Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-50000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0035
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000058.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000059.jsonl.zst1.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000060.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000061.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000062.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000063.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000064.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000065.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000066.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000067.jsonl.zst1.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000068.jsonl.zst1.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000069.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000070.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000071.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000072.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000073.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000074.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000075.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000076.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000077.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000078.jsonl.zst1.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000079.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000080.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000081.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000082.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000083.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000084.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000085.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000086.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000087.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000088.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000089.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000090.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000091.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000092.jsonl.zst1.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000093.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000094.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000095.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000096.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000097.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000098.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000099.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000100.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000101.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000102.jsonl.zst683 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000103.jsonl.zst655 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000104.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000105.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000106.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000107.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000108.jsonl.zst1.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000109.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000110.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000111.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000112.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000113.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000114.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000115.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000116.jsonl.zst1.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000117.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000118.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000119.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000120.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000121.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000122.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000123.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000124.jsonl.zst1.18 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000125.jsonl.zst1.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000126.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000127.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000128.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000129.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000130.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000131.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000132.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000133.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000134.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000135.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000136.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000137.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000138.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000139.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000140.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000141.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000142.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000143.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000144.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000145.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000146.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000147.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000148.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000149.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000150.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000151.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000152.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000153.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000154.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000155.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000156.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000157.jsonl.zst1.52 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors