Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-50000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0049
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000472.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000473.jsonl.zst2.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000474.jsonl.zst2.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000475.jsonl.zst2.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000477.jsonl.zst1.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000478.jsonl.zst1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000479.jsonl.zst1.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000481.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000482.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000483.jsonl.zst3.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000484.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000485.jsonl.zst2.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000486.jsonl.zst2.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000487.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000488.jsonl.zst2.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000489.jsonl.zst2.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000490.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000491.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000492.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000493.jsonl.zst2.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000494.jsonl.zst2.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000495.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000496.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000497.jsonl.zst2.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000498.jsonl.zst2.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000499.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000500.jsonl.zst2.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000501.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000502.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000503.jsonl.zst2.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000504.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000505.jsonl.zst2.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000506.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000507.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000508.jsonl.zst2.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000509.jsonl.zst2.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000510.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000511.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000512.jsonl.zst2.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000513.jsonl.zst2.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000514.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000515.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000516.jsonl.zst2.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000517.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000518.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000519.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000520.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000521.jsonl.zst2.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000522.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000523.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000524.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000525.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000526.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000527.jsonl.zst3.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000528.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000529.jsonl.zst2.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000530.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000531.jsonl.zst2.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000532.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000533.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000534.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000535.jsonl.zst2.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000536.jsonl.zst2.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000537.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000538.jsonl.zst2.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000539.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000540.jsonl.zst2.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000541.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000542.jsonl.zst950 kB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000543.jsonl.zst2.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000544.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000545.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000546.jsonl.zst2.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000547.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000548.jsonl.zst2.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000549.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000550.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000551.jsonl.zst2.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000552.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000553.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000554.jsonl.zst2.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000555.jsonl.zst2.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000556.jsonl.zst2.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000557.jsonl.zst2.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000558.jsonl.zst2.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000559.jsonl.zst2.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000560.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000561.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000562.jsonl.zst2.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000563.jsonl.zst2.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000564.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000565.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000566.jsonl.zst2.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000567.jsonl.zst2.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000568.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000569.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000570.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000571.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000572.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_004__data__common_crawl-politics-0019__shard_00000573.jsonl.zst2.59 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors