Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-100000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-100000-docs / worker_0036
187 GB
58,264 files
Updated 25 days ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000531.jsonl.zst2.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000532.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000533.jsonl.zst3.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000534.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000535.jsonl.zst3.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000536.jsonl.zst2.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000537.jsonl.zst2.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000538.jsonl.zst2.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000539.jsonl.zst2.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000540.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000541.jsonl.zst2.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000542.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000543.jsonl.zst3.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000544.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000545.jsonl.zst3.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000546.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000547.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000548.jsonl.zst2.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000549.jsonl.zst2.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000550.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000551.jsonl.zst2.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000552.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000553.jsonl.zst2.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000554.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000555.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000556.jsonl.zst3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000557.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000558.jsonl.zst2.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000559.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000560.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000561.jsonl.zst2.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000562.jsonl.zst2.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000563.jsonl.zst3.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000564.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000565.jsonl.zst3.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000566.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000567.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000568.jsonl.zst2.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000569.jsonl.zst3.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000570.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000571.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000572.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000573.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000574.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000575.jsonl.zst2.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000576.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000577.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000578.jsonl.zst3.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000579.jsonl.zst3.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000580.jsonl.zst2.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000581.jsonl.zst2.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000582.jsonl.zst2.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000583.jsonl.zst3.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000584.jsonl.zst2.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000585.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000586.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000587.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000588.jsonl.zst3.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000589.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000590.jsonl.zst2.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000591.jsonl.zst2.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000592.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000593.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000594.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000595.jsonl.zst2.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000596.jsonl.zst2.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000597.jsonl.zst3.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000598.jsonl.zst2.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000599.jsonl.zst2.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000600.jsonl.zst2.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000601.jsonl.zst2.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000602.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000603.jsonl.zst2.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000604.jsonl.zst2.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000605.jsonl.zst2.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000606.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000607.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000608.jsonl.zst2.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000609.jsonl.zst3.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000610.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000611.jsonl.zst2.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000612.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000613.jsonl.zst2.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000614.jsonl.zst2.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000615.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000616.jsonl.zst2.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000617.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000618.jsonl.zst2.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000619.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000620.jsonl.zst2.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000621.jsonl.zst2.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000622.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000623.jsonl.zst2.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000624.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000625.jsonl.zst2.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000626.jsonl.zst2.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000627.jsonl.zst2.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000628.jsonl.zst2.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000629.jsonl.zst2.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000630.jsonl.zst1.27 MB
xet
Total size
187 GB
Files
58,264
Last updated
Mar 25
Pre-warmed CDN
US EU US EU

Contributors