Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-10000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-10000-docs / worker_0083
21.6 GB
57,845 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000501.jsonl.zst92.3 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000600.jsonl.zst86.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000614.jsonl.zst169 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000615.jsonl.zst62.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000632.jsonl.zst30.3 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000694.jsonl.zst146 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000695.jsonl.zst48 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000735.jsonl.zst63.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000753.jsonl.zst24.3 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000794.jsonl.zst91.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000844.jsonl.zst84.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000858.jsonl.zst46.8 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000861.jsonl.zst858 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000915.jsonl.zst23.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000959.jsonl.zst9.27 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00000963.jsonl.zst101 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001025.jsonl.zst85.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001075.jsonl.zst83.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001088.jsonl.zst65.8 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001097.jsonl.zst67.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001153.jsonl.zst111 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001201.jsonl.zst50.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001222.jsonl.zst49 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001223.jsonl.zst46 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001262.jsonl.zst60.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001273.jsonl.zst15.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001340.jsonl.zst33.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001349.jsonl.zst59.8 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001354.jsonl.zst26.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001384.jsonl.zst25.2 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001406.jsonl.zst140 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001407.jsonl.zst145 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001468.jsonl.zst53.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001473.jsonl.zst143 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001505.jsonl.zst68.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001519.jsonl.zst15 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001585.jsonl.zst60.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001588.jsonl.zst58.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001622.jsonl.zst131 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001634.jsonl.zst102 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001705.jsonl.zst120 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001711.jsonl.zst291 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001713.jsonl.zst54.3 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001721.jsonl.zst18.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001742.jsonl.zst79.6 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001752.jsonl.zst119 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001831.jsonl.zst76.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001852.jsonl.zst75.2 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001864.jsonl.zst28.6 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001871.jsonl.zst14.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001872.jsonl.zst26.7 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001953.jsonl.zst25 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001965.jsonl.zst84.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001975.jsonl.zst138 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00001989.jsonl.zst72 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002007.jsonl.zst26.2 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002030.jsonl.zst141 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002078.jsonl.zst19.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002082.jsonl.zst21.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002120.jsonl.zst22.3 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002125.jsonl.zst34.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002139.jsonl.zst707 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002161.jsonl.zst114 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002188.jsonl.zst127 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002199.jsonl.zst89 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002227.jsonl.zst84.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002280.jsonl.zst112 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002283.jsonl.zst48.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002286.jsonl.zst49.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002295.jsonl.zst59.2 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002334.jsonl.zst18.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002345.jsonl.zst69.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002371.jsonl.zst14.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002396.jsonl.zst44.2 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002397.jsonl.zst346 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002434.jsonl.zst47.7 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002452.jsonl.zst36 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002463.jsonl.zst17.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002514.jsonl.zst196 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002535.jsonl.zst92.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002540.jsonl.zst25.8 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002570.jsonl.zst22.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002600.jsonl.zst28.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002615.jsonl.zst24.2 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002681.jsonl.zst118 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002693.jsonl.zst68.7 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002706.jsonl.zst62.2 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002754.jsonl.zst55.6 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002756.jsonl.zst45.6 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002772.jsonl.zst114 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002792.jsonl.zst121 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002814.jsonl.zst38.2 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002816.jsonl.zst108 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002888.jsonl.zst78.1 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002896.jsonl.zst183 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002917.jsonl.zst18.4 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002944.jsonl.zst27.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00002978.jsonl.zst67.5 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00003008.jsonl.zst41.9 kB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_007__data__olmocr_science_pdfs-health__shard_00003045.jsonl.zst80.4 kB
xet
Total size
21.6 GB
Files
57,845
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors