| { | |
| "name": "destroyer-1b pretrain corpus pack", | |
| "created": "2026-08-05T15:49:29.122013Z", | |
| "tokenizer": { | |
| "id": "HuggingFaceTB/SmolLM2-1.7B", | |
| "sha256_vocab": "e6d44ded9564218b", | |
| "vocab_size": 49152 | |
| }, | |
| "schema": { | |
| "input_ids": "list<int32>", | |
| "labels": "list<int32>" | |
| }, | |
| "eos_convention": "trailing <|endoftext|> (id 0) per document", | |
| "shard_naming": "data-XXXXX-of-YYYYY.arrow (~62M tokens each)", | |
| "corpora": [ | |
| { | |
| "dataset": "HuggingFaceTB/smollm-corpus", | |
| "config": "cosmopedia-v2", | |
| "split": "train", | |
| "task": "cosmo2-a", | |
| "bucket_prefix": "cosmo2", | |
| "license": "Apache-2.0 (synthetic)", | |
| "source_note": "CosmoPedia v2 subset of smollm-corpus (the 'Cosmo2' corpus)", | |
| "ranges": [ | |
| { | |
| "from_file": 0, | |
| "to_file": 21 | |
| } | |
| ], | |
| "shards": 90, | |
| "rows": 7525780, | |
| "tokens": 5420181378, | |
| "bytes": 43422833360, | |
| "files": [ | |
| "data-00000-of-00093.arrow", | |
| "data-00001-of-00093.arrow", | |
| "data-00002-of-00093.arrow", | |
| "data-00003-of-00093.arrow", | |
| "data-00004-of-00093.arrow", | |
| "data-00005-of-00093.arrow", | |
| "data-00006-of-00093.arrow", | |
| "data-00007-of-00093.arrow", | |
| "data-00008-of-00093.arrow", | |
| "data-00009-of-00093.arrow", | |
| "data-00010-of-00093.arrow", | |
| "data-00011-of-00093.arrow", | |
| "data-00012-of-00093.arrow", | |
| "data-00013-of-00093.arrow", | |
| "data-00014-of-00093.arrow", | |
| "data-00015-of-00093.arrow", | |
| "data-00016-of-00093.arrow", | |
| "data-00017-of-00093.arrow", | |
| "data-00018-of-00093.arrow", | |
| "data-00019-of-00093.arrow", | |
| "data-00020-of-00093.arrow", | |
| "data-00021-of-00093.arrow", | |
| "data-00022-of-00093.arrow", | |
| "data-00023-of-00093.arrow", | |
| "data-00024-of-00093.arrow", | |
| "data-00025-of-00093.arrow", | |
| "data-00026-of-00093.arrow", | |
| "data-00027-of-00093.arrow", | |
| "data-00028-of-00093.arrow", | |
| "data-00029-of-00093.arrow", | |
| "data-00030-of-00093.arrow", | |
| "data-00031-of-00093.arrow", | |
| "data-00032-of-00093.arrow", | |
| "data-00033-of-00093.arrow", | |
| "data-00034-of-00093.arrow", | |
| "data-00035-of-00093.arrow", | |
| "data-00036-of-00093.arrow", | |
| "data-00037-of-00093.arrow", | |
| "data-00038-of-00093.arrow", | |
| "data-00039-of-00093.arrow", | |
| "data-00040-of-00093.arrow", | |
| "data-00041-of-00093.arrow", | |
| "data-00042-of-00093.arrow", | |
| "data-00043-of-00093.arrow", | |
| "data-00044-of-00093.arrow", | |
| "data-00045-of-00093.arrow", | |
| "data-00046-of-00093.arrow", | |
| "data-00047-of-00093.arrow", | |
| "data-00048-of-00093.arrow", | |
| "data-00049-of-00093.arrow", | |
| "data-00050-of-00093.arrow", | |
| "data-00051-of-00093.arrow", | |
| "data-00052-of-00093.arrow", | |
| "data-00053-of-00093.arrow", | |
| "data-00054-of-00093.arrow", | |
| "data-00055-of-00093.arrow", | |
| "data-00056-of-00093.arrow", | |
| "data-00057-of-00093.arrow", | |
| "data-00058-of-00093.arrow", | |
| "data-00059-of-00093.arrow", | |
| "data-00060-of-00093.arrow", | |
| "data-00061-of-00093.arrow", | |
| "data-00062-of-00093.arrow", | |
| "data-00063-of-00093.arrow", | |
| "data-00064-of-00093.arrow", | |
| "data-00065-of-00093.arrow", | |
| "data-00066-of-00093.arrow", | |
| "data-00067-of-00093.arrow", | |
| "data-00068-of-00093.arrow", | |
| "data-00069-of-00093.arrow", | |
| "data-00070-of-00093.arrow", | |
| "data-00071-of-00093.arrow", | |
| "data-00072-of-00093.arrow", | |
| "data-00073-of-00093.arrow", | |
| "data-00074-of-00093.arrow", | |
| "data-00075-of-00093.arrow", | |
| "data-00076-of-00093.arrow", | |
| "data-00077-of-00093.arrow", | |
| "data-00078-of-00093.arrow", | |
| "data-00079-of-00093.arrow", | |
| "data-00080-of-00093.arrow", | |
| "data-00081-of-00093.arrow", | |
| "data-00082-of-00093.arrow", | |
| "data-00083-of-00093.arrow", | |
| "data-00084-of-00093.arrow", | |
| "data-00085-of-00093.arrow", | |
| "data-00086-of-00093.arrow", | |
| "data-00087-of-00093.arrow", | |
| "data-00088-of-00093.arrow", | |
| "data-00089-of-00093.arrow" | |
| ], | |
| "created": "2026-08-05T15:49:28.082247Z" | |
| }, | |
| { | |
| "dataset": "HuggingFaceTB/smollm-corpus", | |
| "config": "cosmopedia-v2", | |
| "split": "train", | |
| "task": "cosmo2-b", | |
| "bucket_prefix": "cosmo2", | |
| "license": "Apache-2.0 (synthetic)", | |
| "source_note": "CosmoPedia v2 files 21-26, continuation of cosmo2-a (non-overlapping)", | |
| "ranges": [ | |
| { | |
| "from_file": 21, | |
| "to_file": 27 | |
| } | |
| ], | |
| "shards": 31, | |
| "rows": 2343758, | |
| "tokens": 1688212214, | |
| "bytes": 13524815120, | |
| "files": [ | |
| "data-00090-of-00028.arrow", | |
| "data-00091-of-00028.arrow", | |
| "data-00092-of-00028.arrow", | |
| "data-00093-of-00028.arrow", | |
| "data-00094-of-00028.arrow", | |
| "data-00095-of-00028.arrow", | |
| "data-00096-of-00028.arrow", | |
| "data-00097-of-00028.arrow", | |
| "data-00098-of-00028.arrow", | |
| "data-00099-of-00028.arrow", | |
| "data-00100-of-00028.arrow", | |
| "data-00101-of-00028.arrow", | |
| "data-00102-of-00028.arrow", | |
| "data-00103-of-00028.arrow", | |
| "data-00104-of-00028.arrow", | |
| "data-00105-of-00028.arrow", | |
| "data-00106-of-00028.arrow", | |
| "data-00107-of-00028.arrow", | |
| "data-00108-of-00028.arrow", | |
| "data-00109-of-00028.arrow", | |
| "data-00110-of-00028.arrow", | |
| "data-00111-of-00028.arrow", | |
| "data-00112-of-00028.arrow", | |
| "data-00113-of-00028.arrow", | |
| "data-00114-of-00028.arrow", | |
| "data-00115-of-00028.arrow", | |
| "data-00116-of-00028.arrow", | |
| "data-00117-of-00028.arrow", | |
| "data-00118-of-00028.arrow", | |
| "data-00119-of-00028.arrow", | |
| "data-00120-of-00028.arrow" | |
| ], | |
| "created": "2026-08-05T15:49:28.082385Z" | |
| }, | |
| { | |
| "dataset": "HuggingFaceTB/finemath", | |
| "config": "finemath-3plus", | |
| "split": "train", | |
| "task": "finemath-a", | |
| "bucket_prefix": "finemath", | |
| "license": "ODC-BY-1.0", | |
| "source_note": "FineMath 3+ (math-filtered web), first 11 parquet files", | |
| "ranges": [ | |
| { | |
| "from_file": 0, | |
| "to_file": 11 | |
| } | |
| ], | |
| "shards": 58, | |
| "rows": 1839552, | |
| "tokens": 3444339592, | |
| "bytes": 27569734192, | |
| "files": [ | |
| "data-00000-of-00056.arrow", | |
| "data-00001-of-00056.arrow", | |
| "data-00002-of-00056.arrow", | |
| "data-00003-of-00056.arrow", | |
| "data-00004-of-00056.arrow", | |
| "data-00005-of-00056.arrow", | |
| "data-00006-of-00056.arrow", | |
| "data-00007-of-00056.arrow", | |
| "data-00008-of-00056.arrow", | |
| "data-00009-of-00056.arrow", | |
| "data-00010-of-00056.arrow", | |
| "data-00011-of-00056.arrow", | |
| "data-00012-of-00056.arrow", | |
| "data-00013-of-00056.arrow", | |
| "data-00014-of-00056.arrow", | |
| "data-00015-of-00056.arrow", | |
| "data-00016-of-00056.arrow", | |
| "data-00017-of-00056.arrow", | |
| "data-00018-of-00056.arrow", | |
| "data-00019-of-00056.arrow", | |
| "data-00020-of-00056.arrow", | |
| "data-00021-of-00056.arrow", | |
| "data-00022-of-00056.arrow", | |
| "data-00023-of-00056.arrow", | |
| "data-00024-of-00056.arrow", | |
| "data-00025-of-00056.arrow", | |
| "data-00026-of-00056.arrow", | |
| "data-00027-of-00056.arrow", | |
| "data-00028-of-00056.arrow", | |
| "data-00029-of-00056.arrow", | |
| "data-00030-of-00056.arrow", | |
| "data-00031-of-00056.arrow", | |
| "data-00032-of-00056.arrow", | |
| "data-00033-of-00056.arrow", | |
| "data-00034-of-00056.arrow", | |
| "data-00035-of-00056.arrow", | |
| "data-00036-of-00056.arrow", | |
| "data-00037-of-00056.arrow", | |
| "data-00038-of-00056.arrow", | |
| "data-00039-of-00056.arrow", | |
| "data-00040-of-00056.arrow", | |
| "data-00041-of-00056.arrow", | |
| "data-00042-of-00056.arrow", | |
| "data-00043-of-00056.arrow", | |
| "data-00044-of-00056.arrow", | |
| "data-00045-of-00056.arrow", | |
| "data-00046-of-00056.arrow", | |
| "data-00047-of-00056.arrow", | |
| "data-00048-of-00056.arrow", | |
| "data-00049-of-00056.arrow", | |
| "data-00050-of-00056.arrow", | |
| "data-00051-of-00056.arrow", | |
| "data-00052-of-00056.arrow", | |
| "data-00053-of-00056.arrow", | |
| "data-00054-of-00056.arrow", | |
| "data-00055-of-00056.arrow", | |
| "data-00056-of-00056.arrow", | |
| "data-00057-of-00056.arrow" | |
| ], | |
| "created": "2026-08-05T15:49:28.082529Z" | |
| }, | |
| { | |
| "dataset": "HuggingFaceFW/fineweb-edu", | |
| "config": "data", | |
| "split": "train", | |
| "task": "fineweb-edu-a", | |
| "bucket_prefix": "fineweb-edu", | |
| "license": "ODC-BY-1.0", | |
| "source_note": "FineWeb-Edu (educational filter of FineWeb), first 24 parquet files of data/", | |
| "ranges": [ | |
| { | |
| "from_file": 0, | |
| "to_file": 24 | |
| } | |
| ], | |
| "shards": 164, | |
| "rows": 9430862, | |
| "tokens": 10039630733, | |
| "bytes": 80393984288, | |
| "files": [ | |
| "data-00000-of-00186.arrow", | |
| "data-00001-of-00186.arrow", | |
| "data-00002-of-00186.arrow", | |
| "data-00003-of-00186.arrow", | |
| "data-00004-of-00186.arrow", | |
| "data-00005-of-00186.arrow", | |
| "data-00006-of-00186.arrow", | |
| "data-00007-of-00186.arrow", | |
| "data-00008-of-00186.arrow", | |
| "data-00009-of-00186.arrow", | |
| "data-00010-of-00186.arrow", | |
| "data-00011-of-00186.arrow", | |
| "data-00012-of-00186.arrow", | |
| "data-00013-of-00186.arrow", | |
| "data-00014-of-00186.arrow", | |
| "data-00015-of-00186.arrow", | |
| "data-00016-of-00186.arrow", | |
| "data-00017-of-00186.arrow", | |
| "data-00018-of-00186.arrow", | |
| "data-00019-of-00186.arrow", | |
| "data-00020-of-00186.arrow", | |
| "data-00021-of-00186.arrow", | |
| "data-00022-of-00186.arrow", | |
| "data-00023-of-00186.arrow", | |
| "data-00024-of-00186.arrow", | |
| "data-00025-of-00186.arrow", | |
| "data-00026-of-00186.arrow", | |
| "data-00027-of-00186.arrow", | |
| "data-00028-of-00186.arrow", | |
| "data-00029-of-00186.arrow", | |
| "data-00030-of-00186.arrow", | |
| "data-00031-of-00186.arrow", | |
| "data-00032-of-00186.arrow", | |
| "data-00033-of-00186.arrow", | |
| "data-00034-of-00186.arrow", | |
| "data-00035-of-00186.arrow", | |
| "data-00036-of-00186.arrow", | |
| "data-00037-of-00186.arrow", | |
| "data-00038-of-00186.arrow", | |
| "data-00039-of-00186.arrow", | |
| "data-00040-of-00186.arrow", | |
| "data-00041-of-00186.arrow", | |
| "data-00042-of-00186.arrow", | |
| "data-00043-of-00186.arrow", | |
| "data-00044-of-00186.arrow", | |
| "data-00045-of-00186.arrow", | |
| "data-00046-of-00186.arrow", | |
| "data-00047-of-00186.arrow", | |
| "data-00048-of-00186.arrow", | |
| "data-00049-of-00186.arrow", | |
| "data-00050-of-00186.arrow", | |
| "data-00051-of-00186.arrow", | |
| "data-00052-of-00186.arrow", | |
| "data-00053-of-00186.arrow", | |
| "data-00054-of-00186.arrow", | |
| "data-00055-of-00186.arrow", | |
| "data-00056-of-00186.arrow", | |
| "data-00057-of-00186.arrow", | |
| "data-00058-of-00186.arrow", | |
| "data-00059-of-00186.arrow", | |
| "data-00060-of-00186.arrow", | |
| "data-00061-of-00186.arrow", | |
| "data-00062-of-00186.arrow", | |
| "data-00063-of-00186.arrow", | |
| "data-00064-of-00186.arrow", | |
| "data-00065-of-00186.arrow", | |
| "data-00066-of-00186.arrow", | |
| "data-00067-of-00186.arrow", | |
| "data-00068-of-00186.arrow", | |
| "data-00069-of-00186.arrow", | |
| "data-00070-of-00186.arrow", | |
| "data-00071-of-00186.arrow", | |
| "data-00072-of-00186.arrow", | |
| "data-00073-of-00186.arrow", | |
| "data-00074-of-00186.arrow", | |
| "data-00075-of-00186.arrow", | |
| "data-00076-of-00186.arrow", | |
| "data-00077-of-00186.arrow", | |
| "data-00078-of-00186.arrow", | |
| "data-00079-of-00186.arrow", | |
| "data-00080-of-00186.arrow", | |
| "data-00081-of-00186.arrow", | |
| "data-00082-of-00186.arrow", | |
| "data-00083-of-00186.arrow", | |
| "data-00084-of-00186.arrow", | |
| "data-00085-of-00186.arrow", | |
| "data-00086-of-00186.arrow", | |
| "data-00087-of-00186.arrow", | |
| "data-00088-of-00186.arrow", | |
| "data-00089-of-00186.arrow", | |
| "data-00090-of-00186.arrow", | |
| "data-00091-of-00186.arrow", | |
| "data-00092-of-00186.arrow", | |
| "data-00093-of-00186.arrow", | |
| "data-00094-of-00186.arrow", | |
| "data-00095-of-00186.arrow", | |
| "data-00096-of-00186.arrow", | |
| "data-00097-of-00186.arrow", | |
| "data-00098-of-00186.arrow", | |
| "data-00099-of-00186.arrow", | |
| "data-00100-of-00186.arrow", | |
| "data-00101-of-00186.arrow", | |
| "data-00102-of-00186.arrow", | |
| "data-00103-of-00186.arrow", | |
| "data-00104-of-00186.arrow", | |
| "data-00105-of-00186.arrow", | |
| "data-00106-of-00186.arrow", | |
| "data-00107-of-00186.arrow", | |
| "data-00108-of-00186.arrow", | |
| "data-00109-of-00186.arrow", | |
| "data-00110-of-00186.arrow", | |
| "data-00111-of-00186.arrow", | |
| "data-00112-of-00186.arrow", | |
| "data-00113-of-00186.arrow", | |
| "data-00114-of-00186.arrow", | |
| "data-00115-of-00186.arrow", | |
| "data-00116-of-00186.arrow", | |
| "data-00117-of-00186.arrow", | |
| "data-00118-of-00186.arrow", | |
| "data-00119-of-00186.arrow", | |
| "data-00120-of-00186.arrow", | |
| "data-00121-of-00186.arrow", | |
| "data-00122-of-00186.arrow", | |
| "data-00123-of-00186.arrow", | |
| "data-00124-of-00186.arrow", | |
| "data-00125-of-00186.arrow", | |
| "data-00126-of-00186.arrow", | |
| "data-00127-of-00186.arrow", | |
| "data-00128-of-00186.arrow", | |
| "data-00129-of-00186.arrow", | |
| "data-00130-of-00186.arrow", | |
| "data-00131-of-00186.arrow", | |
| "data-00132-of-00186.arrow", | |
| "data-00133-of-00186.arrow", | |
| "data-00134-of-00186.arrow", | |
| "data-00135-of-00186.arrow", | |
| "data-00136-of-00186.arrow", | |
| "data-00137-of-00186.arrow", | |
| "data-00138-of-00186.arrow", | |
| "data-00139-of-00186.arrow", | |
| "data-00140-of-00186.arrow", | |
| "data-00141-of-00186.arrow", | |
| "data-00142-of-00186.arrow", | |
| "data-00143-of-00186.arrow", | |
| "data-00144-of-00186.arrow", | |
| "data-00145-of-00186.arrow", | |
| "data-00146-of-00186.arrow", | |
| "data-00147-of-00186.arrow", | |
| "data-00148-of-00186.arrow", | |
| "data-00149-of-00186.arrow", | |
| "data-00150-of-00186.arrow", | |
| "data-00151-of-00186.arrow", | |
| "data-00152-of-00186.arrow", | |
| "data-00153-of-00186.arrow", | |
| "data-00154-of-00186.arrow", | |
| "data-00155-of-00186.arrow", | |
| "data-00156-of-00186.arrow", | |
| "data-00157-of-00186.arrow", | |
| "data-00158-of-00186.arrow", | |
| "data-00159-of-00186.arrow", | |
| "data-00160-of-00186.arrow", | |
| "data-00161-of-00186.arrow", | |
| "data-00162-of-00186.arrow", | |
| "data-00163-of-00186.arrow" | |
| ], | |
| "created": "2026-08-05T15:49:28.082969Z" | |
| }, | |
| { | |
| "dataset": "HuggingFaceTB/smollm-corpus", | |
| "config": "python-edu", | |
| "split": "train", | |
| "task": "python-edu-a", | |
| "bucket_prefix": "python-edu", | |
| "license": "Apache-2.0", | |
| "source_note": "Python-Edu subset of smollm-corpus, first parquet file", | |
| "ranges": [ | |
| { | |
| "from_file": 0, | |
| "to_file": 1 | |
| } | |
| ], | |
| "shards": 5, | |
| "rows": 376289, | |
| "tokens": 270931486, | |
| "bytes": 2170521184, | |
| "files": [ | |
| "data-00000-of-00038.arrow", | |
| "data-00001-of-00038.arrow", | |
| "data-00002-of-00038.arrow", | |
| "data-00003-of-00038.arrow", | |
| "data-00004-of-00038.arrow" | |
| ], | |
| "created": "2026-08-05T15:49:28.083077Z" | |
| } | |
| ], | |
| "total_tokens": 20863295403, | |
| "total_shards": 348 | |
| } |
Xet Storage Details
- Size:
- 16.2 kB
- Xet hash:
- 9ba7e5029afa556445787e8749bcc78f9c64e4835a42d63f8a1c67abefe19e55
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.