Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0044
11.1 GB
56,043 files
Updated about 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000095.jsonl.zst301 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000096.jsonl.zst327 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000097.jsonl.zst107 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000098.jsonl.zst306 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000099.jsonl.zst336 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000100.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000101.jsonl.zst310 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000102.jsonl.zst282 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000103.jsonl.zst244 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000104.jsonl.zst276 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000105.jsonl.zst293 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000106.jsonl.zst275 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000107.jsonl.zst241 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000108.jsonl.zst124 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000109.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000110.jsonl.zst263 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000111.jsonl.zst247 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000112.jsonl.zst228 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000113.jsonl.zst334 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000114.jsonl.zst228 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000115.jsonl.zst270 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000116.jsonl.zst302 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000117.jsonl.zst292 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000118.jsonl.zst259 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000119.jsonl.zst171 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000120.jsonl.zst286 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000121.jsonl.zst252 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000122.jsonl.zst458 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000123.jsonl.zst309 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000124.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000125.jsonl.zst250 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000126.jsonl.zst262 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000127.jsonl.zst276 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000128.jsonl.zst286 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000129.jsonl.zst340 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000130.jsonl.zst243 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000131.jsonl.zst338 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000132.jsonl.zst291 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000133.jsonl.zst257 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000134.jsonl.zst259 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000135.jsonl.zst267 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000136.jsonl.zst288 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000137.jsonl.zst261 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000138.jsonl.zst282 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000139.jsonl.zst317 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000140.jsonl.zst316 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000141.jsonl.zst282 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000142.jsonl.zst302 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000143.jsonl.zst327 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000144.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000145.jsonl.zst234 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000146.jsonl.zst252 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000147.jsonl.zst206 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000148.jsonl.zst368 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000149.jsonl.zst373 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000150.jsonl.zst279 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000151.jsonl.zst306 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000152.jsonl.zst245 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000153.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000154.jsonl.zst235 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000155.jsonl.zst323 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000156.jsonl.zst216 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000157.jsonl.zst254 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000158.jsonl.zst291 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000159.jsonl.zst312 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000160.jsonl.zst280 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000161.jsonl.zst294 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000162.jsonl.zst217 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000163.jsonl.zst361 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000164.jsonl.zst279 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000165.jsonl.zst255 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000166.jsonl.zst287 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000167.jsonl.zst279 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000168.jsonl.zst274 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000169.jsonl.zst296 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000170.jsonl.zst357 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000171.jsonl.zst298 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000172.jsonl.zst203 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000173.jsonl.zst213 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000174.jsonl.zst321 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000175.jsonl.zst335 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000176.jsonl.zst298 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000177.jsonl.zst266 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000178.jsonl.zst231 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000179.jsonl.zst264 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000180.jsonl.zst266 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000181.jsonl.zst252 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000182.jsonl.zst300 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000183.jsonl.zst240 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000184.jsonl.zst319 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000185.jsonl.zst307 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000186.jsonl.zst287 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000187.jsonl.zst308 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000188.jsonl.zst303 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000189.jsonl.zst229 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000190.jsonl.zst260 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000191.jsonl.zst229 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000192.jsonl.zst261 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000193.jsonl.zst293 kB
xet
soc127__phase1_pool_shared__common_crawl__part_003__data__common_crawl-industrial-0019__shard_00000194.jsonl.zst363 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors