Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0034
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000837.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000838.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000839.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000840.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000841.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000842.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000843.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000844.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000845.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000846.jsonl.zst1.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000847.jsonl.zst1.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000848.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000849.jsonl.zst1.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000850.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000851.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000852.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000853.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000854.jsonl.zst1.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000855.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000856.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000857.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000858.jsonl.zst1.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000859.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000860.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000861.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000862.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000863.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000864.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000865.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000866.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000867.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000868.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000869.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000870.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000871.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000872.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000873.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000874.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000875.jsonl.zst1.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000876.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000877.jsonl.zst1.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000878.jsonl.zst1.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000879.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000880.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000881.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000882.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000883.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000884.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000885.jsonl.zst1.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000886.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000887.jsonl.zst1.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000888.jsonl.zst1.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000889.jsonl.zst1.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000890.jsonl.zst1.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000891.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000892.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000893.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000894.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000895.jsonl.zst1.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000896.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000897.jsonl.zst1.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000898.jsonl.zst1.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000899.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000900.jsonl.zst1.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000901.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000902.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000903.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000904.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000905.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000906.jsonl.zst1.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000907.jsonl.zst1.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000908.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000909.jsonl.zst1.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000910.jsonl.zst1.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000911.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000912.jsonl.zst1.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000913.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000914.jsonl.zst1.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000915.jsonl.zst1.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000916.jsonl.zst1.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000917.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000918.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000919.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000920.jsonl.zst1.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000921.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000922.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000923.jsonl.zst1.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000924.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000925.jsonl.zst1.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000926.jsonl.zst1.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000927.jsonl.zst1.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000928.jsonl.zst1.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000929.jsonl.zst1.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000930.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000931.jsonl.zst1.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000932.jsonl.zst1.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000933.jsonl.zst1.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000934.jsonl.zst1.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000935.jsonl.zst1.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000936.jsonl.zst1.49 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors