Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-10000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-10000-docs / worker_0033
21.6 GB
57,845 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000281.jsonl.zst136 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000282.jsonl.zst95.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000283.jsonl.zst346 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000284.jsonl.zst257 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000285.jsonl.zst316 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000286.jsonl.zst344 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000287.jsonl.zst330 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000288.jsonl.zst317 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000289.jsonl.zst242 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000290.jsonl.zst378 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000291.jsonl.zst404 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000292.jsonl.zst349 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000293.jsonl.zst193 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000294.jsonl.zst196 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000295.jsonl.zst302 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000296.jsonl.zst305 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000297.jsonl.zst277 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000298.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000299.jsonl.zst267 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000300.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000301.jsonl.zst195 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000302.jsonl.zst333 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000303.jsonl.zst362 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000304.jsonl.zst286 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000305.jsonl.zst292 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000306.jsonl.zst352 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000307.jsonl.zst396 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000308.jsonl.zst319 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000309.jsonl.zst276 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000310.jsonl.zst226 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000311.jsonl.zst241 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000312.jsonl.zst315 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000313.jsonl.zst373 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000314.jsonl.zst351 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000315.jsonl.zst318 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000316.jsonl.zst234 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000317.jsonl.zst327 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000318.jsonl.zst364 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000319.jsonl.zst446 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000320.jsonl.zst386 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000321.jsonl.zst263 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000322.jsonl.zst320 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000323.jsonl.zst248 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000324.jsonl.zst289 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000325.jsonl.zst324 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000326.jsonl.zst254 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000327.jsonl.zst306 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000328.jsonl.zst234 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000329.jsonl.zst257 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000330.jsonl.zst432 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000331.jsonl.zst369 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000332.jsonl.zst259 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000333.jsonl.zst274 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000334.jsonl.zst370 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000335.jsonl.zst303 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000336.jsonl.zst286 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000337.jsonl.zst290 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000338.jsonl.zst283 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000339.jsonl.zst358 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000340.jsonl.zst332 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000341.jsonl.zst338 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000342.jsonl.zst401 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000343.jsonl.zst231 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000344.jsonl.zst317 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000345.jsonl.zst354 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000346.jsonl.zst282 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000347.jsonl.zst193 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000348.jsonl.zst318 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000349.jsonl.zst324 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000350.jsonl.zst526 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000351.jsonl.zst289 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000352.jsonl.zst391 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000353.jsonl.zst441 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000354.jsonl.zst508 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000355.jsonl.zst376 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000356.jsonl.zst381 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000357.jsonl.zst392 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000358.jsonl.zst285 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000359.jsonl.zst344 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000360.jsonl.zst326 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000361.jsonl.zst356 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000362.jsonl.zst316 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000363.jsonl.zst342 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000364.jsonl.zst242 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000365.jsonl.zst327 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000366.jsonl.zst294 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000367.jsonl.zst386 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000368.jsonl.zst327 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000369.jsonl.zst340 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000370.jsonl.zst300 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000371.jsonl.zst266 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000372.jsonl.zst219 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000373.jsonl.zst324 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000374.jsonl.zst288 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000375.jsonl.zst368 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000376.jsonl.zst234 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000377.jsonl.zst374 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000378.jsonl.zst489 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000379.jsonl.zst317 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000380.jsonl.zst322 kB
xet
Total size
21.6 GB
Files
57,845
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors