Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0079
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000843.jsonl.zst2.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000844.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000845.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000846.jsonl.zst2.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000847.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000848.jsonl.zst2.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000849.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000850.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000851.jsonl.zst2.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000852.jsonl.zst2.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000853.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000854.jsonl.zst2.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000855.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000856.jsonl.zst2.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000857.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000858.jsonl.zst2.18 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000859.jsonl.zst2.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000860.jsonl.zst2.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000861.jsonl.zst2.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000862.jsonl.zst2.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000863.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000864.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000865.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000866.jsonl.zst2.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000867.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000868.jsonl.zst2.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000869.jsonl.zst2.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000870.jsonl.zst2.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000871.jsonl.zst2.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000872.jsonl.zst2.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000873.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-sports_and_fitness-0019__shard_00000874.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0016__shard_00000001.jsonl.zst4.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0016__shard_00000063.jsonl.zst3.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0016__shard_00000093.jsonl.zst3.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0016__shard_00000106.jsonl.zst3.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0016__shard_00000136.jsonl.zst3.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0016__shard_00000260.jsonl.zst3.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0016__shard_00000360.jsonl.zst3.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000012.jsonl.zst3.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000029.jsonl.zst3.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000032.jsonl.zst3.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000035.jsonl.zst3.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000046.jsonl.zst2.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000049.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000051.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000063.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000072.jsonl.zst3.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000084.jsonl.zst3.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000151.jsonl.zst3.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000178.jsonl.zst3.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000186.jsonl.zst3.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000192.jsonl.zst4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000200.jsonl.zst3.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000213.jsonl.zst3.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000219.jsonl.zst3.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000226.jsonl.zst3.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000256.jsonl.zst3.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000259.jsonl.zst3.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000261.jsonl.zst3.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000263.jsonl.zst4.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000274.jsonl.zst3.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000281.jsonl.zst3.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000286.jsonl.zst3.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000290.jsonl.zst3.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000305.jsonl.zst3.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000315.jsonl.zst3.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000321.jsonl.zst3.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000329.jsonl.zst3.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000362.jsonl.zst3.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000373.jsonl.zst4.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000374.jsonl.zst3.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000390.jsonl.zst3.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000425.jsonl.zst3.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0017__shard_00000432.jsonl.zst2.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000002.jsonl.zst3.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000003.jsonl.zst4.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000005.jsonl.zst3.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000006.jsonl.zst3.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000007.jsonl.zst3.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000008.jsonl.zst4.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000009.jsonl.zst3.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000012.jsonl.zst3.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000014.jsonl.zst4.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000016.jsonl.zst3.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000017.jsonl.zst3.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000021.jsonl.zst3.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000022.jsonl.zst3.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000024.jsonl.zst3.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000027.jsonl.zst3.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000031.jsonl.zst3.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000033.jsonl.zst3.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000035.jsonl.zst4.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000037.jsonl.zst3.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000039.jsonl.zst3.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000040.jsonl.zst3.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000044.jsonl.zst4.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000045.jsonl.zst3.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000046.jsonl.zst4.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_007__data__common_crawl-transportation-0018__shard_00000048.jsonl.zst4.12 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors