Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-500-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-500-docs / worker_0046
1.22 GB
43,129 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000914.jsonl.zst26.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000915.jsonl.zst17.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000916.jsonl.zst18.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000917.jsonl.zst139 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000918.jsonl.zst20.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000919.jsonl.zst23 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000920.jsonl.zst13.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000921.jsonl.zst29 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000922.jsonl.zst10.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000923.jsonl.zst5.18 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000924.jsonl.zst49.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000925.jsonl.zst8.07 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000926.jsonl.zst21 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000927.jsonl.zst9.38 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000928.jsonl.zst15.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000929.jsonl.zst28.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000930.jsonl.zst36.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000931.jsonl.zst7.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000932.jsonl.zst10.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000933.jsonl.zst4.14 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000934.jsonl.zst24.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000935.jsonl.zst33.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000936.jsonl.zst24.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000937.jsonl.zst6.05 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000938.jsonl.zst5.45 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000939.jsonl.zst10.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000940.jsonl.zst10.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000941.jsonl.zst39.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000942.jsonl.zst9.39 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000943.jsonl.zst17.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000944.jsonl.zst16.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000945.jsonl.zst14.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000946.jsonl.zst9.79 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000947.jsonl.zst28.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000948.jsonl.zst23.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000949.jsonl.zst3.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000950.jsonl.zst5.72 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000951.jsonl.zst9.91 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000952.jsonl.zst16.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000953.jsonl.zst17.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000954.jsonl.zst2.64 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000955.jsonl.zst36.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000956.jsonl.zst5.95 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000957.jsonl.zst38.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000958.jsonl.zst6.27 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000959.jsonl.zst8.82 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000960.jsonl.zst54.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000961.jsonl.zst37.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000962.jsonl.zst7.95 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000963.jsonl.zst28.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000964.jsonl.zst13.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000965.jsonl.zst20.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000966.jsonl.zst23.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000967.jsonl.zst11.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000968.jsonl.zst13.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000969.jsonl.zst10 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000970.jsonl.zst6.84 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000971.jsonl.zst17.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000972.jsonl.zst21.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000973.jsonl.zst1.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000974.jsonl.zst9.71 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000975.jsonl.zst20.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000976.jsonl.zst5.27 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000977.jsonl.zst12.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000978.jsonl.zst16.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000979.jsonl.zst5.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000980.jsonl.zst5.85 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000981.jsonl.zst18.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000982.jsonl.zst17.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000983.jsonl.zst22.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000984.jsonl.zst32.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000985.jsonl.zst4.74 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000986.jsonl.zst12.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000987.jsonl.zst11.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000988.jsonl.zst10.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000989.jsonl.zst10.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000990.jsonl.zst56.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000991.jsonl.zst2.79 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000992.jsonl.zst30.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000993.jsonl.zst16.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000994.jsonl.zst12.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000995.jsonl.zst26.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000996.jsonl.zst11.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000997.jsonl.zst15.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000998.jsonl.zst16.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00000999.jsonl.zst19.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001000.jsonl.zst23.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001001.jsonl.zst18.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001002.jsonl.zst9.25 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001003.jsonl.zst10.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001004.jsonl.zst5.07 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001005.jsonl.zst15.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001006.jsonl.zst20.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001007.jsonl.zst3.75 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001008.jsonl.zst26.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001009.jsonl.zst38.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001010.jsonl.zst10.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001011.jsonl.zst6.63 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001012.jsonl.zst20.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-health-0018__shard_00001013.jsonl.zst5.06 kB
xet
Total size
1.22 GB
Files
43,129
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors