| {"files": ["part13/sangraha-xl-san__sh0/shard_00001.bin", "part13/sangraha-xl-san__sh1/shard_00001.bin", "part13/sangraha-xl-san__sh2/shard_00001.bin", "part13/sangraha-xl-san__sh3/shard_00002.bin", "part13/sangraha-xl-snd__sh0/shard_00001.bin", "part13/sangraha-xl-snd__sh1/shard_00001.bin", "part13/sangraha-xl-snd__sh2/shard_00001.bin", "part17/scripture-sanskrit-mono__sh1/shard_00001.bin", "part22/reason-numinamath__sh0/shard_00001.bin", "part22/reason-numinamath__sh1/shard_00001.bin", "part22/reason-openorca__sh0/shard_00001.bin", "part22/reason-openorca__sh1/shard_00001.bin", "part4/align-bitext-bn/shard_00001.bin", "part4/align-bitext-gu/shard_00001.bin", "part4/align-bitext-hi/shard_00001.bin", "part4/align-bitext-kn/shard_00001.bin", "part4/align-bitext-ml/shard_00001.bin", "part4/align-bitext-mr/shard_00001.bin", "part4/align-bitext-pa/shard_00001.bin", "part12/sangraha-xl-guj__sh1/shard_00002.bin", "part12/sangraha-xl-guj__sh2/shard_00002.bin", "part12/sangraha-xl-guj__sh3/shard_00003.bin", "part12/sangraha-xl-hin__sh0/shard_00002.bin", "part12/sangraha-xl-hin__sh1/shard_00002.bin", "part12/sangraha-xl-hin__sh2/shard_00002.bin", "part12/sangraha-xl-hin__sh3/shard_00003.bin", "part12/sangraha-xl-kan__sh0/shard_00002.bin", "part12/sangraha-xl-kan__sh1/shard_00002.bin", "part12/sangraha-xl-kan__sh2/shard_00002.bin", "part12/sangraha-xl-kan__sh3/shard_00003.bin", "part12/sangraha-xl-mal__sh0/shard_00002.bin", "part12/sangraha-xl-mal__sh1/shard_00002.bin", "part12/sangraha-xl-mal__sh2/shard_00002.bin", "part12/sangraha-xl-mal__sh3/shard_00003.bin", "part12/sangraha-xl-mar__sh0/shard_00002.bin", "part12/sangraha-xl-mar__sh1/shard_00002.bin", "part12/sangraha-xl-mar__sh2/shard_00002.bin", "part12/sangraha-xl-mar__sh3/shard_00003.bin", "part12/sangraha-xl-pan__sh0/shard_00002.bin", "part12/sangraha-xl-pan__sh1/shard_00002.bin", "part12/sangraha-xl-pan__sh2/shard_00002.bin", "part12/sangraha-xl-pan__sh3/shard_00003.bin", "part12/sangraha-xl-tam__sh0/shard_00002.bin", "part12/sangraha-xl-tam__sh1/shard_00002.bin", "part12/sangraha-xl-tam__sh2/shard_00002.bin", "part12/sangraha-xl-tam__sh3/shard_00003.bin", "part12/sangraha-xl-tel__sh0/shard_00002.bin", "part12/sangraha-xl-tel__sh1/shard_00002.bin", "part12/sangraha-xl-tel__sh2/shard_00002.bin", "part12/sangraha-xl-tel__sh3/shard_00003.bin", "part13/sangraha-xl-nep__sh0/shard_00002.bin", "part13/sangraha-xl-nep__sh1/shard_00002.bin", "part13/sangraha-xl-nep__sh2/shard_00002.bin", "part13/sangraha-xl-nep__sh3/shard_00003.bin", "part13/sangraha-xl-urd__sh0/shard_00002.bin", "part13/sangraha-xl-urd__sh1/shard_00002.bin", "part13/sangraha-xl-urd__sh2/shard_00002.bin", "part13/sangraha-xl-urd__sh3/shard_00003.bin", "part14/culturax-xl-bn__sh0/shard_00002.bin", "part14/culturax-xl-bn__sh1/shard_00002.bin", "part14/culturax-xl-bn__sh2/shard_00002.bin", "part14/culturax-xl-bn__sh3/shard_00003.bin", "part14/culturax-xl-gu__sh0/shard_00002.bin", "part14/culturax-xl-gu__sh1/shard_00002.bin", "part14/culturax-xl-gu__sh2/shard_00002.bin", "part14/culturax-xl-gu__sh3/shard_00003.bin", "part14/culturax-xl-hi__sh0/shard_00002.bin", "part14/culturax-xl-hi__sh1/shard_00002.bin", "part14/culturax-xl-hi__sh2/shard_00002.bin", "part14/culturax-xl-hi__sh3/shard_00003.bin", "part14/culturax-xl-kn__sh0/shard_00002.bin", "part14/culturax-xl-kn__sh1/shard_00002.bin", "part14/culturax-xl-kn__sh2/shard_00002.bin", "part14/culturax-xl-kn__sh3/shard_00003.bin", "part14/culturax-xl-ml__sh0/shard_00002.bin", "part14/culturax-xl-ml__sh1/shard_00002.bin", "part14/culturax-xl-ml__sh2/shard_00002.bin", "part14/culturax-xl-ml__sh3/shard_00003.bin", "part14/culturax-xl-mr__sh0/shard_00002.bin", "part14/culturax-xl-mr__sh1/shard_00002.bin", "part14/culturax-xl-mr__sh2/shard_00002.bin", "part14/culturax-xl-mr__sh3/shard_00003.bin", "part14/culturax-xl-ta__sh0/shard_00002.bin", "part14/culturax-xl-ta__sh1/shard_00002.bin", "part14/culturax-xl-ta__sh2/shard_00002.bin", "part14/culturax-xl-ta__sh3/shard_00003.bin", "part14/culturax-xl-te__sh0/shard_00002.bin", "part14/culturax-xl-te__sh1/shard_00002.bin", "part14/culturax-xl-te__sh2/shard_00002.bin", "part14/culturax-xl-te__sh3/shard_00003.bin", "part15/culturax-xl-ne__sh0/shard_00002.bin", "part15/culturax-xl-ne__sh1/shard_00002.bin", "part15/culturax-xl-ne__sh2/shard_00002.bin", "part15/culturax-xl-ne__sh3/shard_00003.bin", "part15/culturax-xl-pa__sh0/shard_00002.bin", "part15/culturax-xl-pa__sh1/shard_00002.bin", "part15/culturax-xl-pa__sh2/shard_00002.bin", "part15/culturax-xl-ur__sh0/shard_00002.bin", "part15/culturax-xl-ur__sh1/shard_00002.bin", "part15/culturax-xl-ur__sh2/shard_00002.bin", "part15/culturax-xl-ur__sh3/shard_00003.bin", "part1/books-urd-archive/shard_00003.bin", "part1/culturax-bn/shard_00003.bin", "part1/culturax-bn__sh0/shard_00003.bin", "part1/culturax-bn__sh1/shard_00003.bin", "part1/culturax-gu/shard_00003.bin", "part1/culturax-hi/shard_00003.bin", "part1/culturax-hi__sh0/shard_00003.bin", "part1/culturax-hi__sh1/shard_00003.bin", "part1/culturax-kn/shard_00003.bin", "part1/culturax-ml/shard_00003.bin", "part1/culturax-mr/shard_00003.bin", "part1/culturax-ne/shard_00003.bin", "part1/culturax-pa/shard_00003.bin", "part1/culturax-ta/shard_00003.bin", "part1/culturax-ta__sh0/shard_00003.bin", "part1/culturax-ta__sh1/shard_00003.bin", "part1/culturax-te/shard_00003.bin", "part1/culturax-ur/shard_00003.bin", "part1/fw2-ben/shard_00003.bin", "part1/fw2-hin/shard_00003.bin", "part1/fw2-mal/shard_00003.bin", "part1/fw2-tam/shard_00003.bin", "part1/fw2-tel/shard_00003.bin", "part1/fw2-urd/shard_00003.bin", "part1/sangraha-asm/shard_00003.bin", "part1/sangraha-ben/shard_00003.bin", "part1/sangraha-guj/shard_00003.bin", "part1/sangraha-hin/shard_00003.bin", "part1/sangraha-kan/shard_00003.bin", "part1/sangraha-mal/shard_00003.bin", "part1/sangraha-mar/shard_00003.bin", "part1/sangraha-nep/shard_00003.bin", "part1/sangraha-pan/shard_00003.bin", "part1/sangraha-san/shard_00003.bin", "part1/sangraha-snd/shard_00003.bin", "part1/sangraha-tam/shard_00003.bin", "part1/sangraha-tel/shard_00003.bin", "part1/sangraha-urd/shard_00003.bin", "part12/sangraha-xl-ben__sh0/shard_00003.bin", "part12/sangraha-xl-ben__sh1/shard_00003.bin", "part12/sangraha-xl-ben__sh2/shard_00003.bin", "part12/sangraha-xl-ben__sh3/shard_00004.bin", "part12/sangraha-xl-guj__sh0/shard_00003.bin", "part12/sangraha-xl-guj__sh1/shard_00003.bin", "part12/sangraha-xl-guj__sh2/shard_00003.bin", "part12/sangraha-xl-guj__sh3/shard_00004.bin", "part12/sangraha-xl-hin__sh0/shard_00003.bin", "part12/sangraha-xl-hin__sh1/shard_00003.bin", "part12/sangraha-xl-hin__sh2/shard_00003.bin", "part12/sangraha-xl-hin__sh3/shard_00004.bin", "part12/sangraha-xl-kan__sh0/shard_00003.bin", "part12/sangraha-xl-kan__sh1/shard_00003.bin", "part12/sangraha-xl-kan__sh2/shard_00003.bin", "part12/sangraha-xl-kan__sh3/shard_00004.bin", "part12/sangraha-xl-mal__sh0/shard_00003.bin", "part12/sangraha-xl-mal__sh1/shard_00003.bin", "part12/sangraha-xl-mal__sh2/shard_00003.bin", "part12/sangraha-xl-mal__sh3/shard_00004.bin", "part12/sangraha-xl-mar__sh0/shard_00003.bin", "part12/sangraha-xl-mar__sh1/shard_00003.bin", "part12/sangraha-xl-mar__sh2/shard_00003.bin", "part12/sangraha-xl-mar__sh3/shard_00004.bin", "part12/sangraha-xl-pan__sh0/shard_00003.bin", "part12/sangraha-xl-pan__sh1/shard_00003.bin", "part12/sangraha-xl-pan__sh2/shard_00003.bin", "part12/sangraha-xl-pan__sh3/shard_00004.bin", "part12/sangraha-xl-tam__sh0/shard_00003.bin", "part12/sangraha-xl-tam__sh1/shard_00003.bin", "part12/sangraha-xl-tam__sh2/shard_00003.bin", "part12/sangraha-xl-tam__sh3/shard_00004.bin", "part12/sangraha-xl-tel__sh0/shard_00003.bin", "part12/sangraha-xl-tel__sh1/shard_00003.bin", "part12/sangraha-xl-tel__sh2/shard_00003.bin", "part12/sangraha-xl-tel__sh3/shard_00004.bin", "part13/sangraha-xl-nep__sh0/shard_00003.bin", "part13/sangraha-xl-nep__sh1/shard_00003.bin", "part13/sangraha-xl-nep__sh2/shard_00003.bin", "part13/sangraha-xl-urd__sh0/shard_00003.bin", "part13/sangraha-xl-urd__sh1/shard_00003.bin", "part13/sangraha-xl-urd__sh2/shard_00003.bin", "part13/sangraha-xl-urd__sh3/shard_00004.bin", "part14/culturax-xl-bn__sh0/shard_00003.bin", "part14/culturax-xl-bn__sh1/shard_00003.bin", "part14/culturax-xl-bn__sh2/shard_00003.bin", "part14/culturax-xl-bn__sh3/shard_00004.bin", "part14/culturax-xl-gu__sh0/shard_00003.bin", "part14/culturax-xl-gu__sh1/shard_00003.bin", "part14/culturax-xl-gu__sh2/shard_00003.bin", "part21/books-en-gutenberg__sh0/shard_00013.bin", "part21/books-en-gutenberg__sh1/shard_00014.bin", "part21/books-en-pg19__sh0/shard_00013.bin", "part21/books-en-pg19__sh1/shard_00014.bin", "part21/wiki-en__sh0/shard_00013.bin", "part21/wiki-en__sh1/shard_00013.bin", "part21/wiki-en__sh2/shard_00013.bin", "part21/wiki-en__sh3/shard_00014.bin", "part21/academic-pes2o__sh0/shard_00014.bin", "part21/academic-pes2o__sh1/shard_00014.bin", "part21/academic-pes2o__sh2/shard_00014.bin", "part21/academic-pes2o__sh3/shard_00015.bin", "part21/books-en-gutenberg__sh0/shard_00014.bin", "part21/books-en-gutenberg__sh1/shard_00015.bin", "part21/books-en-pg19__sh0/shard_00014.bin", "part21/books-en-pg19__sh1/shard_00015.bin", "part21/wiki-en__sh0/shard_00014.bin", "part21/wiki-en__sh1/shard_00014.bin", "part21/wiki-en__sh2/shard_00014.bin", "part21/wiki-en__sh3/shard_00015.bin", "part21/academic-pes2o__sh0/shard_00015.bin", "part21/academic-pes2o__sh1/shard_00015.bin", "part21/academic-pes2o__sh2/shard_00015.bin", "part21/academic-pes2o__sh3/shard_00016.bin", "part21/books-en-gutenberg__sh0/shard_00015.bin", "part21/books-en-gutenberg__sh1/shard_00016.bin", "part21/books-en-pg19__sh0/shard_00015.bin", "part21/books-en-pg19__sh1/shard_00016.bin", "part21/wiki-en__sh0/shard_00015.bin", "part21/wiki-en__sh1/shard_00015.bin", "part21/wiki-en__sh2/shard_00015.bin", "part21/wiki-en__sh3/shard_00016.bin", "part21/academic-pes2o__sh0/shard_00016.bin", "part21/academic-pes2o__sh1/shard_00016.bin", "part21/academic-pes2o__sh2/shard_00016.bin", "part21/academic-pes2o__sh3/shard_00017.bin", "part21/books-en-gutenberg__sh0/shard_00016.bin", "part21/books-en-gutenberg__sh1/shard_00017.bin", "part21/books-en-pg19__sh0/shard_00016.bin", "part21/books-en-pg19__sh1/shard_00017.bin", "part21/wiki-en__sh0/shard_00016.bin", "part21/wiki-en__sh1/shard_00016.bin", "part21/wiki-en__sh2/shard_00016.bin", "part21/wiki-en__sh3/shard_00017.bin", "part21/academic-pes2o__sh0/shard_00017.bin", "part21/academic-pes2o__sh1/shard_00017.bin", "part21/academic-pes2o__sh2/shard_00017.bin", "part21/academic-pes2o__sh3/shard_00018.bin", "part21/books-en-gutenberg__sh0/shard_00017.bin", "part21/books-en-gutenberg__sh1/shard_00018.bin", "part21/books-en-pg19__sh0/shard_00017.bin", "part21/books-en-pg19__sh1/shard_00018.bin", "part21/wiki-en__sh0/shard_00017.bin", "part21/wiki-en__sh1/shard_00017.bin", "part21/wiki-en__sh2/shard_00017.bin", "part21/wiki-en__sh3/shard_00018.bin", "part21/academic-pes2o__sh0/shard_00018.bin", "part21/academic-pes2o__sh1/shard_00018.bin", "part21/academic-pes2o__sh2/shard_00018.bin", "part21/academic-pes2o__sh3/shard_00019.bin", "part21/books-en-gutenberg__sh0/shard_00018.bin", "part21/books-en-gutenberg__sh1/shard_00019.bin", "part21/books-en-pg19__sh0/shard_00018.bin", "part21/books-en-pg19__sh1/shard_00019.bin", "part21/wiki-en__sh0/shard_00018.bin", "part21/wiki-en__sh1/shard_00018.bin", "part21/wiki-en__sh2/shard_00018.bin", "part21/wiki-en__sh3/shard_00019.bin", "part21/academic-pes2o__sh0/shard_00019.bin", "part21/academic-pes2o__sh1/shard_00019.bin", "part21/academic-pes2o__sh2/shard_00019.bin", "part21/academic-pes2o__sh3/shard_00020.bin", "part21/books-en-gutenberg__sh0/shard_00019.bin", "part21/books-en-gutenberg__sh1/shard_00020.bin", "part21/books-en-pg19__sh0/shard_00019.bin", "part21/books-en-pg19__sh1/shard_00020.bin", "part21/wiki-en__sh0/shard_00019.bin", "part21/wiki-en__sh1/shard_00019.bin", "part21/wiki-en__sh2/shard_00019.bin", "part21/wiki-en__sh3/shard_00020.bin", "part21/academic-pes2o__sh0/shard_00020.bin", "part11/cosmopedia-automath-xl__sh3/shard_00003.bin", "part11/cosmopedia-web2-xl__sh0/shard_00003.bin", "part11/cosmopedia-web2-xl__sh1/shard_00003.bin", "part11/cosmopedia-web2-xl__sh2/shard_00003.bin", "part11/cosmopedia-web2-xl__sh3/shard_00003.bin", "part11/finemath-3plus-xl__sh0/shard_00003.bin", "part11/finemath-3plus-xl__sh1/shard_00003.bin", "part11/finemath-3plus-xl__sh2/shard_00003.bin", "part11/finemath-3plus-xl__sh3/shard_00003.bin", "part11/open-web-math__sh0/shard_00003.bin", "part11/open-web-math__sh1/shard_00003.bin", "part11/open-web-math__sh2/shard_00003.bin", "part11/open-web-math__sh3/shard_00003.bin", "part1/cosmopedia-automath/shard_00004.bin", "part1/cosmopedia-stories/shard_00004.bin", "part1/cosmopedia-web2/shard_00004.bin", "part1/finemath-3plus/shard_00004.bin", "part1/finemath-4plus/shard_00004.bin", "part1/finemath/shard_00004.bin", "part11/cosmopedia-automath-xl__sh0/shard_00004.bin", "part11/cosmopedia-automath-xl__sh1/shard_00004.bin", "part11/cosmopedia-automath-xl__sh2/shard_00004.bin", "part11/cosmopedia-automath-xl__sh3/shard_00004.bin", "part11/cosmopedia-web2-xl__sh0/shard_00004.bin", "part11/cosmopedia-web2-xl__sh1/shard_00004.bin", "part11/cosmopedia-web2-xl__sh2/shard_00004.bin", "part11/cosmopedia-web2-xl__sh3/shard_00004.bin", "part11/finemath-3plus-xl__sh0/shard_00004.bin", "part11/finemath-3plus-xl__sh1/shard_00004.bin", "part11/finemath-3plus-xl__sh2/shard_00004.bin", "part11/finemath-3plus-xl__sh3/shard_00004.bin", "part11/open-web-math__sh0/shard_00004.bin", "part11/open-web-math__sh1/shard_00004.bin", "part11/open-web-math__sh2/shard_00004.bin", "part11/open-web-math__sh3/shard_00004.bin", "part1/cosmopedia-automath/shard_00005.bin", "part1/cosmopedia-stories/shard_00005.bin", "part1/cosmopedia-web2/shard_00005.bin", "part1/finemath-3plus/shard_00005.bin", "part1/finemath-4plus/shard_00005.bin", "part1/finemath/shard_00005.bin", "part20/skills-stackexchange__sh1/shard_00002.bin", "part20/skills-stackexchange__sh2/shard_00002.bin", "part20/skills-stackexchange__sh3/shard_00002.bin", "part18/med-pubmed__sh0/shard_00003.bin", "part18/med-pubmed__sh1/shard_00003.bin", "part18/med-pubmed__sh2/shard_00003.bin", "part18/med-pubmed__sh3/shard_00003.bin", "part19/law-pile__sh0/shard_00003.bin", "part19/law-pile__sh1/shard_00003.bin", "part19/law-pile__sh2/shard_00003.bin", "part19/law-pile__sh3/shard_00003.bin", "part20/skills-stackexchange__sh0/shard_00003.bin", "part20/skills-stackexchange__sh1/shard_00003.bin", "part20/skills-stackexchange__sh2/shard_00003.bin", "part20/skills-stackexchange__sh3/shard_00003.bin", "part18/med-pubmed__sh0/shard_00004.bin", "part18/med-pubmed__sh1/shard_00004.bin", "part18/med-pubmed__sh2/shard_00004.bin", "part18/med-pubmed__sh3/shard_00004.bin", "part2/code-go__sh0/shard_00001.bin", "part2/code-go__sh1/shard_00001.bin", "part2/code-java__sh0/shard_00001.bin", "part2/code-java__sh1/shard_00001.bin", "part2/code-javascript__sh0/shard_00001.bin", "part2/code-javascript__sh1/shard_00001.bin", "part2/code-markdown__sh0/shard_00001.bin", "part2/code-markdown__sh1/shard_00001.bin", "part2/code-php__sh0/shard_00001.bin", "part2/code-php__sh1/shard_00001.bin", "part2/code-python__sh0/shard_00001.bin", "part2/code-python__sh1/shard_00001.bin", "part2/code-ruby__sh0/shard_00001.bin", "part2/code-ruby__sh1/shard_00001.bin"], "picks": [{"hf": "part13/sangraha-xl-san__sh0/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part13/sangraha-xl-san__sh1/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part13/sangraha-xl-san__sh2/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part13/sangraha-xl-san__sh3/shard_00002.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part13/sangraha-xl-snd__sh0/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part13/sangraha-xl-snd__sh1/shard_00001.bin", "b": 124690432, "cat": "core", "ep": 0}, {"hf": "part13/sangraha-xl-snd__sh2/shard_00001.bin", "b": 78675968, "cat": "core", "ep": 0}, {"hf": "part17/scripture-sanskrit-mono__sh1/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part22/reason-numinamath__sh0/shard_00001.bin", "b": 124715008, "cat": "core", "ep": 0}, {"hf": "part22/reason-numinamath__sh1/shard_00001.bin", "b": 122912768, "cat": "core", "ep": 0}, {"hf": "part22/reason-openorca__sh0/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part22/reason-openorca__sh1/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part4/align-bitext-bn/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part4/align-bitext-gu/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part4/align-bitext-hi/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part4/align-bitext-kn/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part4/align-bitext-ml/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part4/align-bitext-mr/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part4/align-bitext-pa/shard_00001.bin", "b": 163840000, "cat": "core", "ep": 0}, {"hf": "part12/sangraha-xl-guj__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-guj__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-guj__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-hin__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-hin__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-hin__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-hin__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-kan__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-kan__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-kan__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-kan__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mal__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mal__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mal__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mal__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mar__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mar__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mar__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mar__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-pan__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-pan__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-pan__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-pan__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tam__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tam__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tam__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tam__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tel__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tel__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tel__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tel__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-nep__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-nep__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-nep__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-nep__sh3/shard_00003.bin", "b": 138133504, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-urd__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-urd__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-urd__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-urd__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-bn__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-bn__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-bn__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-bn__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-gu__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-gu__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-gu__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-gu__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-hi__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-hi__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-hi__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-hi__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-kn__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-kn__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-kn__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-kn__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-ml__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-ml__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-ml__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-ml__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-mr__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-mr__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-mr__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-mr__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-ta__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-ta__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-ta__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-ta__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-te__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-te__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-te__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-te__sh3/shard_00003.bin", "b": 97107968, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-ne__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-ne__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-ne__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-ne__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-pa__sh0/shard_00002.bin", "b": 117211136, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-pa__sh1/shard_00002.bin", "b": 120766464, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-pa__sh2/shard_00002.bin", "b": 119750656, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-ur__sh0/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-ur__sh1/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-ur__sh2/shard_00002.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part15/culturax-xl-ur__sh3/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/books-urd-archive/shard_00003.bin", "b": 65593344, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-bn/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-bn__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-bn__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-gu/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-hi/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-hi__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-hi__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-kn/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-ml/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-mr/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-ne/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-pa/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-ta/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-ta__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-ta__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-te/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/culturax-ur/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/fw2-ben/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/fw2-hin/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/fw2-mal/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/fw2-tam/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/fw2-tel/shard_00003.bin", "b": 162054144, "cat": "indic", "ep": 0}, {"hf": "part1/fw2-urd/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-asm/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-ben/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-guj/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-hin/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-kan/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-mal/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-mar/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-nep/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-pan/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-san/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-snd/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-tam/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-tel/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part1/sangraha-urd/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-ben__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-ben__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-ben__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-ben__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-guj__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-guj__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-guj__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-guj__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-hin__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-hin__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-hin__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-hin__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-kan__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-kan__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-kan__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-kan__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mal__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mal__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mal__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mal__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mar__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mar__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mar__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-mar__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-pan__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-pan__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-pan__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-pan__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tam__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tam__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tam__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tam__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tel__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tel__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tel__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part12/sangraha-xl-tel__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-nep__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-nep__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-nep__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-urd__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-urd__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-urd__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part13/sangraha-xl-urd__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-bn__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-bn__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-bn__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-bn__sh3/shard_00004.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-gu__sh0/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-gu__sh1/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part14/culturax-xl-gu__sh2/shard_00003.bin", "b": 163840000, "cat": "indic", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh0/shard_00013.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh1/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh0/shard_00013.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh1/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh0/shard_00013.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh1/shard_00013.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh2/shard_00013.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh3/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh0/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh1/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh2/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh3/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh0/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh1/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh0/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh1/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh0/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh1/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh2/shard_00014.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh3/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh0/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh1/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh2/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh3/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh0/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh1/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh0/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh1/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh0/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh1/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh2/shard_00015.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh3/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh0/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh1/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh2/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh3/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh0/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh1/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh0/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh1/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh0/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh1/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh2/shard_00016.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh3/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh0/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh1/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh2/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh3/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh0/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh1/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh0/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh1/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh0/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh1/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh2/shard_00017.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh3/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh0/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh1/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh2/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh3/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh0/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh1/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh0/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh1/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh0/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh1/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh2/shard_00018.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh3/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh0/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh1/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh2/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh3/shard_00020.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh0/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-gutenberg__sh1/shard_00020.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh0/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/books-en-pg19__sh1/shard_00020.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh0/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh1/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh2/shard_00019.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/wiki-en__sh3/shard_00020.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part21/academic-pes2o__sh0/shard_00020.bin", "b": 163840000, "cat": "english", "ep": 0}, {"hf": "part11/cosmopedia-automath-xl__sh3/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-web2-xl__sh0/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-web2-xl__sh1/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-web2-xl__sh2/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-web2-xl__sh3/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/finemath-3plus-xl__sh0/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/finemath-3plus-xl__sh1/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/finemath-3plus-xl__sh2/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/finemath-3plus-xl__sh3/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/open-web-math__sh0/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/open-web-math__sh1/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/open-web-math__sh2/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/open-web-math__sh3/shard_00003.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/cosmopedia-automath/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/cosmopedia-stories/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/cosmopedia-web2/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/finemath-3plus/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/finemath-4plus/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/finemath/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-automath-xl__sh0/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-automath-xl__sh1/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-automath-xl__sh2/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-automath-xl__sh3/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-web2-xl__sh0/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-web2-xl__sh1/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-web2-xl__sh2/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/cosmopedia-web2-xl__sh3/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/finemath-3plus-xl__sh0/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/finemath-3plus-xl__sh1/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/finemath-3plus-xl__sh2/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/finemath-3plus-xl__sh3/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/open-web-math__sh0/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/open-web-math__sh1/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/open-web-math__sh2/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part11/open-web-math__sh3/shard_00004.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/cosmopedia-automath/shard_00005.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/cosmopedia-stories/shard_00005.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/cosmopedia-web2/shard_00005.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/finemath-3plus/shard_00005.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/finemath-4plus/shard_00005.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part1/finemath/shard_00005.bin", "b": 163840000, "cat": "math", "ep": 0}, {"hf": "part20/skills-stackexchange__sh1/shard_00002.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part20/skills-stackexchange__sh2/shard_00002.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part20/skills-stackexchange__sh3/shard_00002.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part18/med-pubmed__sh0/shard_00003.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part18/med-pubmed__sh1/shard_00003.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part18/med-pubmed__sh2/shard_00003.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part18/med-pubmed__sh3/shard_00003.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part19/law-pile__sh0/shard_00003.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part19/law-pile__sh1/shard_00003.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part19/law-pile__sh2/shard_00003.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part19/law-pile__sh3/shard_00003.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part20/skills-stackexchange__sh0/shard_00003.bin", "b": 93233152, "cat": "domain", "ep": 0}, {"hf": "part20/skills-stackexchange__sh1/shard_00003.bin", "b": 92913664, "cat": "domain", "ep": 0}, {"hf": "part20/skills-stackexchange__sh2/shard_00003.bin", "b": 92053504, "cat": "domain", "ep": 0}, {"hf": "part20/skills-stackexchange__sh3/shard_00003.bin", "b": 92987392, "cat": "domain", "ep": 0}, {"hf": "part18/med-pubmed__sh0/shard_00004.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part18/med-pubmed__sh1/shard_00004.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part18/med-pubmed__sh2/shard_00004.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part18/med-pubmed__sh3/shard_00004.bin", "b": 163840000, "cat": "domain", "ep": 0}, {"hf": "part2/code-go__sh0/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-go__sh1/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-java__sh0/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-java__sh1/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-javascript__sh0/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-javascript__sh1/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-markdown__sh0/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-markdown__sh1/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-php__sh0/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-php__sh1/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-python__sh0/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-python__sh1/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-ruby__sh0/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}, {"hf": "part2/code-ruby__sh1/shard_00001.bin", "b": 163840000, "cat": "code", "ep": 0}]} |