Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-100000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-100000-docs / worker_0092
187 GB
58,264 files
Updated 27 days ago
NameSize
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005278.jsonl.zst4.69 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005283.jsonl.zst4.37 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005310.jsonl.zst4.85 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005316.jsonl.zst5.38 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005327.jsonl.zst5.03 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005345.jsonl.zst1.96 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005354.jsonl.zst3.31 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005358.jsonl.zst6.38 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005395.jsonl.zst4.85 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005405.jsonl.zst4.64 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005414.jsonl.zst3.53 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005416.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005442.jsonl.zst5.02 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005453.jsonl.zst5.72 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005468.jsonl.zst5.42 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005485.jsonl.zst4.67 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005498.jsonl.zst3.57 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005508.jsonl.zst4.43 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005512.jsonl.zst4.9 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005534.jsonl.zst5.22 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005547.jsonl.zst5.08 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005552.jsonl.zst3.61 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005577.jsonl.zst4.02 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005588.jsonl.zst4.48 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005622.jsonl.zst3.47 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005637.jsonl.zst5.9 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005643.jsonl.zst4.41 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005648.jsonl.zst4.97 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005668.jsonl.zst3.97 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005674.jsonl.zst5.23 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005685.jsonl.zst4.38 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005719.jsonl.zst3.88 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005740.jsonl.zst4.05 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005746.jsonl.zst4.05 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005755.jsonl.zst4.36 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005767.jsonl.zst3.36 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005789.jsonl.zst3.89 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005816.jsonl.zst4.6 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005819.jsonl.zst5.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005838.jsonl.zst3.24 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005843.jsonl.zst4.93 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005863.jsonl.zst4.19 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005869.jsonl.zst3.83 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005893.jsonl.zst4.19 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005912.jsonl.zst5.74 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005921.jsonl.zst4.67 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005930.jsonl.zst4.71 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005932.jsonl.zst5.02 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005972.jsonl.zst3.89 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005984.jsonl.zst5.16 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005992.jsonl.zst5.12 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00005999.jsonl.zst4.62 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006007.jsonl.zst4.57 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006009.jsonl.zst4.89 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006047.jsonl.zst4.19 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006070.jsonl.zst4.38 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006075.jsonl.zst4.05 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006083.jsonl.zst3.97 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006085.jsonl.zst4.78 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006086.jsonl.zst5.42 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006105.jsonl.zst4.53 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006142.jsonl.zst5.19 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006149.jsonl.zst3.16 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006151.jsonl.zst5.33 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006157.jsonl.zst5.63 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006162.jsonl.zst4.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006176.jsonl.zst5.48 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006217.jsonl.zst4.21 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006220.jsonl.zst3.3 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006223.jsonl.zst4.37 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006234.jsonl.zst3.91 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006239.jsonl.zst4.66 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006264.jsonl.zst3.54 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006281.jsonl.zst5.19 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006282.jsonl.zst4.6 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006308.jsonl.zst3.72 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006313.jsonl.zst4 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006321.jsonl.zst4.55 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006347.jsonl.zst4.83 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006351.jsonl.zst4.53 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006352.jsonl.zst3.95 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006367.jsonl.zst4.63 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006384.jsonl.zst4.35 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006399.jsonl.zst3.49 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006420.jsonl.zst4.43 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006428.jsonl.zst5.39 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006431.jsonl.zst2.87 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006435.jsonl.zst5.64 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006444.jsonl.zst3.79 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006463.jsonl.zst5.05 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006488.jsonl.zst3.73 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006507.jsonl.zst4.84 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006509.jsonl.zst4.17 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006510.jsonl.zst5.76 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006527.jsonl.zst4.38 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006545.jsonl.zst4.12 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006567.jsonl.zst4.14 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006575.jsonl.zst3.43 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006577.jsonl.zst4.81 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00006604.jsonl.zst4.05 MB
xet
Total size
187 GB
Files
58,264
Last updated
Mar 25
Pre-warmed CDN
US EU US EU

Contributors