Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-100000-docs / worker_0094
187 GB
58,264 files
Updated 25 days ago
NameSize
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004331.jsonl.zst4.19 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004451.jsonl.zst3.82 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004528.jsonl.zst4.1 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004533.jsonl.zst4.1 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004574.jsonl.zst4.85 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004598.jsonl.zst3.93 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004802.jsonl.zst2.95 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004851.jsonl.zst4.11 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004936.jsonl.zst3.29 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00004962.jsonl.zst3.54 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005012.jsonl.zst5.51 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005071.jsonl.zst3.92 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005105.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005186.jsonl.zst3.74 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005203.jsonl.zst3.25 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005207.jsonl.zst2.97 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005264.jsonl.zst5.93 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005398.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005507.jsonl.zst4.72 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005511.jsonl.zst3.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005592.jsonl.zst4.56 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005620.jsonl.zst4.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005708.jsonl.zst4.1 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005720.jsonl.zst1.86 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005723.jsonl.zst1.64 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005741.jsonl.zst6.45 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005806.jsonl.zst3.55 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005824.jsonl.zst3.78 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005845.jsonl.zst3.05 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005881.jsonl.zst3.69 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005910.jsonl.zst3.5 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00005942.jsonl.zst3.43 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006003.jsonl.zst4.57 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006092.jsonl.zst3.8 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006115.jsonl.zst4.13 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006135.jsonl.zst3.25 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006196.jsonl.zst3.49 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006232.jsonl.zst3.24 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006300.jsonl.zst3.51 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006322.jsonl.zst3.78 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006329.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006386.jsonl.zst3.56 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006392.jsonl.zst5.32 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006393.jsonl.zst2.63 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006441.jsonl.zst4.15 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006547.jsonl.zst3.5 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006627.jsonl.zst3.7 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006641.jsonl.zst4.52 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006679.jsonl.zst5.4 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006726.jsonl.zst3.12 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006746.jsonl.zst4.74 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006765.jsonl.zst4.45 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006774.jsonl.zst3.67 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006799.jsonl.zst4.45 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006834.jsonl.zst5.34 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006886.jsonl.zst3.41 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00006989.jsonl.zst3.29 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007034.jsonl.zst4.53 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007053.jsonl.zst3.23 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007065.jsonl.zst4.09 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007122.jsonl.zst2.96 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007130.jsonl.zst4.76 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007148.jsonl.zst3.58 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007213.jsonl.zst3.65 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007253.jsonl.zst4.23 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007330.jsonl.zst4.98 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007338.jsonl.zst3.92 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007358.jsonl.zst4.08 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007392.jsonl.zst4.01 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007482.jsonl.zst3.48 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007570.jsonl.zst3.87 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007573.jsonl.zst2.95 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007582.jsonl.zst3.26 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007636.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007670.jsonl.zst4.1 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007745.jsonl.zst4.04 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007764.jsonl.zst5.39 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007789.jsonl.zst3.22 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007832.jsonl.zst3.41 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007869.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007915.jsonl.zst3.7 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007933.jsonl.zst4.57 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007951.jsonl.zst4.75 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00007952.jsonl.zst6.18 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008018.jsonl.zst3.92 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008047.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008063.jsonl.zst3.73 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008071.jsonl.zst3.34 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008134.jsonl.zst3.6 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008175.jsonl.zst3.02 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008178.jsonl.zst4.23 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008212.jsonl.zst3.61 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008214.jsonl.zst4.38 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008222.jsonl.zst3.63 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008239.jsonl.zst3.54 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008258.jsonl.zst7.72 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008302.jsonl.zst4.11 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008370.jsonl.zst3.93 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008430.jsonl.zst3.38 MB
xet
soc127__phase1_pool_shared__olmocr_science_pdfs__part_008__data__olmocr_science_pdfs-politics__shard_00008492.jsonl.zst3.83 MB
xet
Total size
187 GB
Files
58,264
Last updated
Mar 25
Pre-warmed CDN
US EU US EU

Contributors