Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0069
11.1 GB
56,043 files
Updated about 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000148.jsonl.zst207 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000167.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000207.jsonl.zst200 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000221.jsonl.zst244 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000254.jsonl.zst246 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000271.jsonl.zst265 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000292.jsonl.zst215 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000307.jsonl.zst237 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000328.jsonl.zst199 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000353.jsonl.zst240 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000354.jsonl.zst264 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000360.jsonl.zst251 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0013__shard_00000374.jsonl.zst187 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000002.jsonl.zst224 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000003.jsonl.zst291 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000006.jsonl.zst219 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000008.jsonl.zst257 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000014.jsonl.zst131 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000020.jsonl.zst202 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000024.jsonl.zst235 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000030.jsonl.zst270 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000032.jsonl.zst237 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000049.jsonl.zst248 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000065.jsonl.zst232 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000069.jsonl.zst198 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000070.jsonl.zst240 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000082.jsonl.zst266 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000085.jsonl.zst257 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000087.jsonl.zst210 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000088.jsonl.zst231 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000100.jsonl.zst193 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000103.jsonl.zst224 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000110.jsonl.zst188 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000111.jsonl.zst203 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000113.jsonl.zst293 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000115.jsonl.zst222 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000118.jsonl.zst246 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000121.jsonl.zst189 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000122.jsonl.zst244 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000128.jsonl.zst275 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000139.jsonl.zst211 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000147.jsonl.zst227 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000148.jsonl.zst231 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000150.jsonl.zst194 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000158.jsonl.zst225 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000167.jsonl.zst197 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000172.jsonl.zst206 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000179.jsonl.zst301 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000219.jsonl.zst175 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000224.jsonl.zst262 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000225.jsonl.zst289 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000242.jsonl.zst199 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000244.jsonl.zst288 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000248.jsonl.zst278 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000249.jsonl.zst202 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000257.jsonl.zst284 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000270.jsonl.zst245 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000284.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000292.jsonl.zst246 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000303.jsonl.zst252 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000314.jsonl.zst228 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000317.jsonl.zst247 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000322.jsonl.zst233 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000344.jsonl.zst245 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000361.jsonl.zst255 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000366.jsonl.zst209 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000373.jsonl.zst187 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000376.jsonl.zst212 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000379.jsonl.zst231 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000383.jsonl.zst203 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000386.jsonl.zst259 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000387.jsonl.zst188 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000390.jsonl.zst280 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000391.jsonl.zst274 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000397.jsonl.zst185 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000405.jsonl.zst206 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000406.jsonl.zst231 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000407.jsonl.zst229 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000408.jsonl.zst200 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0014__shard_00000417.jsonl.zst206 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000003.jsonl.zst239 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000005.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000006.jsonl.zst207 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000008.jsonl.zst123 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000014.jsonl.zst92.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000015.jsonl.zst131 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000017.jsonl.zst94.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000024.jsonl.zst227 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000027.jsonl.zst225 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000028.jsonl.zst212 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000034.jsonl.zst289 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000038.jsonl.zst208 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000039.jsonl.zst234 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000043.jsonl.zst278 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000044.jsonl.zst242 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000045.jsonl.zst264 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000050.jsonl.zst253 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000054.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000067.jsonl.zst283 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0015__shard_00000069.jsonl.zst246 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors