Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-1000-docs / worker_0085
2.37 GB
46,808 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000330.jsonl.zst53.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000331.jsonl.zst26.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000332.jsonl.zst53.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000333.jsonl.zst22.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000334.jsonl.zst89.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000335.jsonl.zst44.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000336.jsonl.zst65.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000337.jsonl.zst22.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000338.jsonl.zst22.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000339.jsonl.zst58.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000340.jsonl.zst35.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000341.jsonl.zst45.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000342.jsonl.zst35.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000343.jsonl.zst63.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000344.jsonl.zst52.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000345.jsonl.zst42.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000346.jsonl.zst39.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000347.jsonl.zst51.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000348.jsonl.zst67.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000349.jsonl.zst35.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000350.jsonl.zst48.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000351.jsonl.zst44.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000352.jsonl.zst22.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000353.jsonl.zst46.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000354.jsonl.zst52.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000355.jsonl.zst59.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000356.jsonl.zst30.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000357.jsonl.zst30.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000358.jsonl.zst49.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000359.jsonl.zst26 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000360.jsonl.zst58.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000361.jsonl.zst30.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000362.jsonl.zst80 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000363.jsonl.zst81.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000364.jsonl.zst49.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000365.jsonl.zst51.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000366.jsonl.zst58.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000367.jsonl.zst26.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000368.jsonl.zst41.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000369.jsonl.zst28 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000370.jsonl.zst35 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000371.jsonl.zst52.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000372.jsonl.zst123 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000373.jsonl.zst42.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000374.jsonl.zst31.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000375.jsonl.zst21.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000376.jsonl.zst30.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000377.jsonl.zst38.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000378.jsonl.zst45 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000379.jsonl.zst22.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000380.jsonl.zst38 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000381.jsonl.zst28 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000382.jsonl.zst45.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000383.jsonl.zst96.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000384.jsonl.zst35.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000385.jsonl.zst58.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000386.jsonl.zst42.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000387.jsonl.zst35 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000388.jsonl.zst36.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000389.jsonl.zst52.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000390.jsonl.zst35.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000391.jsonl.zst35.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000392.jsonl.zst49.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000393.jsonl.zst70.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000394.jsonl.zst33.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000395.jsonl.zst36.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000396.jsonl.zst45.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000397.jsonl.zst28.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000398.jsonl.zst57.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000399.jsonl.zst68.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000400.jsonl.zst54.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000401.jsonl.zst35.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000402.jsonl.zst32.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000403.jsonl.zst39.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000404.jsonl.zst37.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000405.jsonl.zst23 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000406.jsonl.zst40.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000407.jsonl.zst47.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000408.jsonl.zst48.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000409.jsonl.zst90.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000410.jsonl.zst37.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000411.jsonl.zst48.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000412.jsonl.zst35.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000413.jsonl.zst56.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000414.jsonl.zst37.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000415.jsonl.zst58.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000416.jsonl.zst33.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000417.jsonl.zst35.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000418.jsonl.zst48.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000419.jsonl.zst91.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000420.jsonl.zst62.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000421.jsonl.zst44.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000422.jsonl.zst38.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000423.jsonl.zst101 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000424.jsonl.zst39.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000425.jsonl.zst57.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000426.jsonl.zst20.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000427.jsonl.zst17.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000429.jsonl.zst33.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000430.jsonl.zst42.3 kB
xet
Total size
2.37 GB
Files
46,808
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors