Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-1000-docs / worker_0038
2.37 GB
46,808 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000015.jsonl.zst23.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000016.jsonl.zst28.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000017.jsonl.zst29.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000018.jsonl.zst21.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000022.jsonl.zst34.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000023.jsonl.zst33.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000025.jsonl.zst38.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000026.jsonl.zst13.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000027.jsonl.zst36.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000028.jsonl.zst76.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000029.jsonl.zst22.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000033.jsonl.zst30.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000035.jsonl.zst35.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000037.jsonl.zst27 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000038.jsonl.zst34.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000040.jsonl.zst34.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000043.jsonl.zst34.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000044.jsonl.zst46.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000046.jsonl.zst29 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000047.jsonl.zst31.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000048.jsonl.zst58.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000052.jsonl.zst65.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000053.jsonl.zst27.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000057.jsonl.zst52.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000058.jsonl.zst32.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000062.jsonl.zst31.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000063.jsonl.zst23.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000065.jsonl.zst38.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000068.jsonl.zst51.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000070.jsonl.zst57 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000071.jsonl.zst21.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000073.jsonl.zst26 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000075.jsonl.zst49.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000077.jsonl.zst13 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000078.jsonl.zst37.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000079.jsonl.zst17.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000080.jsonl.zst21.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000081.jsonl.zst51.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000082.jsonl.zst38.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000086.jsonl.zst18.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000087.jsonl.zst19.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000090.jsonl.zst47.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000091.jsonl.zst36.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000093.jsonl.zst31.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000094.jsonl.zst23.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000098.jsonl.zst25.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000103.jsonl.zst34.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000104.jsonl.zst36.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000105.jsonl.zst20.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000106.jsonl.zst35.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000107.jsonl.zst19.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000108.jsonl.zst22.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000109.jsonl.zst21.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000110.jsonl.zst13.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000113.jsonl.zst47.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000114.jsonl.zst32.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000115.jsonl.zst22.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000116.jsonl.zst59.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000118.jsonl.zst25.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000119.jsonl.zst55.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000120.jsonl.zst21.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000121.jsonl.zst28 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000124.jsonl.zst19 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000125.jsonl.zst39.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000126.jsonl.zst28.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000128.jsonl.zst21.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000129.jsonl.zst35.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000130.jsonl.zst18.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000131.jsonl.zst22 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000132.jsonl.zst38.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000133.jsonl.zst26.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000134.jsonl.zst72 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000135.jsonl.zst22.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000136.jsonl.zst46.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000138.jsonl.zst19.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000142.jsonl.zst92.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000144.jsonl.zst67.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000148.jsonl.zst52.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000149.jsonl.zst16 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000151.jsonl.zst33.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000153.jsonl.zst36.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000154.jsonl.zst22.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000155.jsonl.zst21 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000156.jsonl.zst17 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000157.jsonl.zst27.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000159.jsonl.zst28.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000161.jsonl.zst24.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000162.jsonl.zst30.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000163.jsonl.zst18.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000164.jsonl.zst12.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000165.jsonl.zst88.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000167.jsonl.zst35.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000171.jsonl.zst63.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000173.jsonl.zst52.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000174.jsonl.zst59.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000175.jsonl.zst29.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000177.jsonl.zst52.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000178.jsonl.zst25.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000181.jsonl.zst55.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000182.jsonl.zst28.2 kB
xet
Total size
2.37 GB
Files
46,808
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors