Hugging Face's logo

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

Files
xet
HCAI-Lab/dolma3-6t-sample-50000-docs / worker_0009
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-0018__shard_00000024.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000025.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000026.jsonl.zst2.48 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000027.jsonl.zst2.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000028.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000029.jsonl.zst2.36 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000030.jsonl.zst2.9 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000031.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000032.jsonl.zst2.72 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000033.jsonl.zst2.42 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000034.jsonl.zst2.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000035.jsonl.zst2.85 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000036.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000037.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000038.jsonl.zst2.63 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000039.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000040.jsonl.zst2.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000041.jsonl.zst2.69 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000042.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000043.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000044.jsonl.zst2.74 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000045.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000046.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000047.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000048.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000049.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000050.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000051.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000052.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000053.jsonl.zst2.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000054.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000055.jsonl.zst2.95 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000056.jsonl.zst2.53 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000057.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000058.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000059.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000060.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000061.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000062.jsonl.zst2.61 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000063.jsonl.zst2.5 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000064.jsonl.zst2.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000065.jsonl.zst2.39 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000066.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000067.jsonl.zst2.34 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000068.jsonl.zst2.87 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000069.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000070.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000071.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000072.jsonl.zst2.77 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000073.jsonl.zst2.89 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000074.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000075.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000076.jsonl.zst2.47 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000077.jsonl.zst2.6 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000078.jsonl.zst2.59 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000079.jsonl.zst2.22 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000080.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000081.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000082.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000083.jsonl.zst2.86 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000084.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000085.jsonl.zst2.38 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000086.jsonl.zst2.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000087.jsonl.zst3.08 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000088.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000089.jsonl.zst2.49 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000090.jsonl.zst2.88 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000091.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000092.jsonl.zst2.58 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000093.jsonl.zst2.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000094.jsonl.zst2.93 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000095.jsonl.zst2.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000096.jsonl.zst2.83 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000097.jsonl.zst2.82 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000098.jsonl.zst2.43 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000099.jsonl.zst2.68 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000100.jsonl.zst2.62 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000101.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000102.jsonl.zst2.45 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000103.jsonl.zst2.75 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000104.jsonl.zst2.7 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000105.jsonl.zst2.84 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000106.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000107.jsonl.zst2.46 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000108.jsonl.zst2.79 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000109.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000110.jsonl.zst2.31 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000111.jsonl.zst2.67 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000112.jsonl.zst2.57 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000113.jsonl.zst2.71 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000114.jsonl.zst2.56 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000115.jsonl.zst2.51 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000116.jsonl.zst2.54 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000117.jsonl.zst2.78 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000118.jsonl.zst2.52 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000119.jsonl.zst2.65 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000120.jsonl.zst2.33 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000121.jsonl.zst2.76 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000122.jsonl.zst2.64 MB
xet
soc127__phase1_pool_shared__common_crawl__part_000__data__common_crawl-electronics_and_hardware-0018__shard_00000123.jsonl.zst2.73 MB
xet
Total size
99 GB
Files
58,246
Last updated
Mar 23
Pre-warmed CDN
US EU US EU

Contributors