Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-1000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-1000-docs / worker_0040
2.37 GB
46,808 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000008.jsonl.zst25.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000009.jsonl.zst21.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000010.jsonl.zst12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000011.jsonl.zst31.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000012.jsonl.zst20.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000013.jsonl.zst9.75 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000014.jsonl.zst29.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000015.jsonl.zst42.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000016.jsonl.zst56.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000017.jsonl.zst17.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000018.jsonl.zst20.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000019.jsonl.zst30.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000020.jsonl.zst51.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000021.jsonl.zst44.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000022.jsonl.zst31.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000023.jsonl.zst17.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000024.jsonl.zst24.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000025.jsonl.zst21.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000026.jsonl.zst20.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000027.jsonl.zst37.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000028.jsonl.zst19.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000029.jsonl.zst23.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000030.jsonl.zst32.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000031.jsonl.zst27 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000032.jsonl.zst48.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000033.jsonl.zst18 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000034.jsonl.zst32.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000035.jsonl.zst79.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000036.jsonl.zst13.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000037.jsonl.zst122 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000038.jsonl.zst46.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000039.jsonl.zst47.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000040.jsonl.zst30.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000041.jsonl.zst24 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000042.jsonl.zst31.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000043.jsonl.zst20.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000044.jsonl.zst16.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000045.jsonl.zst32.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000046.jsonl.zst30.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000047.jsonl.zst15.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000048.jsonl.zst35.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000049.jsonl.zst42.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000050.jsonl.zst30.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000051.jsonl.zst32 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000052.jsonl.zst39.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000053.jsonl.zst25.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000054.jsonl.zst20 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000055.jsonl.zst4.45 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000056.jsonl.zst11.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000057.jsonl.zst15.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000058.jsonl.zst95.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000059.jsonl.zst11.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000060.jsonl.zst19.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000061.jsonl.zst48.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000062.jsonl.zst28.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000063.jsonl.zst32.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000064.jsonl.zst20.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000065.jsonl.zst25.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000066.jsonl.zst8.69 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000067.jsonl.zst36.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000068.jsonl.zst14.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000069.jsonl.zst23.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000070.jsonl.zst39 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000071.jsonl.zst19.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000072.jsonl.zst87.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000073.jsonl.zst26 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000074.jsonl.zst56.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000075.jsonl.zst76.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000076.jsonl.zst45.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000077.jsonl.zst46.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000078.jsonl.zst38.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000079.jsonl.zst35.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000080.jsonl.zst33 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000081.jsonl.zst37.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000082.jsonl.zst20.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000083.jsonl.zst29.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000084.jsonl.zst28.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000085.jsonl.zst53.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000086.jsonl.zst31.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000087.jsonl.zst40.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000088.jsonl.zst7.12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000089.jsonl.zst20.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000090.jsonl.zst19.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000091.jsonl.zst32.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000092.jsonl.zst32 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000093.jsonl.zst55.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000094.jsonl.zst47 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000095.jsonl.zst39.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000096.jsonl.zst32.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000097.jsonl.zst29.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000098.jsonl.zst41.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000099.jsonl.zst42.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000100.jsonl.zst13.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000101.jsonl.zst15.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000102.jsonl.zst31.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000103.jsonl.zst24.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000104.jsonl.zst33.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000105.jsonl.zst21.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000106.jsonl.zst79.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000107.jsonl.zst24.7 kB
xet
Total size
2.37 GB
Files
46,808
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors