{ "revisions": { "bigcode/starcoderdata": "9fc30b578cedaec69e47302df72cf00feed7c8c4" }, "width": 50, "stride": 50, "num_partitions": 1, "stage_partitions": { "main": 1 }, "combined_error": 0.01, "per_filter_error": 0.010000000000000009, "est_unique_ngrams": { "main": 12871792175 }, "skipped_sources": [], "partitions": [ { "index": 0, "stage": "main", "stage_index": 0, "tag": "p0of1", "key": "starcoder-p0of1.50-50.bf", "error_rate": 0.010000000000000009, "capacity": 15446150611, "est_ngrams": 12871792175, "est_gib": 17.235550949355208, "families": { "ada": 1, "agda": 1, "alloy": 1, "antlr": 1, "applescript": 1, "assembly": 2, "augeas": 1, "awk": 1, "batchfile": 1, "bluespec": 1, "c": 53, "c-sharp": 45, "clojure": 1, "cmake": 1, "coffeescript": 1, "common-lisp": 2, "cpp": 48, "css": 12, "cuda": 1, "dart": 4, "dockerfile": 1, "elixir": 1, "elm": 1, "emacs-lisp": 1, "erlang": 1, "f-sharp": 1, "fortran": 2, "git-commits-cleaned": 55, "github-issues-filtered-structured": 59, "glsl": 1, "go": 24, "groovy": 1, "haskell": 3, "html": 29, "idris": 1, "isabelle": 1, "java": 87, "java-server-pages": 1, "javascript": 65, "json": 6, "julia": 2, "jupyter-scripts-dedup-filtered": 8, "jupyter-structured-clean-dedup": 6, "kotlin": 6, "lean": 1, "literate-agda": 1, "literate-coffeescript": 1, "literate-haskell": 1, "lua": 3, "makefile": 2, "maple": 1, "markdown": 79, "mathematica": 2, "matlab": 1, "ocaml": 1, "pascal": 2, "perl": 3, "php": 61, "powershell": 2, "prolog": 1, "protocol-buffer": 1, "python": 59, "r": 1, "racket": 1, "restructuredtext": 4, "rmarkdown": 1, "ruby": 7, "rust": 9, "sas": 1, "scala": 5, "scheme": 1, "shell": 4, "smalltalk": 1, "solidity": 1, "sparql": 1, "sql": 11, "stan": 1, "standard-ml": 1, "stata": 1, "systemverilog": 1, "tcl": 1, "tcsh": 1, "tex": 6, "thrift": 1, "typescript": 27, "verilog": 1, "vhdl": 1, "visual-basic": 2, "xslt": 1, "yacc": 1, "yaml": 4, "zig": 1 }, "shards": [ "bigcode/starcoderdata:ada/train-00000-of-00001.parquet", "bigcode/starcoderdata:agda/train-00000-of-00001.parquet", "bigcode/starcoderdata:alloy/train-00000-of-00001.parquet", "bigcode/starcoderdata:antlr/train-00000-of-00001.parquet", "bigcode/starcoderdata:applescript/train-00000-of-00001.parquet", "bigcode/starcoderdata:assembly/train-00000-of-00002.parquet", "bigcode/starcoderdata:assembly/train-00001-of-00002.parquet", "bigcode/starcoderdata:augeas/train-00000-of-00001.parquet", "bigcode/starcoderdata:awk/train-00000-of-00001.parquet", "bigcode/starcoderdata:batchfile/train-00000-of-00001.parquet", "bigcode/starcoderdata:bluespec/train-00000-of-00001.parquet", "bigcode/starcoderdata:c-sharp/train-00000-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00001-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00002-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00003-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00004-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00005-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00006-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00007-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00008-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00009-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00010-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00011-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00012-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00013-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00014-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00015-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00016-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00017-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00018-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00019-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00020-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00021-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00022-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00023-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00024-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00025-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00026-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00027-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00028-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00029-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00030-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00031-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00032-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00033-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00034-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00035-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00036-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00037-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00038-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00039-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00040-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00041-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00042-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00043-of-00045.parquet", "bigcode/starcoderdata:c-sharp/train-00044-of-00045.parquet", "bigcode/starcoderdata:c/train-00000-of-00053.parquet", "bigcode/starcoderdata:c/train-00001-of-00053.parquet", "bigcode/starcoderdata:c/train-00002-of-00053.parquet", "bigcode/starcoderdata:c/train-00003-of-00053.parquet", "bigcode/starcoderdata:c/train-00004-of-00053.parquet", "bigcode/starcoderdata:c/train-00005-of-00053.parquet", "bigcode/starcoderdata:c/train-00006-of-00053.parquet", "bigcode/starcoderdata:c/train-00007-of-00053.parquet", "bigcode/starcoderdata:c/train-00008-of-00053.parquet", "bigcode/starcoderdata:c/train-00009-of-00053.parquet", "bigcode/starcoderdata:c/train-00010-of-00053.parquet", "bigcode/starcoderdata:c/train-00011-of-00053.parquet", "bigcode/starcoderdata:c/train-00012-of-00053.parquet", "bigcode/starcoderdata:c/train-00013-of-00053.parquet", "bigcode/starcoderdata:c/train-00014-of-00053.parquet", "bigcode/starcoderdata:c/train-00015-of-00053.parquet", "bigcode/starcoderdata:c/train-00016-of-00053.parquet", "bigcode/starcoderdata:c/train-00017-of-00053.parquet", "bigcode/starcoderdata:c/train-00018-of-00053.parquet", "bigcode/starcoderdata:c/train-00019-of-00053.parquet", "bigcode/starcoderdata:c/train-00020-of-00053.parquet", "bigcode/starcoderdata:c/train-00021-of-00053.parquet", "bigcode/starcoderdata:c/train-00022-of-00053.parquet", "bigcode/starcoderdata:c/train-00023-of-00053.parquet", "bigcode/starcoderdata:c/train-00024-of-00053.parquet", "bigcode/starcoderdata:c/train-00025-of-00053.parquet", "bigcode/starcoderdata:c/train-00026-of-00053.parquet", "bigcode/starcoderdata:c/train-00027-of-00053.parquet", "bigcode/starcoderdata:c/train-00028-of-00053.parquet", "bigcode/starcoderdata:c/train-00029-of-00053.parquet", "bigcode/starcoderdata:c/train-00030-of-00053.parquet", "bigcode/starcoderdata:c/train-00031-of-00053.parquet", "bigcode/starcoderdata:c/train-00032-of-00053.parquet", "bigcode/starcoderdata:c/train-00033-of-00053.parquet", "bigcode/starcoderdata:c/train-00034-of-00053.parquet", "bigcode/starcoderdata:c/train-00035-of-00053.parquet", "bigcode/starcoderdata:c/train-00036-of-00053.parquet", "bigcode/starcoderdata:c/train-00037-of-00053.parquet", "bigcode/starcoderdata:c/train-00038-of-00053.parquet", "bigcode/starcoderdata:c/train-00039-of-00053.parquet", "bigcode/starcoderdata:c/train-00040-of-00053.parquet", "bigcode/starcoderdata:c/train-00041-of-00053.parquet", "bigcode/starcoderdata:c/train-00042-of-00053.parquet", "bigcode/starcoderdata:c/train-00043-of-00053.parquet", "bigcode/starcoderdata:c/train-00044-of-00053.parquet", "bigcode/starcoderdata:c/train-00045-of-00053.parquet", "bigcode/starcoderdata:c/train-00046-of-00053.parquet", "bigcode/starcoderdata:c/train-00047-of-00053.parquet", "bigcode/starcoderdata:c/train-00048-of-00053.parquet", "bigcode/starcoderdata:c/train-00049-of-00053.parquet", "bigcode/starcoderdata:c/train-00050-of-00053.parquet", "bigcode/starcoderdata:c/train-00051-of-00053.parquet", "bigcode/starcoderdata:c/train-00052-of-00053.parquet", "bigcode/starcoderdata:clojure/train-00000-of-00001.parquet", "bigcode/starcoderdata:cmake/train-00000-of-00001.parquet", "bigcode/starcoderdata:coffeescript/train-00000-of-00001.parquet", "bigcode/starcoderdata:common-lisp/train-00000-of-00002.parquet", "bigcode/starcoderdata:common-lisp/train-00001-of-00002.parquet", "bigcode/starcoderdata:cpp/train-00000-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00001-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00002-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00003-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00004-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00005-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00006-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00007-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00008-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00009-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00010-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00011-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00012-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00013-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00014-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00015-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00016-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00017-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00018-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00019-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00020-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00021-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00022-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00023-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00024-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00025-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00026-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00027-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00028-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00029-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00030-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00031-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00032-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00033-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00034-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00035-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00036-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00037-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00038-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00039-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00040-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00041-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00042-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00043-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00044-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00045-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00046-of-00048.parquet", "bigcode/starcoderdata:cpp/train-00047-of-00048.parquet", "bigcode/starcoderdata:css/train-00000-of-00012.parquet", "bigcode/starcoderdata:css/train-00001-of-00012.parquet", "bigcode/starcoderdata:css/train-00002-of-00012.parquet", "bigcode/starcoderdata:css/train-00003-of-00012.parquet", "bigcode/starcoderdata:css/train-00004-of-00012.parquet", "bigcode/starcoderdata:css/train-00005-of-00012.parquet", "bigcode/starcoderdata:css/train-00006-of-00012.parquet", "bigcode/starcoderdata:css/train-00007-of-00012.parquet", "bigcode/starcoderdata:css/train-00008-of-00012.parquet", "bigcode/starcoderdata:css/train-00009-of-00012.parquet", "bigcode/starcoderdata:css/train-00010-of-00012.parquet", "bigcode/starcoderdata:css/train-00011-of-00012.parquet", "bigcode/starcoderdata:cuda/train-00000-of-00001.parquet", "bigcode/starcoderdata:dart/train-00000-of-00004.parquet", "bigcode/starcoderdata:dart/train-00001-of-00004.parquet", "bigcode/starcoderdata:dart/train-00002-of-00004.parquet", "bigcode/starcoderdata:dart/train-00003-of-00004.parquet", "bigcode/starcoderdata:dockerfile/train-00000-of-00001.parquet", "bigcode/starcoderdata:elixir/train-00000-of-00001.parquet", "bigcode/starcoderdata:elm/train-00000-of-00001.parquet", "bigcode/starcoderdata:emacs-lisp/train-00000-of-00001.parquet", "bigcode/starcoderdata:erlang/train-00000-of-00001.parquet", "bigcode/starcoderdata:f-sharp/train-00000-of-00001.parquet", "bigcode/starcoderdata:fortran/train-00000-of-00002.parquet", "bigcode/starcoderdata:fortran/train-00001-of-00002.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00000-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00001-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00002-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00003-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00004-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00005-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00006-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00007-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00008-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00009-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00010-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00011-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00012-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00013-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00014-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00015-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00016-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00017-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00018-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00019-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00020-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00021-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00022-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00023-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00024-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00025-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00026-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00027-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00028-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00029-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00030-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00031-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00032-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00033-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00034-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00035-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00036-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00037-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00038-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00039-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00040-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00041-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00042-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00043-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00044-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00045-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00046-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00047-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00048-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00049-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00050-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00051-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00052-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00053-of-00055.parquet", "bigcode/starcoderdata:git-commits-cleaned/train-00054-of-00055.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00000-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00001-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00002-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00003-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00004-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00005-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00006-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00007-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00008-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00009-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00010-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00011-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00012-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00013-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00014-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00015-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00016-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00017-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00018-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00019-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00020-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00021-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00022-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00023-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00024-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00025-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00026-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00027-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00028-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00029-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00030-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00031-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00032-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00033-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00034-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00035-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00036-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00037-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00038-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00039-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00040-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00041-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00042-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00043-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00044-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00045-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00046-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00047-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00048-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00049-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00050-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00051-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00052-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00053-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00054-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00055-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00056-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00057-of-00059.parquet", "bigcode/starcoderdata:github-issues-filtered-structured/train-00058-of-00059.parquet", "bigcode/starcoderdata:glsl/train-00000-of-00001.parquet", "bigcode/starcoderdata:go/train-00000-of-00024.parquet", "bigcode/starcoderdata:go/train-00001-of-00024.parquet", "bigcode/starcoderdata:go/train-00002-of-00024.parquet", "bigcode/starcoderdata:go/train-00003-of-00024.parquet", "bigcode/starcoderdata:go/train-00004-of-00024.parquet", "bigcode/starcoderdata:go/train-00005-of-00024.parquet", "bigcode/starcoderdata:go/train-00006-of-00024.parquet", "bigcode/starcoderdata:go/train-00007-of-00024.parquet", "bigcode/starcoderdata:go/train-00008-of-00024.parquet", "bigcode/starcoderdata:go/train-00009-of-00024.parquet", "bigcode/starcoderdata:go/train-00010-of-00024.parquet", "bigcode/starcoderdata:go/train-00011-of-00024.parquet", "bigcode/starcoderdata:go/train-00012-of-00024.parquet", "bigcode/starcoderdata:go/train-00013-of-00024.parquet", "bigcode/starcoderdata:go/train-00014-of-00024.parquet", "bigcode/starcoderdata:go/train-00015-of-00024.parquet", "bigcode/starcoderdata:go/train-00016-of-00024.parquet", "bigcode/starcoderdata:go/train-00017-of-00024.parquet", "bigcode/starcoderdata:go/train-00018-of-00024.parquet", "bigcode/starcoderdata:go/train-00019-of-00024.parquet", "bigcode/starcoderdata:go/train-00020-of-00024.parquet", "bigcode/starcoderdata:go/train-00021-of-00024.parquet", "bigcode/starcoderdata:go/train-00022-of-00024.parquet", "bigcode/starcoderdata:go/train-00023-of-00024.parquet", "bigcode/starcoderdata:groovy/train-00000-of-00001.parquet", "bigcode/starcoderdata:haskell/train-00000-of-00003.parquet", "bigcode/starcoderdata:haskell/train-00001-of-00003.parquet", "bigcode/starcoderdata:haskell/train-00002-of-00003.parquet", "bigcode/starcoderdata:html/train-00000-of-00029.parquet", "bigcode/starcoderdata:html/train-00001-of-00029.parquet", "bigcode/starcoderdata:html/train-00002-of-00029.parquet", "bigcode/starcoderdata:html/train-00003-of-00029.parquet", "bigcode/starcoderdata:html/train-00004-of-00029.parquet", "bigcode/starcoderdata:html/train-00005-of-00029.parquet", "bigcode/starcoderdata:html/train-00006-of-00029.parquet", "bigcode/starcoderdata:html/train-00007-of-00029.parquet", "bigcode/starcoderdata:html/train-00008-of-00029.parquet", "bigcode/starcoderdata:html/train-00009-of-00029.parquet", "bigcode/starcoderdata:html/train-00010-of-00029.parquet", "bigcode/starcoderdata:html/train-00011-of-00029.parquet", "bigcode/starcoderdata:html/train-00012-of-00029.parquet", "bigcode/starcoderdata:html/train-00013-of-00029.parquet", "bigcode/starcoderdata:html/train-00014-of-00029.parquet", "bigcode/starcoderdata:html/train-00015-of-00029.parquet", "bigcode/starcoderdata:html/train-00016-of-00029.parquet", "bigcode/starcoderdata:html/train-00017-of-00029.parquet", "bigcode/starcoderdata:html/train-00018-of-00029.parquet", "bigcode/starcoderdata:html/train-00019-of-00029.parquet", "bigcode/starcoderdata:html/train-00020-of-00029.parquet", "bigcode/starcoderdata:html/train-00021-of-00029.parquet", "bigcode/starcoderdata:html/train-00022-of-00029.parquet", "bigcode/starcoderdata:html/train-00023-of-00029.parquet", "bigcode/starcoderdata:html/train-00024-of-00029.parquet", "bigcode/starcoderdata:html/train-00025-of-00029.parquet", "bigcode/starcoderdata:html/train-00026-of-00029.parquet", "bigcode/starcoderdata:html/train-00027-of-00029.parquet", "bigcode/starcoderdata:html/train-00028-of-00029.parquet", "bigcode/starcoderdata:idris/train-00000-of-00001.parquet", "bigcode/starcoderdata:isabelle/train-00000-of-00001.parquet", "bigcode/starcoderdata:java-server-pages/train-00000-of-00001.parquet", "bigcode/starcoderdata:java/train-00000-of-00087.parquet", "bigcode/starcoderdata:java/train-00001-of-00087.parquet", "bigcode/starcoderdata:java/train-00002-of-00087.parquet", "bigcode/starcoderdata:java/train-00003-of-00087.parquet", "bigcode/starcoderdata:java/train-00004-of-00087.parquet", "bigcode/starcoderdata:java/train-00005-of-00087.parquet", "bigcode/starcoderdata:java/train-00006-of-00087.parquet", "bigcode/starcoderdata:java/train-00007-of-00087.parquet", "bigcode/starcoderdata:java/train-00008-of-00087.parquet", "bigcode/starcoderdata:java/train-00009-of-00087.parquet", "bigcode/starcoderdata:java/train-00010-of-00087.parquet", "bigcode/starcoderdata:java/train-00011-of-00087.parquet", "bigcode/starcoderdata:java/train-00012-of-00087.parquet", "bigcode/starcoderdata:java/train-00013-of-00087.parquet", "bigcode/starcoderdata:java/train-00014-of-00087.parquet", "bigcode/starcoderdata:java/train-00015-of-00087.parquet", "bigcode/starcoderdata:java/train-00016-of-00087.parquet", "bigcode/starcoderdata:java/train-00017-of-00087.parquet", "bigcode/starcoderdata:java/train-00018-of-00087.parquet", "bigcode/starcoderdata:java/train-00019-of-00087.parquet", "bigcode/starcoderdata:java/train-00020-of-00087.parquet", "bigcode/starcoderdata:java/train-00021-of-00087.parquet", "bigcode/starcoderdata:java/train-00022-of-00087.parquet", "bigcode/starcoderdata:java/train-00023-of-00087.parquet", "bigcode/starcoderdata:java/train-00024-of-00087.parquet", "bigcode/starcoderdata:java/train-00025-of-00087.parquet", "bigcode/starcoderdata:java/train-00026-of-00087.parquet", "bigcode/starcoderdata:java/train-00027-of-00087.parquet", "bigcode/starcoderdata:java/train-00028-of-00087.parquet", "bigcode/starcoderdata:java/train-00029-of-00087.parquet", "bigcode/starcoderdata:java/train-00030-of-00087.parquet", "bigcode/starcoderdata:java/train-00031-of-00087.parquet", "bigcode/starcoderdata:java/train-00032-of-00087.parquet", "bigcode/starcoderdata:java/train-00033-of-00087.parquet", "bigcode/starcoderdata:java/train-00034-of-00087.parquet", "bigcode/starcoderdata:java/train-00035-of-00087.parquet", "bigcode/starcoderdata:java/train-00036-of-00087.parquet", "bigcode/starcoderdata:java/train-00037-of-00087.parquet", "bigcode/starcoderdata:java/train-00038-of-00087.parquet", "bigcode/starcoderdata:java/train-00039-of-00087.parquet", "bigcode/starcoderdata:java/train-00040-of-00087.parquet", "bigcode/starcoderdata:java/train-00041-of-00087.parquet", "bigcode/starcoderdata:java/train-00042-of-00087.parquet", "bigcode/starcoderdata:java/train-00043-of-00087.parquet", "bigcode/starcoderdata:java/train-00044-of-00087.parquet", "bigcode/starcoderdata:java/train-00045-of-00087.parquet", "bigcode/starcoderdata:java/train-00046-of-00087.parquet", "bigcode/starcoderdata:java/train-00047-of-00087.parquet", "bigcode/starcoderdata:java/train-00048-of-00087.parquet", "bigcode/starcoderdata:java/train-00049-of-00087.parquet", "bigcode/starcoderdata:java/train-00050-of-00087.parquet", "bigcode/starcoderdata:java/train-00051-of-00087.parquet", "bigcode/starcoderdata:java/train-00052-of-00087.parquet", "bigcode/starcoderdata:java/train-00053-of-00087.parquet", "bigcode/starcoderdata:java/train-00054-of-00087.parquet", "bigcode/starcoderdata:java/train-00055-of-00087.parquet", "bigcode/starcoderdata:java/train-00056-of-00087.parquet", "bigcode/starcoderdata:java/train-00057-of-00087.parquet", "bigcode/starcoderdata:java/train-00058-of-00087.parquet", "bigcode/starcoderdata:java/train-00059-of-00087.parquet", "bigcode/starcoderdata:java/train-00060-of-00087.parquet", "bigcode/starcoderdata:java/train-00061-of-00087.parquet", "bigcode/starcoderdata:java/train-00062-of-00087.parquet", "bigcode/starcoderdata:java/train-00063-of-00087.parquet", "bigcode/starcoderdata:java/train-00064-of-00087.parquet", "bigcode/starcoderdata:java/train-00065-of-00087.parquet", "bigcode/starcoderdata:java/train-00066-of-00087.parquet", "bigcode/starcoderdata:java/train-00067-of-00087.parquet", "bigcode/starcoderdata:java/train-00068-of-00087.parquet", "bigcode/starcoderdata:java/train-00069-of-00087.parquet", "bigcode/starcoderdata:java/train-00070-of-00087.parquet", "bigcode/starcoderdata:java/train-00071-of-00087.parquet", "bigcode/starcoderdata:java/train-00072-of-00087.parquet", "bigcode/starcoderdata:java/train-00073-of-00087.parquet", "bigcode/starcoderdata:java/train-00074-of-00087.parquet", "bigcode/starcoderdata:java/train-00075-of-00087.parquet", "bigcode/starcoderdata:java/train-00076-of-00087.parquet", "bigcode/starcoderdata:java/train-00077-of-00087.parquet", "bigcode/starcoderdata:java/train-00078-of-00087.parquet", "bigcode/starcoderdata:java/train-00079-of-00087.parquet", "bigcode/starcoderdata:java/train-00080-of-00087.parquet", "bigcode/starcoderdata:java/train-00081-of-00087.parquet", "bigcode/starcoderdata:java/train-00082-of-00087.parquet", "bigcode/starcoderdata:java/train-00083-of-00087.parquet", "bigcode/starcoderdata:java/train-00084-of-00087.parquet", "bigcode/starcoderdata:java/train-00085-of-00087.parquet", "bigcode/starcoderdata:java/train-00086-of-00087.parquet", "bigcode/starcoderdata:javascript/train-00000-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00001-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00002-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00003-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00004-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00005-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00006-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00007-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00008-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00009-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00010-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00011-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00012-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00013-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00014-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00015-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00016-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00017-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00018-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00019-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00020-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00021-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00022-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00023-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00024-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00025-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00026-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00027-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00028-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00029-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00030-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00031-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00032-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00033-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00034-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00035-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00036-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00037-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00038-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00039-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00040-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00041-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00042-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00043-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00044-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00045-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00046-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00047-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00048-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00049-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00050-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00051-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00052-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00053-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00054-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00055-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00056-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00057-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00058-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00059-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00060-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00061-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00062-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00063-of-00065.parquet", "bigcode/starcoderdata:javascript/train-00064-of-00065.parquet", "bigcode/starcoderdata:json/train-00000-of-00006.parquet", "bigcode/starcoderdata:json/train-00001-of-00006.parquet", "bigcode/starcoderdata:json/train-00002-of-00006.parquet", "bigcode/starcoderdata:json/train-00003-of-00006.parquet", "bigcode/starcoderdata:json/train-00004-of-00006.parquet", "bigcode/starcoderdata:json/train-00005-of-00006.parquet", "bigcode/starcoderdata:julia/train-00000-of-00002.parquet", "bigcode/starcoderdata:julia/train-00001-of-00002.parquet", "bigcode/starcoderdata:jupyter-scripts-dedup-filtered/train-00000-of-00008.parquet", "bigcode/starcoderdata:jupyter-scripts-dedup-filtered/train-00001-of-00008.parquet", "bigcode/starcoderdata:jupyter-scripts-dedup-filtered/train-00002-of-00008.parquet", "bigcode/starcoderdata:jupyter-scripts-dedup-filtered/train-00003-of-00008.parquet", "bigcode/starcoderdata:jupyter-scripts-dedup-filtered/train-00004-of-00008.parquet", "bigcode/starcoderdata:jupyter-scripts-dedup-filtered/train-00005-of-00008.parquet", "bigcode/starcoderdata:jupyter-scripts-dedup-filtered/train-00006-of-00008.parquet", "bigcode/starcoderdata:jupyter-scripts-dedup-filtered/train-00007-of-00008.parquet", "bigcode/starcoderdata:jupyter-structured-clean-dedup/train-00000-of-00006.parquet", "bigcode/starcoderdata:jupyter-structured-clean-dedup/train-00001-of-00006.parquet", "bigcode/starcoderdata:jupyter-structured-clean-dedup/train-00002-of-00006.parquet", "bigcode/starcoderdata:jupyter-structured-clean-dedup/train-00003-of-00006.parquet", "bigcode/starcoderdata:jupyter-structured-clean-dedup/train-00004-of-00006.parquet", "bigcode/starcoderdata:jupyter-structured-clean-dedup/train-00005-of-00006.parquet", "bigcode/starcoderdata:kotlin/train-00000-of-00006.parquet", "bigcode/starcoderdata:kotlin/train-00001-of-00006.parquet", "bigcode/starcoderdata:kotlin/train-00002-of-00006.parquet", "bigcode/starcoderdata:kotlin/train-00003-of-00006.parquet", "bigcode/starcoderdata:kotlin/train-00004-of-00006.parquet", "bigcode/starcoderdata:kotlin/train-00005-of-00006.parquet", "bigcode/starcoderdata:lean/train-00000-of-00001.parquet", "bigcode/starcoderdata:literate-agda/train-00000-of-00001.parquet", "bigcode/starcoderdata:literate-coffeescript/train-00000-of-00001.parquet", "bigcode/starcoderdata:literate-haskell/train-00000-of-00001.parquet", "bigcode/starcoderdata:lua/train-00000-of-00003.parquet", "bigcode/starcoderdata:lua/train-00001-of-00003.parquet", "bigcode/starcoderdata:lua/train-00002-of-00003.parquet", "bigcode/starcoderdata:makefile/train-00000-of-00002.parquet", "bigcode/starcoderdata:makefile/train-00001-of-00002.parquet", "bigcode/starcoderdata:maple/train-00000-of-00001.parquet", "bigcode/starcoderdata:markdown/train-00000-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00001-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00002-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00003-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00004-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00005-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00006-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00007-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00008-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00009-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00010-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00011-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00012-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00013-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00014-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00015-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00016-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00017-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00018-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00019-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00020-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00021-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00022-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00023-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00024-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00025-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00026-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00027-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00028-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00029-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00030-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00031-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00032-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00033-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00034-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00035-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00036-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00037-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00038-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00039-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00040-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00041-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00042-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00043-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00044-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00045-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00046-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00047-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00048-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00049-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00050-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00051-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00052-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00053-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00054-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00055-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00056-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00057-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00058-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00059-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00060-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00061-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00062-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00063-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00064-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00065-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00066-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00067-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00068-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00069-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00070-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00071-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00072-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00073-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00074-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00075-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00076-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00077-of-00079.parquet", "bigcode/starcoderdata:markdown/train-00078-of-00079.parquet", "bigcode/starcoderdata:mathematica/train-00000-of-00002.parquet", "bigcode/starcoderdata:mathematica/train-00001-of-00002.parquet", "bigcode/starcoderdata:matlab/train-00000-of-00001.parquet", "bigcode/starcoderdata:ocaml/train-00000-of-00001.parquet", "bigcode/starcoderdata:pascal/train-00000-of-00002.parquet", "bigcode/starcoderdata:pascal/train-00001-of-00002.parquet", "bigcode/starcoderdata:perl/train-00000-of-00003.parquet", "bigcode/starcoderdata:perl/train-00001-of-00003.parquet", "bigcode/starcoderdata:perl/train-00002-of-00003.parquet", "bigcode/starcoderdata:php/train-00000-of-00061.parquet", "bigcode/starcoderdata:php/train-00001-of-00061.parquet", "bigcode/starcoderdata:php/train-00002-of-00061.parquet", "bigcode/starcoderdata:php/train-00003-of-00061.parquet", "bigcode/starcoderdata:php/train-00004-of-00061.parquet", "bigcode/starcoderdata:php/train-00005-of-00061.parquet", "bigcode/starcoderdata:php/train-00006-of-00061.parquet", "bigcode/starcoderdata:php/train-00007-of-00061.parquet", "bigcode/starcoderdata:php/train-00008-of-00061.parquet", "bigcode/starcoderdata:php/train-00009-of-00061.parquet", "bigcode/starcoderdata:php/train-00010-of-00061.parquet", "bigcode/starcoderdata:php/train-00011-of-00061.parquet", "bigcode/starcoderdata:php/train-00012-of-00061.parquet", "bigcode/starcoderdata:php/train-00013-of-00061.parquet", "bigcode/starcoderdata:php/train-00014-of-00061.parquet", "bigcode/starcoderdata:php/train-00015-of-00061.parquet", "bigcode/starcoderdata:php/train-00016-of-00061.parquet", "bigcode/starcoderdata:php/train-00017-of-00061.parquet", "bigcode/starcoderdata:php/train-00018-of-00061.parquet", "bigcode/starcoderdata:php/train-00019-of-00061.parquet", "bigcode/starcoderdata:php/train-00020-of-00061.parquet", "bigcode/starcoderdata:php/train-00021-of-00061.parquet", "bigcode/starcoderdata:php/train-00022-of-00061.parquet", "bigcode/starcoderdata:php/train-00023-of-00061.parquet", "bigcode/starcoderdata:php/train-00024-of-00061.parquet", "bigcode/starcoderdata:php/train-00025-of-00061.parquet", "bigcode/starcoderdata:php/train-00026-of-00061.parquet", "bigcode/starcoderdata:php/train-00027-of-00061.parquet", "bigcode/starcoderdata:php/train-00028-of-00061.parquet", "bigcode/starcoderdata:php/train-00029-of-00061.parquet", "bigcode/starcoderdata:php/train-00030-of-00061.parquet", "bigcode/starcoderdata:php/train-00031-of-00061.parquet", "bigcode/starcoderdata:php/train-00032-of-00061.parquet", "bigcode/starcoderdata:php/train-00033-of-00061.parquet", "bigcode/starcoderdata:php/train-00034-of-00061.parquet", "bigcode/starcoderdata:php/train-00035-of-00061.parquet", "bigcode/starcoderdata:php/train-00036-of-00061.parquet", "bigcode/starcoderdata:php/train-00037-of-00061.parquet", "bigcode/starcoderdata:php/train-00038-of-00061.parquet", "bigcode/starcoderdata:php/train-00039-of-00061.parquet", "bigcode/starcoderdata:php/train-00040-of-00061.parquet", "bigcode/starcoderdata:php/train-00041-of-00061.parquet", "bigcode/starcoderdata:php/train-00042-of-00061.parquet", "bigcode/starcoderdata:php/train-00043-of-00061.parquet", "bigcode/starcoderdata:php/train-00044-of-00061.parquet", "bigcode/starcoderdata:php/train-00045-of-00061.parquet", "bigcode/starcoderdata:php/train-00046-of-00061.parquet", "bigcode/starcoderdata:php/train-00047-of-00061.parquet", "bigcode/starcoderdata:php/train-00048-of-00061.parquet", "bigcode/starcoderdata:php/train-00049-of-00061.parquet", "bigcode/starcoderdata:php/train-00050-of-00061.parquet", "bigcode/starcoderdata:php/train-00051-of-00061.parquet", "bigcode/starcoderdata:php/train-00052-of-00061.parquet", "bigcode/starcoderdata:php/train-00053-of-00061.parquet", "bigcode/starcoderdata:php/train-00054-of-00061.parquet", "bigcode/starcoderdata:php/train-00055-of-00061.parquet", "bigcode/starcoderdata:php/train-00056-of-00061.parquet", "bigcode/starcoderdata:php/train-00057-of-00061.parquet", "bigcode/starcoderdata:php/train-00058-of-00061.parquet", "bigcode/starcoderdata:php/train-00059-of-00061.parquet", "bigcode/starcoderdata:php/train-00060-of-00061.parquet", "bigcode/starcoderdata:powershell/train-00000-of-00002.parquet", "bigcode/starcoderdata:powershell/train-00001-of-00002.parquet", "bigcode/starcoderdata:prolog/train-00000-of-00001.parquet", "bigcode/starcoderdata:protocol-buffer/train-00000-of-00001.parquet", "bigcode/starcoderdata:python/train-00000-of-00059.parquet", "bigcode/starcoderdata:python/train-00001-of-00059.parquet", "bigcode/starcoderdata:python/train-00002-of-00059.parquet", "bigcode/starcoderdata:python/train-00003-of-00059.parquet", "bigcode/starcoderdata:python/train-00004-of-00059.parquet", "bigcode/starcoderdata:python/train-00005-of-00059.parquet", "bigcode/starcoderdata:python/train-00006-of-00059.parquet", "bigcode/starcoderdata:python/train-00007-of-00059.parquet", "bigcode/starcoderdata:python/train-00008-of-00059.parquet", "bigcode/starcoderdata:python/train-00009-of-00059.parquet", "bigcode/starcoderdata:python/train-00010-of-00059.parquet", "bigcode/starcoderdata:python/train-00011-of-00059.parquet", "bigcode/starcoderdata:python/train-00012-of-00059.parquet", "bigcode/starcoderdata:python/train-00013-of-00059.parquet", "bigcode/starcoderdata:python/train-00014-of-00059.parquet", "bigcode/starcoderdata:python/train-00015-of-00059.parquet", "bigcode/starcoderdata:python/train-00016-of-00059.parquet", "bigcode/starcoderdata:python/train-00017-of-00059.parquet", "bigcode/starcoderdata:python/train-00018-of-00059.parquet", "bigcode/starcoderdata:python/train-00019-of-00059.parquet", "bigcode/starcoderdata:python/train-00020-of-00059.parquet", "bigcode/starcoderdata:python/train-00021-of-00059.parquet", "bigcode/starcoderdata:python/train-00022-of-00059.parquet", "bigcode/starcoderdata:python/train-00023-of-00059.parquet", "bigcode/starcoderdata:python/train-00024-of-00059.parquet", "bigcode/starcoderdata:python/train-00025-of-00059.parquet", "bigcode/starcoderdata:python/train-00026-of-00059.parquet", "bigcode/starcoderdata:python/train-00027-of-00059.parquet", "bigcode/starcoderdata:python/train-00028-of-00059.parquet", "bigcode/starcoderdata:python/train-00029-of-00059.parquet", "bigcode/starcoderdata:python/train-00030-of-00059.parquet", "bigcode/starcoderdata:python/train-00031-of-00059.parquet", "bigcode/starcoderdata:python/train-00032-of-00059.parquet", "bigcode/starcoderdata:python/train-00033-of-00059.parquet", "bigcode/starcoderdata:python/train-00034-of-00059.parquet", "bigcode/starcoderdata:python/train-00035-of-00059.parquet", "bigcode/starcoderdata:python/train-00036-of-00059.parquet", "bigcode/starcoderdata:python/train-00037-of-00059.parquet", "bigcode/starcoderdata:python/train-00038-of-00059.parquet", "bigcode/starcoderdata:python/train-00039-of-00059.parquet", "bigcode/starcoderdata:python/train-00040-of-00059.parquet", "bigcode/starcoderdata:python/train-00041-of-00059.parquet", "bigcode/starcoderdata:python/train-00042-of-00059.parquet", "bigcode/starcoderdata:python/train-00043-of-00059.parquet", "bigcode/starcoderdata:python/train-00044-of-00059.parquet", "bigcode/starcoderdata:python/train-00045-of-00059.parquet", "bigcode/starcoderdata:python/train-00046-of-00059.parquet", "bigcode/starcoderdata:python/train-00047-of-00059.parquet", "bigcode/starcoderdata:python/train-00048-of-00059.parquet", "bigcode/starcoderdata:python/train-00049-of-00059.parquet", "bigcode/starcoderdata:python/train-00050-of-00059.parquet", "bigcode/starcoderdata:python/train-00051-of-00059.parquet", "bigcode/starcoderdata:python/train-00052-of-00059.parquet", "bigcode/starcoderdata:python/train-00053-of-00059.parquet", "bigcode/starcoderdata:python/train-00054-of-00059.parquet", "bigcode/starcoderdata:python/train-00055-of-00059.parquet", "bigcode/starcoderdata:python/train-00056-of-00059.parquet", "bigcode/starcoderdata:python/train-00057-of-00059.parquet", "bigcode/starcoderdata:python/train-00058-of-00059.parquet", "bigcode/starcoderdata:r/train-00000-of-00001.parquet", "bigcode/starcoderdata:racket/train-00000-of-00001.parquet", "bigcode/starcoderdata:restructuredtext/train-00000-of-00004.parquet", "bigcode/starcoderdata:restructuredtext/train-00001-of-00004.parquet", "bigcode/starcoderdata:restructuredtext/train-00002-of-00004.parquet", "bigcode/starcoderdata:restructuredtext/train-00003-of-00004.parquet", "bigcode/starcoderdata:rmarkdown/train-00000-of-00001.parquet", "bigcode/starcoderdata:ruby/train-00000-of-00007.parquet", "bigcode/starcoderdata:ruby/train-00001-of-00007.parquet", "bigcode/starcoderdata:ruby/train-00002-of-00007.parquet", "bigcode/starcoderdata:ruby/train-00003-of-00007.parquet", "bigcode/starcoderdata:ruby/train-00004-of-00007.parquet", "bigcode/starcoderdata:ruby/train-00005-of-00007.parquet", "bigcode/starcoderdata:ruby/train-00006-of-00007.parquet", "bigcode/starcoderdata:rust/train-00000-of-00009.parquet", "bigcode/starcoderdata:rust/train-00001-of-00009.parquet", "bigcode/starcoderdata:rust/train-00002-of-00009.parquet", "bigcode/starcoderdata:rust/train-00003-of-00009.parquet", "bigcode/starcoderdata:rust/train-00004-of-00009.parquet", "bigcode/starcoderdata:rust/train-00005-of-00009.parquet", "bigcode/starcoderdata:rust/train-00006-of-00009.parquet", "bigcode/starcoderdata:rust/train-00007-of-00009.parquet", "bigcode/starcoderdata:rust/train-00008-of-00009.parquet", "bigcode/starcoderdata:sas/train-00000-of-00001.parquet", "bigcode/starcoderdata:scala/train-00000-of-00005.parquet", "bigcode/starcoderdata:scala/train-00001-of-00005.parquet", "bigcode/starcoderdata:scala/train-00002-of-00005.parquet", "bigcode/starcoderdata:scala/train-00003-of-00005.parquet", "bigcode/starcoderdata:scala/train-00004-of-00005.parquet", "bigcode/starcoderdata:scheme/train-00000-of-00001.parquet", "bigcode/starcoderdata:shell/train-00000-of-00004.parquet", "bigcode/starcoderdata:shell/train-00001-of-00004.parquet", "bigcode/starcoderdata:shell/train-00002-of-00004.parquet", "bigcode/starcoderdata:shell/train-00003-of-00004.parquet", "bigcode/starcoderdata:smalltalk/train-00000-of-00001.parquet", "bigcode/starcoderdata:solidity/train-00000-of-00001.parquet", "bigcode/starcoderdata:sparql/train-00000-of-00001.parquet", "bigcode/starcoderdata:sql/train-00000-of-00011.parquet", "bigcode/starcoderdata:sql/train-00001-of-00011.parquet", "bigcode/starcoderdata:sql/train-00002-of-00011.parquet", "bigcode/starcoderdata:sql/train-00003-of-00011.parquet", "bigcode/starcoderdata:sql/train-00004-of-00011.parquet", "bigcode/starcoderdata:sql/train-00005-of-00011.parquet", "bigcode/starcoderdata:sql/train-00006-of-00011.parquet", "bigcode/starcoderdata:sql/train-00007-of-00011.parquet", "bigcode/starcoderdata:sql/train-00008-of-00011.parquet", "bigcode/starcoderdata:sql/train-00009-of-00011.parquet", "bigcode/starcoderdata:sql/train-00010-of-00011.parquet", "bigcode/starcoderdata:stan/train-00000-of-00001.parquet", "bigcode/starcoderdata:standard-ml/train-00000-of-00001.parquet", "bigcode/starcoderdata:stata/train-00000-of-00001.parquet", "bigcode/starcoderdata:systemverilog/train-00000-of-00001.parquet", "bigcode/starcoderdata:tcl/train-00000-of-00001.parquet", "bigcode/starcoderdata:tcsh/train-00000-of-00001.parquet", "bigcode/starcoderdata:tex/train-00000-of-00006.parquet", "bigcode/starcoderdata:tex/train-00001-of-00006.parquet", "bigcode/starcoderdata:tex/train-00002-of-00006.parquet", "bigcode/starcoderdata:tex/train-00003-of-00006.parquet", "bigcode/starcoderdata:tex/train-00004-of-00006.parquet", "bigcode/starcoderdata:tex/train-00005-of-00006.parquet", "bigcode/starcoderdata:thrift/train-00000-of-00001.parquet", "bigcode/starcoderdata:typescript/train-00000-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00001-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00002-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00003-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00004-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00005-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00006-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00007-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00008-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00009-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00010-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00011-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00012-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00013-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00014-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00015-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00016-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00017-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00018-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00019-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00020-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00021-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00022-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00023-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00024-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00025-of-00027.parquet", "bigcode/starcoderdata:typescript/train-00026-of-00027.parquet", "bigcode/starcoderdata:verilog/train-00000-of-00001.parquet", "bigcode/starcoderdata:vhdl/train-00000-of-00001.parquet", "bigcode/starcoderdata:visual-basic/train-00000-of-00002.parquet", "bigcode/starcoderdata:visual-basic/train-00001-of-00002.parquet", "bigcode/starcoderdata:xslt/train-00000-of-00001.parquet", "bigcode/starcoderdata:yacc/train-00000-of-00001.parquet", "bigcode/starcoderdata:yaml/train-00000-of-00004.parquet", "bigcode/starcoderdata:yaml/train-00001-of-00004.parquet", "bigcode/starcoderdata:yaml/train-00002-of-00004.parquet", "bigcode/starcoderdata:yaml/train-00003-of-00004.parquet", "bigcode/starcoderdata:zig/train-00000-of-00001.parquet" ] } ] }