Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-5000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0034
11.1 GB
56,043 files
Updated about 1 month ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000257.jsonl.zst184 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000258.jsonl.zst123 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000259.jsonl.zst161 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000260.jsonl.zst314 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000261.jsonl.zst135 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000262.jsonl.zst202 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000263.jsonl.zst260 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000264.jsonl.zst155 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000265.jsonl.zst219 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000266.jsonl.zst132 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000267.jsonl.zst155 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000268.jsonl.zst202 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000269.jsonl.zst112 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000270.jsonl.zst103 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000271.jsonl.zst134 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000272.jsonl.zst171 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000273.jsonl.zst249 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000274.jsonl.zst177 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000275.jsonl.zst115 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000276.jsonl.zst209 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000277.jsonl.zst205 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000278.jsonl.zst122 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000279.jsonl.zst162 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000280.jsonl.zst181 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000281.jsonl.zst64.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000282.jsonl.zst50.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000283.jsonl.zst172 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000284.jsonl.zst97.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000285.jsonl.zst129 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000286.jsonl.zst199 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000287.jsonl.zst203 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000288.jsonl.zst155 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000289.jsonl.zst141 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000290.jsonl.zst176 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000291.jsonl.zst214 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000292.jsonl.zst214 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000293.jsonl.zst115 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000294.jsonl.zst115 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000295.jsonl.zst170 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000296.jsonl.zst169 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000297.jsonl.zst166 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000298.jsonl.zst155 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000299.jsonl.zst139 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000300.jsonl.zst132 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000301.jsonl.zst106 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000302.jsonl.zst102 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000303.jsonl.zst227 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000304.jsonl.zst141 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000305.jsonl.zst148 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000306.jsonl.zst193 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000307.jsonl.zst233 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000308.jsonl.zst160 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000309.jsonl.zst149 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000310.jsonl.zst113 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000311.jsonl.zst122 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000312.jsonl.zst178 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000313.jsonl.zst235 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000314.jsonl.zst183 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000315.jsonl.zst135 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000316.jsonl.zst116 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000317.jsonl.zst154 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000318.jsonl.zst178 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000319.jsonl.zst151 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000320.jsonl.zst207 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000321.jsonl.zst147 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000322.jsonl.zst115 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000323.jsonl.zst164 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000324.jsonl.zst146 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000325.jsonl.zst197 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000326.jsonl.zst124 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000327.jsonl.zst158 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000328.jsonl.zst152 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000329.jsonl.zst127 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000330.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000331.jsonl.zst194 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000332.jsonl.zst161 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000333.jsonl.zst136 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000334.jsonl.zst157 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000335.jsonl.zst135 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000336.jsonl.zst146 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000337.jsonl.zst115 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000338.jsonl.zst136 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000339.jsonl.zst149 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000340.jsonl.zst193 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000341.jsonl.zst221 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000342.jsonl.zst205 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000343.jsonl.zst109 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000344.jsonl.zst177 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000345.jsonl.zst198 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000346.jsonl.zst154 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000347.jsonl.zst80.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000348.jsonl.zst176 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000349.jsonl.zst201 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000350.jsonl.zst335 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000351.jsonl.zst148 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000352.jsonl.zst150 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000353.jsonl.zst211 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000354.jsonl.zst280 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000355.jsonl.zst262 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-health-0018__shard_00000356.jsonl.zst253 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors