Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0008
99 GB
58,246 files
Updated 4 months ago
Name
Size
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0015__shard_00000326.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0015__shard_00000361.jsonl.zst2.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000004.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000006.jsonl.zst2.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000009.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000011.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000014.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000015.jsonl.zst2.41 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000016.jsonl.zst2.8 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000019.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000021.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000023.jsonl.zst2.19 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000025.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000035.jsonl.zst2.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000045.jsonl.zst2.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000054.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000057.jsonl.zst2.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000060.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000061.jsonl.zst2.27 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000063.jsonl.zst2.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000067.jsonl.zst2.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000068.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000073.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000074.jsonl.zst2.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000086.jsonl.zst2.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000090.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000092.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000095.jsonl.zst2.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000097.jsonl.zst2.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000098.jsonl.zst2.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000099.jsonl.zst2.4 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000100.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000103.jsonl.zst2.37 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000104.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000105.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000114.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000115.jsonl.zst2.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000122.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000123.jsonl.zst2.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000129.jsonl.zst2.32 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000131.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000134.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000137.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000145.jsonl.zst2.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000149.jsonl.zst2.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000167.jsonl.zst2.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000168.jsonl.zst2.44 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000174.jsonl.zst2.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000175.jsonl.zst2.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000180.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000187.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000188.jsonl.zst2.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000204.jsonl.zst2.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000205.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000207.jsonl.zst2.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000221.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000224.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000227.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000230.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000234.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000239.jsonl.zst2.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000248.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000255.jsonl.zst2.55 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000258.jsonl.zst2.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000260.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000267.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000268.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000269.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000270.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000276.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000278.jsonl.zst2.26 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000280.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000282.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000283.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000289.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000291.jsonl.zst2.66 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000295.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000299.jsonl.zst2.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000307.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000308.jsonl.zst2.99 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000309.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000316.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000332.jsonl.zst2.35 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000333.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000336.jsonl.zst2.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000339.jsonl.zst2.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000341.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000343.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000350.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000351.jsonl.zst2.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000352.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000353.jsonl.zst2.73 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000354.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000356.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000357.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000358.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000364.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000373.jsonl.zst2.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000378.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0016__shard_00000382.jsonl.zst2.55 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors