Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0033
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000382.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000383.jsonl.zst1.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000384.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000385.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000386.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000387.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000388.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000389.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000390.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000391.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000392.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000393.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000394.jsonl.zst1.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000395.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000396.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000397.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000398.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000399.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000400.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000401.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000402.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000403.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000404.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000405.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000406.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000407.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000408.jsonl.zst1.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000409.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000410.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000411.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000412.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000413.jsonl.zst659 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000414.jsonl.zst610 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000415.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000416.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000417.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000418.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000419.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000420.jsonl.zst1.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000421.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000422.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000423.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000424.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000425.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000426.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000427.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000428.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000429.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000430.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000431.jsonl.zst1.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000432.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000433.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000434.jsonl.zst1.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000435.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000436.jsonl.zst1.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000437.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000438.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000439.jsonl.zst1.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000440.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000441.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000442.jsonl.zst1.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000443.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000444.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000445.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000446.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000447.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000448.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000449.jsonl.zst1.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000450.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000451.jsonl.zst649 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000452.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000453.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000454.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000455.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000456.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000457.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000458.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000459.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000460.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000461.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000462.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000463.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000464.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000465.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000466.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000467.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000468.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000469.jsonl.zst1.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000470.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000471.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000472.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000473.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000474.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000475.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000476.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000477.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000478.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000479.jsonl.zst959 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000480.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000481.jsonl.zst1.57 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors