Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0070
11.1 GB
56,043 files
Updated about 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000263.jsonl.zst214 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000265.jsonl.zst179 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000266.jsonl.zst201 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000267.jsonl.zst224 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000268.jsonl.zst253 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000269.jsonl.zst171 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000271.jsonl.zst211 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000272.jsonl.zst256 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000274.jsonl.zst219 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000275.jsonl.zst310 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000276.jsonl.zst203 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000277.jsonl.zst229 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000278.jsonl.zst227 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000279.jsonl.zst274 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000280.jsonl.zst208 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000282.jsonl.zst247 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000283.jsonl.zst262 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000284.jsonl.zst262 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000285.jsonl.zst244 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000286.jsonl.zst269 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000287.jsonl.zst238 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000290.jsonl.zst251 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000291.jsonl.zst223 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000293.jsonl.zst211 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000294.jsonl.zst284 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000295.jsonl.zst252 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000296.jsonl.zst261 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000298.jsonl.zst217 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000299.jsonl.zst272 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000300.jsonl.zst284 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000301.jsonl.zst184 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000302.jsonl.zst230 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000303.jsonl.zst257 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000305.jsonl.zst224 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000306.jsonl.zst309 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000307.jsonl.zst238 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000308.jsonl.zst284 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000309.jsonl.zst282 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000310.jsonl.zst258 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000313.jsonl.zst61.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000316.jsonl.zst112 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000318.jsonl.zst85.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000319.jsonl.zst415 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000321.jsonl.zst178 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000322.jsonl.zst299 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000323.jsonl.zst270 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000326.jsonl.zst202 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000327.jsonl.zst195 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000330.jsonl.zst242 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000331.jsonl.zst206 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000332.jsonl.zst171 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000333.jsonl.zst237 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000334.jsonl.zst291 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000335.jsonl.zst164 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000336.jsonl.zst264 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000337.jsonl.zst319 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000338.jsonl.zst230 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000339.jsonl.zst300 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000340.jsonl.zst217 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000341.jsonl.zst266 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000343.jsonl.zst303 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000344.jsonl.zst266 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000345.jsonl.zst243 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000346.jsonl.zst238 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000347.jsonl.zst209 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000348.jsonl.zst294 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000349.jsonl.zst310 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000350.jsonl.zst136 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000354.jsonl.zst213 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000355.jsonl.zst207 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000356.jsonl.zst259 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000357.jsonl.zst254 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000359.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000360.jsonl.zst173 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000362.jsonl.zst306 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000365.jsonl.zst252 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000366.jsonl.zst226 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000367.jsonl.zst227 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000368.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000369.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000370.jsonl.zst239 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000372.jsonl.zst338 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000374.jsonl.zst223 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000375.jsonl.zst215 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000376.jsonl.zst216 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000377.jsonl.zst208 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000379.jsonl.zst248 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000381.jsonl.zst257 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000382.jsonl.zst243 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000383.jsonl.zst260 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000384.jsonl.zst235 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000386.jsonl.zst200 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000387.jsonl.zst232 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000388.jsonl.zst270 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000389.jsonl.zst219 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000390.jsonl.zst223 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000391.jsonl.zst219 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000393.jsonl.zst191 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000394.jsonl.zst250 kB
xet
soc127__phase1_pool_shared__common_crawl__part_006__data__common_crawl-software-0016__shard_00000395.jsonl.zst245 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors