Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0043
11.1 GB
56,043 files
Updated about 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000003.jsonl.zst387 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000008.jsonl.zst360 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000013.jsonl.zst330 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000016.jsonl.zst374 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000023.jsonl.zst335 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000024.jsonl.zst299 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000030.jsonl.zst415 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000034.jsonl.zst285 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000035.jsonl.zst302 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000039.jsonl.zst275 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000043.jsonl.zst405 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000044.jsonl.zst379 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000055.jsonl.zst423 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000060.jsonl.zst356 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000064.jsonl.zst417 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000076.jsonl.zst444 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000084.jsonl.zst281 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000086.jsonl.zst348 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000090.jsonl.zst301 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000092.jsonl.zst243 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000093.jsonl.zst339 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000095.jsonl.zst350 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000099.jsonl.zst318 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000101.jsonl.zst366 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000103.jsonl.zst433 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000105.jsonl.zst385 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000109.jsonl.zst267 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000113.jsonl.zst345 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000115.jsonl.zst337 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000116.jsonl.zst383 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000117.jsonl.zst308 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000121.jsonl.zst319 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000130.jsonl.zst399 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000132.jsonl.zst379 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000135.jsonl.zst336 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000139.jsonl.zst315 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000143.jsonl.zst285 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000144.jsonl.zst309 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000147.jsonl.zst170 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000150.jsonl.zst123 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000152.jsonl.zst412 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000158.jsonl.zst486 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000161.jsonl.zst352 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000167.jsonl.zst314 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000172.jsonl.zst448 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000174.jsonl.zst358 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000175.jsonl.zst363 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000176.jsonl.zst216 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000179.jsonl.zst176 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000180.jsonl.zst135 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000184.jsonl.zst352 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000186.jsonl.zst446 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000188.jsonl.zst395 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000191.jsonl.zst396 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000195.jsonl.zst481 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000198.jsonl.zst322 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000200.jsonl.zst320 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000211.jsonl.zst341 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000212.jsonl.zst400 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000213.jsonl.zst367 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000217.jsonl.zst352 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000220.jsonl.zst283 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000227.jsonl.zst283 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000233.jsonl.zst369 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000238.jsonl.zst321 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000242.jsonl.zst340 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000243.jsonl.zst483 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000254.jsonl.zst376 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000255.jsonl.zst374 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000261.jsonl.zst398 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000262.jsonl.zst445 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000264.jsonl.zst271 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000265.jsonl.zst317 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0017__shard_00000269.jsonl.zst322 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000000.jsonl.zst396 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000001.jsonl.zst396 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000002.jsonl.zst306 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000003.jsonl.zst263 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000004.jsonl.zst291 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000005.jsonl.zst371 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000006.jsonl.zst311 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000007.jsonl.zst376 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000008.jsonl.zst280 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000009.jsonl.zst285 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000010.jsonl.zst400 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000011.jsonl.zst335 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000012.jsonl.zst286 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000013.jsonl.zst369 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000014.jsonl.zst271 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000015.jsonl.zst260 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000016.jsonl.zst362 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000017.jsonl.zst423 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000018.jsonl.zst350 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000019.jsonl.zst347 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000020.jsonl.zst346 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000021.jsonl.zst440 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000022.jsonl.zst363 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000023.jsonl.zst291 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000024.jsonl.zst466 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0018__shard_00000025.jsonl.zst489 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors