Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-500-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-500-docs / worker_0038
1.22 GB
43,129 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000456.jsonl.zst224 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000457.jsonl.zst5.35 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000458.jsonl.zst56.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000459.jsonl.zst18.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000460.jsonl.zst12 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000461.jsonl.zst74.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000462.jsonl.zst2.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000463.jsonl.zst44.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000464.jsonl.zst7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000465.jsonl.zst5.94 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000466.jsonl.zst13.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000467.jsonl.zst20.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000468.jsonl.zst18.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000469.jsonl.zst16.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000470.jsonl.zst14.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000471.jsonl.zst3.49 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000472.jsonl.zst24.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000473.jsonl.zst7.24 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000474.jsonl.zst27.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000475.jsonl.zst26.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000476.jsonl.zst23.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000477.jsonl.zst15.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000478.jsonl.zst6.24 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000479.jsonl.zst38.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000480.jsonl.zst24.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000481.jsonl.zst31.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000482.jsonl.zst15.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000483.jsonl.zst21.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000484.jsonl.zst15.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000485.jsonl.zst48.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000486.jsonl.zst62.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000487.jsonl.zst36.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000488.jsonl.zst31.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000489.jsonl.zst22.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000490.jsonl.zst37.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000491.jsonl.zst9.47 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000492.jsonl.zst16.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000493.jsonl.zst26.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000494.jsonl.zst52.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000495.jsonl.zst19.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000496.jsonl.zst20.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000497.jsonl.zst25.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000498.jsonl.zst22.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000499.jsonl.zst44.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000500.jsonl.zst21.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000501.jsonl.zst20.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000502.jsonl.zst15.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000503.jsonl.zst13.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000504.jsonl.zst20 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000505.jsonl.zst40.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000506.jsonl.zst21.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000507.jsonl.zst22.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000508.jsonl.zst6.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000509.jsonl.zst6.04 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000510.jsonl.zst27.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000511.jsonl.zst39.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000512.jsonl.zst12.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000513.jsonl.zst35.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000514.jsonl.zst13.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000515.jsonl.zst18.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000516.jsonl.zst53.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000517.jsonl.zst10.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000518.jsonl.zst42.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000519.jsonl.zst14.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000520.jsonl.zst27 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000521.jsonl.zst67.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000522.jsonl.zst10.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000523.jsonl.zst19.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000524.jsonl.zst13 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000525.jsonl.zst27.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000526.jsonl.zst18.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000527.jsonl.zst32.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000528.jsonl.zst29.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000529.jsonl.zst12.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000530.jsonl.zst17.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000531.jsonl.zst23.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000532.jsonl.zst32.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000533.jsonl.zst42.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000534.jsonl.zst88.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000535.jsonl.zst46.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000536.jsonl.zst17.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000537.jsonl.zst39.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000538.jsonl.zst17 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000539.jsonl.zst11.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000540.jsonl.zst5.55 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000541.jsonl.zst11.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000542.jsonl.zst19.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000543.jsonl.zst22.4 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000544.jsonl.zst13.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000545.jsonl.zst26.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000546.jsonl.zst47.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000547.jsonl.zst13.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000548.jsonl.zst8.39 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000549.jsonl.zst19.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000550.jsonl.zst17.3 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000551.jsonl.zst18.8 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000552.jsonl.zst88.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000553.jsonl.zst17.2 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000554.jsonl.zst15.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_002__data__common_crawl-games-0018__shard_00000555.jsonl.zst35.5 kB
xet
Total size
1.22 GB
Files
43,129
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors