Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0074
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000347.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000348.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000349.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000350.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000351.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000352.jsonl.zst1.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000353.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000354.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000355.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000356.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000357.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000358.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0016__shard_00000359.jsonl.zst233 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000000.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000001.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000002.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000003.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000004.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000005.jsonl.zst1.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000006.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000007.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000008.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000009.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000010.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000011.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000012.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000013.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000014.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000015.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000016.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000017.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000018.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000019.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000020.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000021.jsonl.zst2.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000022.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000023.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000024.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000025.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000026.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000027.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000028.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000029.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000030.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000031.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000032.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000033.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000034.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000035.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000036.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000037.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000038.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000039.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000040.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000041.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000042.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000043.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000044.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000045.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000046.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000047.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000048.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000049.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000050.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000051.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000052.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000053.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000054.jsonl.zst1.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000055.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000056.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000057.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000058.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000059.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000060.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000061.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000062.jsonl.zst600 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000063.jsonl.zst651 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000064.jsonl.zst761 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000065.jsonl.zst672 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000066.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000067.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000068.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000069.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000070.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000071.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000072.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000073.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000074.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000075.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000076.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000077.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000078.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000079.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000080.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000081.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000082.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000083.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000084.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000085.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0017__shard_00000086.jsonl.zst1.52 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors