Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-500-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-500-docs / worker_0092
1.22 GB
43,129 files
Updated 3 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000404.jsonl.zst15.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000405.jsonl.zst9.92 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000406.jsonl.zst26.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000407.jsonl.zst22.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000408.jsonl.zst32.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000409.jsonl.zst37 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000410.jsonl.zst18.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000411.jsonl.zst15.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000412.jsonl.zst12.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000413.jsonl.zst25.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000414.jsonl.zst7.06 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000415.jsonl.zst31.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000416.jsonl.zst15.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000417.jsonl.zst14.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000418.jsonl.zst18.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000419.jsonl.zst78.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000420.jsonl.zst21.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000421.jsonl.zst15.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000422.jsonl.zst22.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000423.jsonl.zst34.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000424.jsonl.zst14 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000425.jsonl.zst23.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000426.jsonl.zst13.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000429.jsonl.zst26 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000430.jsonl.zst30.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000431.jsonl.zst27.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000432.jsonl.zst13 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000433.jsonl.zst32.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000434.jsonl.zst25.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000435.jsonl.zst42.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000436.jsonl.zst42.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000437.jsonl.zst30.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000438.jsonl.zst18.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000439.jsonl.zst17 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000440.jsonl.zst30.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000441.jsonl.zst32.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000442.jsonl.zst45.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000443.jsonl.zst29.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000444.jsonl.zst25 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000445.jsonl.zst11.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000446.jsonl.zst17.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000447.jsonl.zst24.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000000.jsonl.zst25.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000001.jsonl.zst40 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000002.jsonl.zst12.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000003.jsonl.zst32.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000004.jsonl.zst22.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000005.jsonl.zst26.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000006.jsonl.zst22.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000007.jsonl.zst41.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000008.jsonl.zst17.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000009.jsonl.zst15.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000010.jsonl.zst23.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000011.jsonl.zst24.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000012.jsonl.zst11.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000013.jsonl.zst6.34 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000014.jsonl.zst33.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000015.jsonl.zst15.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000016.jsonl.zst32.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000017.jsonl.zst30.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000018.jsonl.zst45.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000019.jsonl.zst32.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000020.jsonl.zst12.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000021.jsonl.zst65.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000022.jsonl.zst7.63 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000023.jsonl.zst12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000024.jsonl.zst18.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000025.jsonl.zst104 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000026.jsonl.zst18.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000027.jsonl.zst33.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000028.jsonl.zst11.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000029.jsonl.zst18.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000030.jsonl.zst14.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000031.jsonl.zst22.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000032.jsonl.zst22.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000033.jsonl.zst28.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000034.jsonl.zst32.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000035.jsonl.zst41.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000036.jsonl.zst23.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000037.jsonl.zst35.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000038.jsonl.zst29.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000039.jsonl.zst19.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000040.jsonl.zst33.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000041.jsonl.zst21.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000042.jsonl.zst22.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000043.jsonl.zst16.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000044.jsonl.zst15.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000045.jsonl.zst35.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000046.jsonl.zst4.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000047.jsonl.zst28.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000048.jsonl.zst30.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000049.jsonl.zst38.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000050.jsonl.zst32 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000051.jsonl.zst12.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000052.jsonl.zst37.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000053.jsonl.zst15.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000054.jsonl.zst14.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000055.jsonl.zst25.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000056.jsonl.zst25.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0018__shard_00000057.jsonl.zst16.3 kB
xet
Total size
1.22 GB
Files
43,129
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors