Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0073
11.1 GB
56,043 files
Updated about 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000288.jsonl.zst241 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000289.jsonl.zst272 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000290.jsonl.zst202 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000291.jsonl.zst205 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000292.jsonl.zst216 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000293.jsonl.zst138 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000294.jsonl.zst154 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000295.jsonl.zst162 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000296.jsonl.zst195 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000297.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000298.jsonl.zst217 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000299.jsonl.zst228 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000300.jsonl.zst196 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000301.jsonl.zst251 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000302.jsonl.zst183 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000303.jsonl.zst207 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000304.jsonl.zst174 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000305.jsonl.zst184 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000306.jsonl.zst203 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000307.jsonl.zst205 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000308.jsonl.zst216 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000309.jsonl.zst166 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000310.jsonl.zst178 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000311.jsonl.zst186 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000312.jsonl.zst179 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000313.jsonl.zst255 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000314.jsonl.zst192 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000315.jsonl.zst290 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000316.jsonl.zst154 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000317.jsonl.zst180 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000318.jsonl.zst186 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000319.jsonl.zst174 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000320.jsonl.zst221 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000321.jsonl.zst230 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000322.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000323.jsonl.zst167 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000324.jsonl.zst224 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000325.jsonl.zst239 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000326.jsonl.zst187 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000327.jsonl.zst175 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000329.jsonl.zst51.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000331.jsonl.zst127 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000332.jsonl.zst194 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000333.jsonl.zst172 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000334.jsonl.zst197 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000335.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000336.jsonl.zst196 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000337.jsonl.zst122 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000338.jsonl.zst196 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000339.jsonl.zst189 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000340.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000341.jsonl.zst233 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000342.jsonl.zst231 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000343.jsonl.zst273 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000344.jsonl.zst196 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000345.jsonl.zst238 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000346.jsonl.zst188 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000347.jsonl.zst174 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000348.jsonl.zst175 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000349.jsonl.zst152 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000350.jsonl.zst244 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000351.jsonl.zst237 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000352.jsonl.zst212 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000353.jsonl.zst309 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000354.jsonl.zst145 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000355.jsonl.zst141 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000356.jsonl.zst178 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000357.jsonl.zst279 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000358.jsonl.zst153 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000359.jsonl.zst236 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000360.jsonl.zst207 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000361.jsonl.zst186 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000362.jsonl.zst208 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000363.jsonl.zst227 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000364.jsonl.zst125 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000365.jsonl.zst192 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000366.jsonl.zst214 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000367.jsonl.zst194 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000368.jsonl.zst181 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000369.jsonl.zst150 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000370.jsonl.zst190 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000371.jsonl.zst181 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000372.jsonl.zst183 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000373.jsonl.zst161 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000374.jsonl.zst163 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000375.jsonl.zst110 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000376.jsonl.zst158 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000377.jsonl.zst162 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0019__shard_00000378.jsonl.zst172 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000000.jsonl.zst159 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000001.jsonl.zst108 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000002.jsonl.zst140 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000003.jsonl.zst201 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000004.jsonl.zst146 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000005.jsonl.zst163 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000006.jsonl.zst139 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000007.jsonl.zst173 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000008.jsonl.zst157 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000009.jsonl.zst162 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software_development-0012__shard_00000010.jsonl.zst172 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors