Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0019
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000813.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000814.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000815.jsonl.zst1.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000817.jsonl.zst2.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000818.jsonl.zst2.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000819.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000820.jsonl.zst2.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000822.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000823.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000824.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000825.jsonl.zst1.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000826.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000828.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000830.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000831.jsonl.zst1.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000832.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000834.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000836.jsonl.zst1.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000838.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000841.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000842.jsonl.zst2.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000843.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000844.jsonl.zst2.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000846.jsonl.zst2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000848.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000849.jsonl.zst2.03 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000851.jsonl.zst2.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000853.jsonl.zst1.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000854.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000857.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000858.jsonl.zst2.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000861.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000862.jsonl.zst2.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000864.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000865.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000867.jsonl.zst1.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000870.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000871.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000872.jsonl.zst1.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000873.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000876.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000879.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000880.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000881.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000882.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000883.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000884.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000885.jsonl.zst2.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000888.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000889.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000891.jsonl.zst2.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000895.jsonl.zst2.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000896.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000898.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000900.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000901.jsonl.zst1.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000903.jsonl.zst1.96 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000904.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000905.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000906.jsonl.zst2.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000907.jsonl.zst1.81 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000910.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000911.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000912.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000913.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000914.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000916.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000918.jsonl.zst1.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000919.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000920.jsonl.zst2.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000922.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000923.jsonl.zst2.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000924.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000925.jsonl.zst2.23 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000926.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000927.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000928.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000929.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000931.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000932.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000934.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000935.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000936.jsonl.zst1.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000944.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000945.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000947.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000949.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000950.jsonl.zst2.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000951.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000952.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000956.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000957.jsonl.zst2.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000960.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000961.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000963.jsonl.zst1.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000964.jsonl.zst2.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000965.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000966.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000969.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_001__data__common_crawl-finance_and_business-0018__shard_00000971.jsonl.zst1.95 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors