Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-100000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-100000-docs / worker_0074
187 GB
58,264 files
Updated 24 days ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000349.jsonl.zst2.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000350.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000351.jsonl.zst3.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000352.jsonl.zst3.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000353.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000354.jsonl.zst3.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000355.jsonl.zst3.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000356.jsonl.zst2.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000357.jsonl.zst2.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000358.jsonl.zst3.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000359.jsonl.zst400 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000000.jsonl.zst2.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000001.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000002.jsonl.zst2.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000003.jsonl.zst3.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000004.jsonl.zst2.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000005.jsonl.zst3.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000006.jsonl.zst3.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000007.jsonl.zst3.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000008.jsonl.zst2.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000009.jsonl.zst3.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000010.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000011.jsonl.zst2.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000012.jsonl.zst3.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000013.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000014.jsonl.zst3.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000015.jsonl.zst3.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000016.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000017.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000018.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000019.jsonl.zst3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000020.jsonl.zst3.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000021.jsonl.zst3.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000022.jsonl.zst3.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000023.jsonl.zst3.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000024.jsonl.zst3.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000025.jsonl.zst2.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000026.jsonl.zst3.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000027.jsonl.zst3.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000028.jsonl.zst3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000029.jsonl.zst3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000030.jsonl.zst3.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000031.jsonl.zst3.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000032.jsonl.zst3.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000033.jsonl.zst3.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000034.jsonl.zst3.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000035.jsonl.zst2.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000036.jsonl.zst2.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000037.jsonl.zst3.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000038.jsonl.zst3.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000039.jsonl.zst3.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000040.jsonl.zst3.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000041.jsonl.zst3.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000042.jsonl.zst3.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000043.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000044.jsonl.zst3.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000045.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000046.jsonl.zst3.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000047.jsonl.zst3.24 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000048.jsonl.zst3.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000049.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000050.jsonl.zst2.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000051.jsonl.zst3.24 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000052.jsonl.zst3.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000053.jsonl.zst3.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000054.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000055.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000056.jsonl.zst3.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000057.jsonl.zst3.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000058.jsonl.zst3.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000059.jsonl.zst2.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000060.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000061.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000062.jsonl.zst1.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000063.jsonl.zst1.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000064.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000065.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000066.jsonl.zst3.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000067.jsonl.zst3.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000068.jsonl.zst3.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000069.jsonl.zst3.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000070.jsonl.zst3.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000071.jsonl.zst3.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000072.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000073.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000074.jsonl.zst3.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000075.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000076.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000077.jsonl.zst3.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000078.jsonl.zst3.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000079.jsonl.zst3.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000080.jsonl.zst3.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000081.jsonl.zst3.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000082.jsonl.zst3.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000083.jsonl.zst3.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000084.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000085.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000086.jsonl.zst2.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000087.jsonl.zst3.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000088.jsonl.zst3.33 MB
xet
Total size
187 GB
Files
58,264
Last updated
Mar 25
Pre-warmed CDN
US EU US EU

Contributors