Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-1000-docs / worker_0090
2.37 GB
46,808 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0014__shard_00000313.jsonl.zst13.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0014__shard_00000314.jsonl.zst11.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0014__shard_00000315.jsonl.zst47.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0014__shard_00000316.jsonl.zst45 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0014__shard_00000317.jsonl.zst47.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0014__shard_00000318.jsonl.zst5.19 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000000.jsonl.zst29.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000001.jsonl.zst23.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000002.jsonl.zst30.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000003.jsonl.zst28.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000004.jsonl.zst23.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000005.jsonl.zst35.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000006.jsonl.zst49.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000007.jsonl.zst52.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000008.jsonl.zst49.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000009.jsonl.zst54.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000010.jsonl.zst36.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000011.jsonl.zst41.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000012.jsonl.zst26.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000013.jsonl.zst63.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000014.jsonl.zst40.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000015.jsonl.zst20.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000016.jsonl.zst39.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000017.jsonl.zst42.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000018.jsonl.zst15.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000019.jsonl.zst40.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000020.jsonl.zst27.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000021.jsonl.zst40.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000022.jsonl.zst30 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000023.jsonl.zst33.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000024.jsonl.zst35.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000025.jsonl.zst60.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000026.jsonl.zst29.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000027.jsonl.zst36.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000028.jsonl.zst31.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000029.jsonl.zst32.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000030.jsonl.zst22.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000031.jsonl.zst14.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000032.jsonl.zst44.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000033.jsonl.zst22.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000034.jsonl.zst30.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000035.jsonl.zst35.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000036.jsonl.zst23 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000037.jsonl.zst22.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000038.jsonl.zst26.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000039.jsonl.zst29.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000040.jsonl.zst22.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000041.jsonl.zst29.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000042.jsonl.zst83.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000043.jsonl.zst28.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000044.jsonl.zst43.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000045.jsonl.zst24.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000046.jsonl.zst40 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000047.jsonl.zst16.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000048.jsonl.zst40.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000049.jsonl.zst31.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000050.jsonl.zst41.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000051.jsonl.zst30.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000052.jsonl.zst16.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000053.jsonl.zst65.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000054.jsonl.zst36.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000055.jsonl.zst44.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000056.jsonl.zst70.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000057.jsonl.zst32.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000058.jsonl.zst201 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000059.jsonl.zst25.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000060.jsonl.zst26.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000061.jsonl.zst35.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000062.jsonl.zst49.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000063.jsonl.zst34.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000064.jsonl.zst41.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000065.jsonl.zst28.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000066.jsonl.zst39.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000067.jsonl.zst51.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000068.jsonl.zst14.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000069.jsonl.zst23 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000070.jsonl.zst37.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000071.jsonl.zst22.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000072.jsonl.zst8.29 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000073.jsonl.zst38.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000074.jsonl.zst18.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000075.jsonl.zst24.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000076.jsonl.zst28.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000077.jsonl.zst27.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000078.jsonl.zst38.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000079.jsonl.zst23.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000080.jsonl.zst45.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000081.jsonl.zst45.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000082.jsonl.zst21.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000083.jsonl.zst38.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000084.jsonl.zst38.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000085.jsonl.zst28.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000086.jsonl.zst29.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000087.jsonl.zst19.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000088.jsonl.zst20.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000089.jsonl.zst58 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000090.jsonl.zst22.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000091.jsonl.zst15.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000092.jsonl.zst63.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0015__shard_00000093.jsonl.zst23.1 kB
xet
Total size
2.37 GB
Files
46,808
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors