Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-50000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0036
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000513.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000514.jsonl.zst1.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000515.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000516.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000517.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000518.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000519.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000520.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000521.jsonl.zst1.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000522.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000523.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000524.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000525.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000526.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000527.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000528.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000529.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000530.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000531.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000532.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000533.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000534.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000535.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000536.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000537.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000538.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000539.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000540.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000541.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000542.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000543.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000544.jsonl.zst1.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000545.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000546.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000547.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000548.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000549.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000550.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000551.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000552.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000553.jsonl.zst1.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000554.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000555.jsonl.zst1.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000556.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000557.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000558.jsonl.zst1.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000559.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000560.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000561.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000562.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000563.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000564.jsonl.zst823 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000565.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000566.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000567.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000568.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000569.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000570.jsonl.zst1.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000571.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000572.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000573.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000574.jsonl.zst1.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000575.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000576.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000577.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000578.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000579.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000580.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000581.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000582.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000583.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000584.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000585.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000586.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000587.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000588.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000589.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000590.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000591.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000592.jsonl.zst1.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000593.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000594.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000595.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000596.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000597.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000598.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000599.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000600.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000601.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000602.jsonl.zst1.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000603.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000604.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000605.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000606.jsonl.zst1.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000607.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000608.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000609.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000610.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000611.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0019__shard_00000612.jsonl.zst1.41 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors