Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0071
11.1 GB
56,043 files
Updated about 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000300.jsonl.zst198 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000301.jsonl.zst278 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000302.jsonl.zst188 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000303.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000304.jsonl.zst193 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000305.jsonl.zst213 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000306.jsonl.zst239 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000307.jsonl.zst207 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000308.jsonl.zst165 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000309.jsonl.zst171 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000310.jsonl.zst369 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000311.jsonl.zst194 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000312.jsonl.zst176 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000313.jsonl.zst211 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000314.jsonl.zst241 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000315.jsonl.zst176 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000316.jsonl.zst215 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000317.jsonl.zst227 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000318.jsonl.zst233 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000319.jsonl.zst271 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000320.jsonl.zst259 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000321.jsonl.zst221 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000322.jsonl.zst263 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000323.jsonl.zst174 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000324.jsonl.zst209 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000325.jsonl.zst168 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000326.jsonl.zst262 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000327.jsonl.zst226 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000328.jsonl.zst223 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000329.jsonl.zst268 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000330.jsonl.zst242 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000331.jsonl.zst161 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000332.jsonl.zst275 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000333.jsonl.zst179 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000334.jsonl.zst292 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000335.jsonl.zst173 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000336.jsonl.zst261 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000337.jsonl.zst167 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000338.jsonl.zst229 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000339.jsonl.zst221 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000340.jsonl.zst176 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000341.jsonl.zst193 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000342.jsonl.zst153 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000343.jsonl.zst200 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000344.jsonl.zst199 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000345.jsonl.zst222 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000346.jsonl.zst171 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000347.jsonl.zst235 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000348.jsonl.zst241 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000349.jsonl.zst258 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000350.jsonl.zst225 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000351.jsonl.zst223 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000352.jsonl.zst195 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000353.jsonl.zst155 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000354.jsonl.zst262 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000355.jsonl.zst306 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000356.jsonl.zst182 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000357.jsonl.zst218 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000358.jsonl.zst161 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000359.jsonl.zst208 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000360.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000361.jsonl.zst192 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000362.jsonl.zst307 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000363.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000364.jsonl.zst281 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000365.jsonl.zst246 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000366.jsonl.zst253 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000367.jsonl.zst261 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000368.jsonl.zst280 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000369.jsonl.zst192 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000370.jsonl.zst148 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000371.jsonl.zst222 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000372.jsonl.zst273 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000373.jsonl.zst260 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000374.jsonl.zst162 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000375.jsonl.zst173 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000376.jsonl.zst206 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000377.jsonl.zst201 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000378.jsonl.zst247 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000379.jsonl.zst131 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000380.jsonl.zst221 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000381.jsonl.zst203 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000382.jsonl.zst169 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000383.jsonl.zst255 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000384.jsonl.zst206 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000385.jsonl.zst211 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000386.jsonl.zst249 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000387.jsonl.zst155 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000388.jsonl.zst181 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000389.jsonl.zst226 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000390.jsonl.zst213 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000391.jsonl.zst257 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000392.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000393.jsonl.zst192 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000394.jsonl.zst217 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000395.jsonl.zst176 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000396.jsonl.zst246 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000397.jsonl.zst197 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000398.jsonl.zst237 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0017__shard_00000399.jsonl.zst245 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors