Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0070
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000142.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000143.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000144.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000145.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000146.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000147.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000148.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000149.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000150.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000151.jsonl.zst1.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000152.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000153.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000154.jsonl.zst1.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000155.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000156.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000157.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000158.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000159.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000160.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000161.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000162.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000163.jsonl.zst2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000164.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000165.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000166.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000167.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000168.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000169.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000170.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000171.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000172.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000173.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000174.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000175.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000176.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000177.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000178.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000179.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000180.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000181.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000182.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000183.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000184.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000185.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000186.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000187.jsonl.zst1.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000188.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000189.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000190.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000191.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000192.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000193.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000194.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000195.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000196.jsonl.zst789 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000197.jsonl.zst647 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000198.jsonl.zst635 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000199.jsonl.zst678 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000200.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000201.jsonl.zst1.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000202.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000203.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000204.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000205.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000206.jsonl.zst1.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000207.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000208.jsonl.zst1.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000209.jsonl.zst1.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000210.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000211.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000212.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000213.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000214.jsonl.zst1.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000215.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000216.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000217.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000218.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000219.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000220.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000221.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000222.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000223.jsonl.zst1.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000224.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000225.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000226.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000227.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000228.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000229.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000230.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000231.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000232.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000233.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000234.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000235.jsonl.zst1.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000236.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000237.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000238.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000239.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000240.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000241.jsonl.zst1.57 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors