Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0031
99 GB
58,246 files
Updated 3 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000346.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000348.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000349.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000350.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000353.jsonl.zst1.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000356.jsonl.zst1.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000357.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000358.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000359.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000360.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000361.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000362.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000365.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000366.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000372.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000373.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000375.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000377.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000379.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000383.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000384.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000385.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000386.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000389.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000390.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000391.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000394.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000397.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000398.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000399.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000400.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000401.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000402.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000403.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000404.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000405.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000406.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000408.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000409.jsonl.zst1.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000410.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000412.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000413.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000414.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000415.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000418.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000419.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000420.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000421.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000423.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000424.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000425.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000426.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000427.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000428.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000429.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000431.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000432.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000433.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000434.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000439.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000440.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000442.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000445.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000446.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000447.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000453.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000454.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000456.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000457.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000458.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000459.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000460.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000461.jsonl.zst1.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000462.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000465.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000466.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000467.jsonl.zst2.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000468.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000469.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000470.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000471.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000473.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000477.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000479.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000480.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000481.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000485.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000489.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000492.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000494.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000495.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000498.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000500.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000501.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000502.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000503.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000505.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000506.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000507.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000512.jsonl.zst1.53 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors