Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0030
99 GB
58,246 files
Updated 3 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000011.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000014.jsonl.zst2.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000052.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000169.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000188.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000257.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000286.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000295.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000300.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000336.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000344.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000359.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000378.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000413.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000437.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000441.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000445.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000481.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000522.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000544.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000574.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000603.jsonl.zst1.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000607.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000630.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000631.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000696.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000702.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000709.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000731.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000776.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000788.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000789.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000802.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000842.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000872.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000873.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000876.jsonl.zst1.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000882.jsonl.zst2.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000907.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000923.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000932.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000952.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000953.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000955.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00000997.jsonl.zst1.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001003.jsonl.zst1.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001005.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001031.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001058.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001075.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001080.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001085.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001100.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0015__shard_00001122.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000007.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000012.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000014.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000030.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000033.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000041.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000050.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000054.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000055.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000059.jsonl.zst1.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000066.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000070.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000078.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000086.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000096.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000099.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000114.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000116.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000140.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000154.jsonl.zst1.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000158.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000161.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000162.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000167.jsonl.zst1.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000172.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000173.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000174.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000175.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000180.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000183.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000185.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000192.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000202.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000207.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000208.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000214.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000223.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000225.jsonl.zst1.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000227.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000235.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000236.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000245.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000265.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000269.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000278.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000282.jsonl.zst1.73 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors