Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0055
99 GB
58,246 files
Updated 2 months ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000416.jsonl.zst1.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000417.jsonl.zst1.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000418.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000419.jsonl.zst2.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000420.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000421.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000422.jsonl.zst2.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000423.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000424.jsonl.zst1.94 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000425.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000426.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000427.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000428.jsonl.zst2.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000429.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000430.jsonl.zst2.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000431.jsonl.zst2.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000432.jsonl.zst2.15 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000433.jsonl.zst2.02 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000434.jsonl.zst2.24 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000435.jsonl.zst2.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000436.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000437.jsonl.zst2.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000438.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000439.jsonl.zst2.09 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000440.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000441.jsonl.zst2.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000442.jsonl.zst1.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000443.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000444.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000445.jsonl.zst1.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000446.jsonl.zst2.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000447.jsonl.zst2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000448.jsonl.zst1.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000449.jsonl.zst1.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000450.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000451.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000452.jsonl.zst758 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000453.jsonl.zst994 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000454.jsonl.zst852 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000455.jsonl.zst849 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000456.jsonl.zst1.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000457.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000458.jsonl.zst2.12 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000459.jsonl.zst2.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000460.jsonl.zst2.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000461.jsonl.zst2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000462.jsonl.zst1.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000463.jsonl.zst2.29 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000464.jsonl.zst2.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000465.jsonl.zst2.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000466.jsonl.zst2.04 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000467.jsonl.zst2.28 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000468.jsonl.zst2.01 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000469.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000470.jsonl.zst2.2 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000471.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000472.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000473.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000474.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000475.jsonl.zst1.92 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000476.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000477.jsonl.zst1.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000478.jsonl.zst2.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000479.jsonl.zst2.06 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000480.jsonl.zst1.91 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000481.jsonl.zst1.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000482.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000483.jsonl.zst2.21 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000484.jsonl.zst2.17 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000485.jsonl.zst2.24 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000486.jsonl.zst1.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000487.jsonl.zst2.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000488.jsonl.zst1.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000489.jsonl.zst1.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000490.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000491.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000492.jsonl.zst1.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000493.jsonl.zst2.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000494.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000495.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000496.jsonl.zst1.97 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000497.jsonl.zst2.16 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000498.jsonl.zst1.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000499.jsonl.zst1.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000500.jsonl.zst2.3 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000501.jsonl.zst2.07 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000502.jsonl.zst1.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000503.jsonl.zst2.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000504.jsonl.zst1.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000505.jsonl.zst1.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000506.jsonl.zst1.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000507.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000508.jsonl.zst1.98 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000509.jsonl.zst2.25 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000510.jsonl.zst2.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000511.jsonl.zst2.1 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000512.jsonl.zst1.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000513.jsonl.zst2.11 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000514.jsonl.zst2.13 MB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0014__shard_00000515.jsonl.zst1.89 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors