Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-500-docs / worker_0045
1.22 GB
43,129 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000571.jsonl.zst27.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000572.jsonl.zst10.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000573.jsonl.zst16.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000574.jsonl.zst37.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000575.jsonl.zst17.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000576.jsonl.zst16.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000577.jsonl.zst15.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000578.jsonl.zst33.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000579.jsonl.zst6.52 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000580.jsonl.zst7.47 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000581.jsonl.zst27.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000582.jsonl.zst10.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000583.jsonl.zst14.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000584.jsonl.zst22.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000585.jsonl.zst22.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000586.jsonl.zst9.06 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000587.jsonl.zst16.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000588.jsonl.zst9.87 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000589.jsonl.zst19.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000590.jsonl.zst13.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000591.jsonl.zst13.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000592.jsonl.zst5.43 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000593.jsonl.zst13.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000594.jsonl.zst5.95 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000595.jsonl.zst11.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000596.jsonl.zst4.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000597.jsonl.zst18.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000598.jsonl.zst13.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000599.jsonl.zst28.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000600.jsonl.zst20.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000601.jsonl.zst8.01 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000602.jsonl.zst14.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000603.jsonl.zst11.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000604.jsonl.zst7.16 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000605.jsonl.zst9.72 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000606.jsonl.zst29.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000607.jsonl.zst23.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000608.jsonl.zst7.86 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000609.jsonl.zst20.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000610.jsonl.zst30.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000611.jsonl.zst7.13 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000612.jsonl.zst13.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000613.jsonl.zst8.66 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000614.jsonl.zst6.62 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000615.jsonl.zst7.97 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000616.jsonl.zst41.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000617.jsonl.zst26.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000618.jsonl.zst15.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000619.jsonl.zst4.37 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000620.jsonl.zst25.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000621.jsonl.zst13.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000622.jsonl.zst12.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000623.jsonl.zst9.63 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000624.jsonl.zst5.37 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000625.jsonl.zst4.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000626.jsonl.zst12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000627.jsonl.zst20.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000628.jsonl.zst27.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000629.jsonl.zst7.97 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000630.jsonl.zst16.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000631.jsonl.zst9.72 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000632.jsonl.zst23.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000633.jsonl.zst21.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000634.jsonl.zst23.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000635.jsonl.zst3.17 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000636.jsonl.zst12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000637.jsonl.zst6.25 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000638.jsonl.zst9.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000639.jsonl.zst30.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000640.jsonl.zst2.96 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000641.jsonl.zst23.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000642.jsonl.zst4.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000643.jsonl.zst2.59 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000644.jsonl.zst8.42 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000645.jsonl.zst10.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000646.jsonl.zst10.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000647.jsonl.zst42.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000648.jsonl.zst7.73 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000649.jsonl.zst38.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000650.jsonl.zst16.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000651.jsonl.zst5.81 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000652.jsonl.zst18.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000653.jsonl.zst15.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000654.jsonl.zst12.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000655.jsonl.zst10.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000656.jsonl.zst12.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000657.jsonl.zst9.28 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000658.jsonl.zst38.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000659.jsonl.zst22.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000660.jsonl.zst12.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000661.jsonl.zst13.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000662.jsonl.zst5.92 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000663.jsonl.zst6.18 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000664.jsonl.zst17.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000665.jsonl.zst12.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000666.jsonl.zst38.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000667.jsonl.zst13.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000668.jsonl.zst37.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000669.jsonl.zst62.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000670.jsonl.zst24.5 kB
xet
Total size
1.22 GB
Files
43,129
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors