst624 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000148.jsonl.zst620 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000149.jsonl.zst335 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000150.jsonl.zst529 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000151.jsonl.zst518 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000152.jsonl.zst548 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000153.jsonl.zst501 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000154.jsonl.zst587 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000155.jsonl.zst438 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000156.jsonl.zst585 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000157.jsonl.zst496 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000158.jsonl.zst360 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000159.jsonl.zst397 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000160.jsonl.zst391 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000161.jsonl.zst409 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000162.jsonl.zst360 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000163.jsonl.zst402 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000164.jsonl.zst552 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000165.jsonl.zst594 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000166.jsonl.zst465 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000167.jsonl.zst754 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000168.jsonl.zst653 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000169.jsonl.zst324 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000170.jsonl.zst174 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000171.jsonl.zst654 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000172.jsonl.zst447 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000173.jsonl.zst369 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000174.jsonl.zst571 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000175.jsonl.zst480 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000176.jsonl.zst519 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000177.jsonl.zst404 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000178.jsonl.zst560 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000179.jsonl.zst381 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000180.jsonl.zst492 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000181.jsonl.zst414 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000182.jsonl.zst547 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000183.jsonl.zst482 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000184.jsonl.zst478 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000185.jsonl.zst340 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000186.jsonl.zst320 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000187.jsonl.zst513 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000188.jsonl.zst419 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000189.jsonl.zst417 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000190.jsonl.zst803 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000191.jsonl.zst408 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000192.jsonl.zst551 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000193.jsonl.zst739 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors