Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-100000-docs / worker_0003
187 GB
58,264 files
Updated 25 days ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000446.jsonl.zst6.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000447.jsonl.zst5.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000448.jsonl.zst6.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000449.jsonl.zst6.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000450.jsonl.zst5.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000451.jsonl.zst6.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000452.jsonl.zst6.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000453.jsonl.zst6.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000454.jsonl.zst6.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000455.jsonl.zst6.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000456.jsonl.zst6.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000457.jsonl.zst6.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000458.jsonl.zst6.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000459.jsonl.zst6.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000460.jsonl.zst6.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000461.jsonl.zst6.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000462.jsonl.zst6.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000463.jsonl.zst6.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000464.jsonl.zst6.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000465.jsonl.zst6.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000466.jsonl.zst5.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000467.jsonl.zst6.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000468.jsonl.zst6.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000469.jsonl.zst6.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000470.jsonl.zst6.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000471.jsonl.zst6.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000472.jsonl.zst6.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000473.jsonl.zst5.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000474.jsonl.zst6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000475.jsonl.zst6.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000476.jsonl.zst6.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000477.jsonl.zst6.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000478.jsonl.zst6.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000479.jsonl.zst6.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000480.jsonl.zst6.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000481.jsonl.zst6.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000482.jsonl.zst5.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000483.jsonl.zst6.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000484.jsonl.zst6.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000485.jsonl.zst6.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000486.jsonl.zst6.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000487.jsonl.zst5.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000488.jsonl.zst6.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000489.jsonl.zst6.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000490.jsonl.zst6.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000491.jsonl.zst6.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000492.jsonl.zst6.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000493.jsonl.zst6.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000494.jsonl.zst6.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000495.jsonl.zst6.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000496.jsonl.zst6.18 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000497.jsonl.zst6.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000498.jsonl.zst6.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000499.jsonl.zst6.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000500.jsonl.zst6.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000000.jsonl.zst6.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000001.jsonl.zst6.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000002.jsonl.zst6.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000003.jsonl.zst6.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000004.jsonl.zst6.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000005.jsonl.zst6.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000006.jsonl.zst6.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000007.jsonl.zst6.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000008.jsonl.zst6.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000009.jsonl.zst6.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000010.jsonl.zst5.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000011.jsonl.zst6.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000012.jsonl.zst6.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000013.jsonl.zst6.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000014.jsonl.zst6.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000015.jsonl.zst6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000016.jsonl.zst6.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000017.jsonl.zst6.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000018.jsonl.zst6.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000019.jsonl.zst6.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000020.jsonl.zst6.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000021.jsonl.zst6.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000022.jsonl.zst6.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000023.jsonl.zst6.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000024.jsonl.zst6.18 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000025.jsonl.zst6.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000026.jsonl.zst6.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000027.jsonl.zst6.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000028.jsonl.zst6.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000029.jsonl.zst6.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000030.jsonl.zst4.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000031.jsonl.zst6.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000032.jsonl.zst6.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000033.jsonl.zst6.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000034.jsonl.zst6.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000035.jsonl.zst6.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000036.jsonl.zst6.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000037.jsonl.zst6.24 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000038.jsonl.zst6.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000039.jsonl.zst6.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000040.jsonl.zst6.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000041.jsonl.zst6.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000042.jsonl.zst6.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000043.jsonl.zst6.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0019__shard_00000044.jsonl.zst6.65 MB
xet
Total size
187 GB
Files
58,264
Last updated
Mar 25
Pre-warmed CDN
US EU US EU

Contributors