Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-100000-docs / worker_0002
187 GB
58,264 files
Updated 4 months ago
Name
Size
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000433.jsonl.zst6.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000436.jsonl.zst6.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000440.jsonl.zst6.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000443.jsonl.zst6.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000448.jsonl.zst6.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000452.jsonl.zst6.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000458.jsonl.zst6.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000467.jsonl.zst6.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000468.jsonl.zst6.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0017__shard_00000469.jsonl.zst6.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000000.jsonl.zst6.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000001.jsonl.zst6.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000002.jsonl.zst5.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000003.jsonl.zst6.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000004.jsonl.zst6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000005.jsonl.zst6.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000006.jsonl.zst6.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000007.jsonl.zst6.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000008.jsonl.zst5.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000009.jsonl.zst6.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000010.jsonl.zst6.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000011.jsonl.zst6.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000012.jsonl.zst6.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000013.jsonl.zst6.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000014.jsonl.zst6.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000015.jsonl.zst6.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000016.jsonl.zst6.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000017.jsonl.zst6.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000018.jsonl.zst6.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000019.jsonl.zst6.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000020.jsonl.zst6.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000021.jsonl.zst6.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000022.jsonl.zst7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000023.jsonl.zst6.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000024.jsonl.zst6.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000025.jsonl.zst6.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000026.jsonl.zst6.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000027.jsonl.zst6.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000028.jsonl.zst6.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000029.jsonl.zst6.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000030.jsonl.zst6.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000031.jsonl.zst6.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000032.jsonl.zst3.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000033.jsonl.zst6.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000034.jsonl.zst7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000035.jsonl.zst6.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000036.jsonl.zst6.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000037.jsonl.zst6.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000038.jsonl.zst6.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000039.jsonl.zst5.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000040.jsonl.zst6.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000041.jsonl.zst5.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000042.jsonl.zst5.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000043.jsonl.zst6.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000044.jsonl.zst6.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000045.jsonl.zst6.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000046.jsonl.zst6.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000047.jsonl.zst6.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000048.jsonl.zst6.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000049.jsonl.zst6.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000050.jsonl.zst6.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000051.jsonl.zst6.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000052.jsonl.zst6.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000053.jsonl.zst6.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000054.jsonl.zst6.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000055.jsonl.zst6.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000056.jsonl.zst6.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000057.jsonl.zst6.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000058.jsonl.zst6.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000059.jsonl.zst6.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000060.jsonl.zst6.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000061.jsonl.zst6.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000062.jsonl.zst5.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000063.jsonl.zst6.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000064.jsonl.zst6.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000065.jsonl.zst6.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000066.jsonl.zst6.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000067.jsonl.zst6.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000068.jsonl.zst6.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000069.jsonl.zst6.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000070.jsonl.zst6.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000071.jsonl.zst6.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000072.jsonl.zst6.24 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000073.jsonl.zst6.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000074.jsonl.zst6.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000075.jsonl.zst6.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000076.jsonl.zst6.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000077.jsonl.zst6.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000078.jsonl.zst6.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000079.jsonl.zst6.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000080.jsonl.zst6.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000081.jsonl.zst5.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000082.jsonl.zst6.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000083.jsonl.zst6.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000084.jsonl.zst6.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000085.jsonl.zst6.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000086.jsonl.zst6.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000087.jsonl.zst6.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000088.jsonl.zst6.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-crime_and_law-0018__shard_00000089.jsonl.zst7.05 MB
xet
Total size
187 GB
Files
58,264
Last updated
Mar 25
Pre-warmed CDN
US EU US EU

Contributors