Hugging Face's logo

Buckets:
HCAI-Lab
/
dolma3-6t-sample-5000-docs

Files
xet
HCAI-Lab/dolma3-6t-sample-5000-docs / worker_0064
11.1 GB
56,043 files
Updated about 1 month ago
NameSize
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000958.jsonl.zst204 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000959.jsonl.zst146 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000960.jsonl.zst111 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000961.jsonl.zst114 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000962.jsonl.zst128 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000963.jsonl.zst148 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000964.jsonl.zst214 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000965.jsonl.zst161 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000966.jsonl.zst136 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000967.jsonl.zst163 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000968.jsonl.zst74.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0017__shard_00000969.jsonl.zst12.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000000.jsonl.zst129 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000001.jsonl.zst86.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000002.jsonl.zst109 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000003.jsonl.zst191 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000004.jsonl.zst149 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000005.jsonl.zst107 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000006.jsonl.zst205 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000007.jsonl.zst102 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000008.jsonl.zst131 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000009.jsonl.zst374 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000010.jsonl.zst309 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000011.jsonl.zst112 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000012.jsonl.zst94.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000013.jsonl.zst134 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000014.jsonl.zst222 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000015.jsonl.zst128 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000016.jsonl.zst126 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000017.jsonl.zst170 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000018.jsonl.zst124 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000019.jsonl.zst130 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000020.jsonl.zst197 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000021.jsonl.zst108 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000022.jsonl.zst167 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000023.jsonl.zst124 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000024.jsonl.zst201 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000025.jsonl.zst110 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000026.jsonl.zst220 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000027.jsonl.zst96.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000028.jsonl.zst59.7 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000031.jsonl.zst42.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000032.jsonl.zst108 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000033.jsonl.zst77.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000034.jsonl.zst156 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000035.jsonl.zst92.6 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000036.jsonl.zst141 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000037.jsonl.zst200 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000038.jsonl.zst75.5 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000039.jsonl.zst115 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000040.jsonl.zst202 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000041.jsonl.zst131 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000042.jsonl.zst103 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000043.jsonl.zst186 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000044.jsonl.zst169 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000045.jsonl.zst116 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000046.jsonl.zst115 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000047.jsonl.zst223 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000048.jsonl.zst94.9 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000049.jsonl.zst138 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000050.jsonl.zst121 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000051.jsonl.zst135 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000052.jsonl.zst188 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000053.jsonl.zst111 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000054.jsonl.zst134 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000055.jsonl.zst108 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000056.jsonl.zst195 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000057.jsonl.zst173 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000058.jsonl.zst140 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000059.jsonl.zst112 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000060.jsonl.zst206 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000061.jsonl.zst168 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000062.jsonl.zst121 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000063.jsonl.zst143 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000064.jsonl.zst172 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000065.jsonl.zst179 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000066.jsonl.zst164 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000067.jsonl.zst152 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000068.jsonl.zst210 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000069.jsonl.zst205 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000070.jsonl.zst106 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000071.jsonl.zst83.1 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000072.jsonl.zst208 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000073.jsonl.zst167 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000074.jsonl.zst210 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000075.jsonl.zst104 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000076.jsonl.zst171 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000077.jsonl.zst158 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000078.jsonl.zst131 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000079.jsonl.zst360 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000080.jsonl.zst138 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000081.jsonl.zst158 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000082.jsonl.zst166 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000083.jsonl.zst127 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000084.jsonl.zst149 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000085.jsonl.zst111 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000086.jsonl.zst146 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000087.jsonl.zst172 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000088.jsonl.zst116 kB
xet
soc127__phase1_pool_shared__common_crawl__part_005__data__common_crawl-science_math_and_technology-0018__shard_00000089.jsonl.zst188 kB
xet
Total size
11.1 GB
Files
56,043
Last updated
Mar 24
Pre-warmed CDN
US EU US EU

Contributors