Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0093
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00010991.jsonl.zst3.33 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00010999.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011011.jsonl.zst3.34 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011012.jsonl.zst2.09 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011029.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011044.jsonl.zst2.26 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011059.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011070.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011073.jsonl.zst2.47 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011081.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011100.jsonl.zst2.29 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011111.jsonl.zst2.8 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011129.jsonl.zst2.17 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011133.jsonl.zst2.91 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011135.jsonl.zst3.6 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011157.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011164.jsonl.zst3.19 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011187.jsonl.zst2.39 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011190.jsonl.zst2.82 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011195.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011216.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011221.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011246.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011252.jsonl.zst2.98 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011258.jsonl.zst2.35 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011275.jsonl.zst2.77 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011281.jsonl.zst3.07 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011300.jsonl.zst3.55 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011307.jsonl.zst3.28 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011313.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011329.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011339.jsonl.zst3.72 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011356.jsonl.zst2.29 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011376.jsonl.zst2.44 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011377.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011385.jsonl.zst2.14 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011395.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011414.jsonl.zst2.88 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011432.jsonl.zst3.39 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011436.jsonl.zst3.21 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011442.jsonl.zst3.28 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011454.jsonl.zst1.77 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011475.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011487.jsonl.zst2.32 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011491.jsonl.zst3.43 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011495.jsonl.zst2.8 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011513.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011530.jsonl.zst2.54 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011544.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011547.jsonl.zst3.01 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011550.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011568.jsonl.zst3.26 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011585.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011600.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011603.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011605.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011627.jsonl.zst2.69 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011640.jsonl.zst2.36 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011655.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011659.jsonl.zst2.63 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011665.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011687.jsonl.zst2.17 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011698.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011712.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011716.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011722.jsonl.zst3.84 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011745.jsonl.zst3.15 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011751.jsonl.zst2.26 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011766.jsonl.zst2.69 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011774.jsonl.zst2.17 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011782.jsonl.zst2.14 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011795.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011807.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011821.jsonl.zst2.54 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011831.jsonl.zst2.87 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011841.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011855.jsonl.zst2.53 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011858.jsonl.zst1.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011890.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011900.jsonl.zst2.05 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011910.jsonl.zst1.39 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011911.jsonl.zst2.18 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011927.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011945.jsonl.zst2.87 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011954.jsonl.zst1.63 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011968.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011970.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00011980.jsonl.zst3.19 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012003.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012013.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012024.jsonl.zst2.73 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012025.jsonl.zst5.09 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012035.jsonl.zst3.09 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012063.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012068.jsonl.zst3.3 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012079.jsonl.zst3.21 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012081.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012091.jsonl.zst2.14 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012118.jsonl.zst2.32 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-industrial__shard_00012129.jsonl.zst2.84 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors