Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-500-docs / worker_0041
1.22 GB
43,129 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000834.jsonl.zst17.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000844.jsonl.zst29.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000854.jsonl.zst21.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000859.jsonl.zst8.12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000864.jsonl.zst22.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000869.jsonl.zst5.21 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000880.jsonl.zst17.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000884.jsonl.zst57.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000885.jsonl.zst6.32 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000898.jsonl.zst27 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000904.jsonl.zst21.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000910.jsonl.zst2.71 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000914.jsonl.zst6.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000922.jsonl.zst2.22 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000923.jsonl.zst15.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000924.jsonl.zst16.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000926.jsonl.zst29.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000931.jsonl.zst36.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000936.jsonl.zst77.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000937.jsonl.zst23.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000949.jsonl.zst22.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000950.jsonl.zst30.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000955.jsonl.zst12.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000966.jsonl.zst17.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000972.jsonl.zst25.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000984.jsonl.zst16.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00000987.jsonl.zst26.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001010.jsonl.zst4.89 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001015.jsonl.zst21.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001016.jsonl.zst23 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001027.jsonl.zst30.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001034.jsonl.zst17.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001039.jsonl.zst5.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001046.jsonl.zst20.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001066.jsonl.zst12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001067.jsonl.zst26.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001068.jsonl.zst4.16 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001077.jsonl.zst12.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001083.jsonl.zst2.19 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001089.jsonl.zst36.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001093.jsonl.zst9.23 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001095.jsonl.zst13.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001098.jsonl.zst2.14 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001105.jsonl.zst9.53 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001106.jsonl.zst6.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001109.jsonl.zst15.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001115.jsonl.zst13.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001118.jsonl.zst3.74 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001125.jsonl.zst183 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001136.jsonl.zst15.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001139.jsonl.zst37.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001143.jsonl.zst13.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001154.jsonl.zst19.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001166.jsonl.zst34.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001173.jsonl.zst20.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001179.jsonl.zst30.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001181.jsonl.zst2.16 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001183.jsonl.zst16.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001186.jsonl.zst16.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001190.jsonl.zst12.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001193.jsonl.zst12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001194.jsonl.zst25.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001196.jsonl.zst14.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0016__shard_00001201.jsonl.zst32 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000005.jsonl.zst17.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000007.jsonl.zst46.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000011.jsonl.zst20.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000012.jsonl.zst26.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000013.jsonl.zst5.08 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000015.jsonl.zst12.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000016.jsonl.zst9.08 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000017.jsonl.zst5.33 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000018.jsonl.zst15.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000022.jsonl.zst25.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000023.jsonl.zst11.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000025.jsonl.zst26.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000026.jsonl.zst6.02 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000027.jsonl.zst22.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000028.jsonl.zst57.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000029.jsonl.zst18.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000033.jsonl.zst1.82 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000035.jsonl.zst31 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000037.jsonl.zst10.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000038.jsonl.zst15.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000040.jsonl.zst17.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000043.jsonl.zst12.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000044.jsonl.zst16.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000046.jsonl.zst19.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000047.jsonl.zst15.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000048.jsonl.zst40.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000052.jsonl.zst30 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000053.jsonl.zst11.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000057.jsonl.zst25.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000058.jsonl.zst17.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000062.jsonl.zst10.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000063.jsonl.zst14.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000065.jsonl.zst16.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000068.jsonl.zst35.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000070.jsonl.zst53.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0017__shard_00000071.jsonl.zst13.7 kB
xet
Total size
1.22 GB
Files
43,129
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors