Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-10000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-10000-docs / worker_0038
21.6 GB
57,845 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000188.jsonl.zst787 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000189.jsonl.zst844 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000190.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000191.jsonl.zst919 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000192.jsonl.zst1.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000193.jsonl.zst1.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000194.jsonl.zst673 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000195.jsonl.zst822 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000196.jsonl.zst976 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000197.jsonl.zst1.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000198.jsonl.zst979 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000199.jsonl.zst939 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000200.jsonl.zst955 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000201.jsonl.zst1.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000202.jsonl.zst965 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000203.jsonl.zst1.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000204.jsonl.zst1.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000205.jsonl.zst961 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000206.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000207.jsonl.zst815 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000208.jsonl.zst739 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000209.jsonl.zst1.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000210.jsonl.zst1.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000211.jsonl.zst1.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000212.jsonl.zst793 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000213.jsonl.zst1.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000214.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000215.jsonl.zst684 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000216.jsonl.zst914 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000217.jsonl.zst1.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000218.jsonl.zst1.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000219.jsonl.zst997 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000220.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000221.jsonl.zst1.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000222.jsonl.zst934 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000223.jsonl.zst745 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000224.jsonl.zst729 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000225.jsonl.zst911 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000226.jsonl.zst925 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000227.jsonl.zst1.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000228.jsonl.zst1.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000229.jsonl.zst872 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000230.jsonl.zst844 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000231.jsonl.zst919 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000232.jsonl.zst1.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000233.jsonl.zst927 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000234.jsonl.zst768 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000235.jsonl.zst800 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000236.jsonl.zst908 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000237.jsonl.zst1.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000238.jsonl.zst945 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000239.jsonl.zst924 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000240.jsonl.zst1.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000241.jsonl.zst1.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000242.jsonl.zst901 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000243.jsonl.zst800 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000244.jsonl.zst826 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000245.jsonl.zst896 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000246.jsonl.zst1.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000247.jsonl.zst934 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000248.jsonl.zst906 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000249.jsonl.zst720 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000250.jsonl.zst878 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000251.jsonl.zst1.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000252.jsonl.zst944 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000253.jsonl.zst873 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000254.jsonl.zst859 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000255.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000256.jsonl.zst869 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000257.jsonl.zst1.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000258.jsonl.zst702 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000259.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000260.jsonl.zst867 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000261.jsonl.zst1.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000262.jsonl.zst1.14 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000263.jsonl.zst960 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000264.jsonl.zst849 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000265.jsonl.zst1.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000266.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000267.jsonl.zst1.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000268.jsonl.zst1.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000269.jsonl.zst1.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000270.jsonl.zst790 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000271.jsonl.zst988 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000272.jsonl.zst944 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000273.jsonl.zst952 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000274.jsonl.zst830 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000275.jsonl.zst927 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000276.jsonl.zst925 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000277.jsonl.zst1.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000278.jsonl.zst792 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000279.jsonl.zst1.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000280.jsonl.zst1.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000281.jsonl.zst936 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000282.jsonl.zst957 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000283.jsonl.zst850 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000284.jsonl.zst1.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000285.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000286.jsonl.zst1.05 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-history_and_geography-0018__shard_00000287.jsonl.zst1.05 MB
xet
Total size
21.6 GB
Files
57,845
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors