From 5e766a1a105b0217b85cd694cc2a52667bcfa5fe Mon Sep 17 00:00:00 2001
From: Gaetan Lepage <gaetan@glepage.com>
Date: Sat, 20 Apr 2024 00:07:38 +0200
Subject: [PATCH] python311Packages.tokenizers: 0.15.0 -> 0.19.1

Diff: https://github.com/huggingface/tokenizers/compare/v0.15.0...v0.19.1
---
 .../python-modules/tokenizers/Cargo.lock      | 566 +++++++-----------
 .../python-modules/tokenizers/default.nix     |  20 +-
 2 files changed, 243 insertions(+), 343 deletions(-)

diff --git a/pkgs/development/python-modules/tokenizers/Cargo.lock b/pkgs/development/python-modules/tokenizers/Cargo.lock
index 295d232e6b38..a0324bff8aba 100644
--- a/pkgs/development/python-modules/tokenizers/Cargo.lock
+++ b/pkgs/development/python-modules/tokenizers/Cargo.lock
@@ -4,18 +4,18 @@ version = 3
 
 [[package]]
 name = "aho-corasick"
-version = "1.1.2"
+version = "1.1.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b2969dcb958b36655471fc61f7e416fa76033bdd4bfed0678d8fee1e2d07a1f0"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
 dependencies = [
  "memchr",
 ]
 
 [[package]]
 name = "anstream"
-version = "0.6.4"
+version = "0.6.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2ab91ebe16eb252986481c5b62f6098f3b698a45e34b5b98200cf20dd2484a44"
+checksum = "d96bd03f33fe50a863e394ee9718a706f988b9079b20c3784fb726e7678b62fb"
 dependencies = [
  "anstyle",
  "anstyle-parse",
@@ -27,43 +27,43 @@ dependencies = [
 
 [[package]]
 name = "anstyle"
-version = "1.0.4"
+version = "1.0.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7079075b41f533b8c61d2a4d073c4676e1f8b249ff94a393b0595db304e0dd87"
+checksum = "8901269c6307e8d93993578286ac0edf7f195079ffff5ebdeea6a59ffb7e36bc"
 
 [[package]]
 name = "anstyle-parse"
-version = "0.2.2"
+version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "317b9a89c1868f5ea6ff1d9539a69f45dffc21ce321ac1fd1160dfa48c8e2140"
+checksum = "c75ac65da39e5fe5ab759307499ddad880d724eed2f6ce5b5e8a26f4f387928c"
 dependencies = [
  "utf8parse",
 ]
 
 [[package]]
 name = "anstyle-query"
-version = "1.0.0"
+version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5ca11d4be1bab0c8bc8734a9aa7bf4ee8316d462a08c6ac5052f888fef5b494b"
+checksum = "e28923312444cdd728e4738b3f9c9cac739500909bb3d3c94b43551b16517648"
 dependencies = [
- "windows-sys 0.48.0",
+ "windows-sys",
 ]
 
 [[package]]
 name = "anstyle-wincon"
-version = "3.0.1"
+version = "3.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f0699d10d2f4d628a98ee7b57b289abbc98ff3bad977cb3152709d4bf2330628"
+checksum = "1cd54b81ec8d6180e24654d0b371ad22fc3dd083b6ff8ba325b72e00c87660a7"
 dependencies = [
  "anstyle",
- "windows-sys 0.48.0",
+ "windows-sys",
 ]
 
 [[package]]
 name = "autocfg"
-version = "1.1.0"
+version = "1.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
+checksum = "f1fdabc7756949593fe60f30ec81974b613357de856987752631dea1e3394c80"
 
 [[package]]
 name = "base64"
@@ -79,18 +79,15 @@ checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
 
 [[package]]
 name = "bitflags"
-version = "2.4.1"
+version = "2.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "327762f6e5a765692301e5bb513e0d9fef63be86bbc14528052b1cd3e6f03e07"
+checksum = "cf4b9d6a944f767f8e5e0db018570623c85f3d925ac718db4e06d0187adb21c1"
 
 [[package]]
 name = "cc"
-version = "1.0.83"
+version = "1.0.94"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f1174fb0b6ec23863f8b971027804a42614e347eafb0a95bf0b12cdae21fc4d0"
-dependencies = [
- "libc",
-]
+checksum = "17f6e324229dc011159fcc089755d1e2e216a90d43a7dea6853ca740b84f35e7"
 
 [[package]]
 name = "cfg-if"
@@ -98,46 +95,6 @@ version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
-[[package]]
-name = "clap"
-version = "4.4.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2275f18819641850fa26c89acc84d465c1bf91ce57bc2748b28c420473352f64"
-dependencies = [
- "clap_builder",
- "clap_derive",
-]
-
-[[package]]
-name = "clap_builder"
-version = "4.4.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "07cdf1b148b25c1e1f7a42225e30a0d99a615cd4637eae7365548dd4529b95bc"
-dependencies = [
- "anstream",
- "anstyle",
- "clap_lex",
- "strsim",
-]
-
-[[package]]
-name = "clap_derive"
-version = "4.4.7"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf9804afaaf59a91e75b022a30fb7229a7901f60c755489cc61c9b423b836442"
-dependencies = [
- "heck",
- "proc-macro2",
- "quote",
- "syn 2.0.39",
-]
-
-[[package]]
-name = "clap_lex"
-version = "0.6.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "702fc72eb24e5a1e48ce58027a675bc24edd52096d5397d4aea7c6dd9eca0bd1"
-
 [[package]]
 name = "colorchoice"
 version = "1.0.0"
@@ -146,55 +103,47 @@ checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"
 
 [[package]]
 name = "console"
-version = "0.15.7"
+version = "0.15.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c926e00cc70edefdc64d3a5ff31cc65bb97a3460097762bd23afb4d8145fccf8"
+checksum = "0e1f83fc076bd6dd27517eacdf25fef6c4dfe5f1d7448bafaaf3a26f13b5e4eb"
 dependencies = [
  "encode_unicode",
  "lazy_static",
  "libc",
  "unicode-width",
- "windows-sys 0.45.0",
+ "windows-sys",
 ]
 
 [[package]]
 name = "crossbeam-deque"
-version = "0.8.3"
+version = "0.8.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce6fd6f855243022dcecf8702fef0c297d4338e226845fe067f6341ad9fa0cef"
+checksum = "613f8cc01fe9cf1a3eb3d7f488fd2fa8388403e97039e2f73692932e291a770d"
 dependencies = [
- "cfg-if",
  "crossbeam-epoch",
  "crossbeam-utils",
 ]
 
 [[package]]
 name = "crossbeam-epoch"
-version = "0.9.15"
+version = "0.9.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ae211234986c545741a7dc064309f67ee1e5ad243d0e48335adc0484d960bcc7"
+checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
 dependencies = [
- "autocfg",
- "cfg-if",
  "crossbeam-utils",
- "memoffset",
- "scopeguard",
 ]
 
 [[package]]
 name = "crossbeam-utils"
-version = "0.8.16"
+version = "0.8.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5a22b2d63d4d1dc0b7f1b6b2747dd0088008a9be28b6ddf0b1e7d335e3037294"
-dependencies = [
- "cfg-if",
-]
+checksum = "248e3bacc7dc6baa3b21e405ee045c3047101a49145e7e9eca583ab4c2ca5345"
 
 [[package]]
 name = "darling"
-version = "0.14.4"
+version = "0.20.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7b750cb3417fd1b327431a470f388520309479ab0bf5e323505daf0290cd3850"
+checksum = "54e36fcd13ed84ffdfda6f5be89b31287cbb80c439841fe69e04841435464391"
 dependencies = [
  "darling_core",
  "darling_macro",
@@ -202,65 +151,65 @@ dependencies = [
 
 [[package]]
 name = "darling_core"
-version = "0.14.4"
+version = "0.20.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "109c1ca6e6b7f82cc233a97004ea8ed7ca123a9af07a8230878fcfda9b158bf0"
+checksum = "9c2cf1c23a687a1feeb728783b993c4e1ad83d99f351801977dd809b48d0a70f"
 dependencies = [
  "fnv",
  "ident_case",
  "proc-macro2",
  "quote",
  "strsim",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "darling_macro"
-version = "0.14.4"
+version = "0.20.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a4aab4dbc9f7611d8b55048a3a16d2d010c2c8334e46304b40ac1cc14bf3b48e"
+checksum = "a668eda54683121533a393014d8692171709ff57a7d61f187b6e782719f8933f"
 dependencies = [
  "darling_core",
  "quote",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "derive_builder"
-version = "0.12.0"
+version = "0.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8d67778784b508018359cbc8696edb3db78160bab2c2a28ba7f56ef6932997f8"
+checksum = "0350b5cb0331628a5916d6c5c0b72e97393b8b6b03b47a9284f4e7f5a405ffd7"
 dependencies = [
  "derive_builder_macro",
 ]
 
 [[package]]
 name = "derive_builder_core"
-version = "0.12.0"
+version = "0.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c11bdc11a0c47bc7d37d582b5285da6849c96681023680b906673c5707af7b0f"
+checksum = "d48cda787f839151732d396ac69e3473923d54312c070ee21e9effcaa8ca0b1d"
 dependencies = [
  "darling",
  "proc-macro2",
  "quote",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "derive_builder_macro"
-version = "0.12.0"
+version = "0.20.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ebcda35c7a396850a55ffeac740804b40ffec779b98fffbb1738f4033f0ee79e"
+checksum = "206868b8242f27cecce124c19fd88157fbd0dd334df2587f36417bafbc85097b"
 dependencies = [
  "derive_builder_core",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "either"
-version = "1.9.0"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a26ae43d7bcc3b814de94796a5e736d4029efb0ee900c12e2d54c993ad1a1e07"
+checksum = "a47c1c47d2f5964e29c61246e81db715514cd532db6b5116a25ea3c03d6780a2"
 
 [[package]]
 name = "encode_unicode"
@@ -269,26 +218,36 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a357d28ed41a50f9c765dbfe56cbc04a64e53e5fc58ba79fbc34c10ef3df831f"
 
 [[package]]
-name = "env_logger"
-version = "0.10.1"
+name = "env_filter"
+version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "95b3f3e67048839cb0d0781f445682a35113da7121f7c949db0e2be96a4fbece"
+checksum = "a009aa4810eb158359dda09d0c87378e4bbb89b5a801f016885a4707ba24f7ea"
 dependencies = [
- "humantime",
- "is-terminal",
  "log",
  "regex",
- "termcolor",
+]
+
+[[package]]
+name = "env_logger"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "38b35839ba51819680ba087cd351788c9a3c476841207e0b8cee0b04722343b9"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "env_filter",
+ "humantime",
+ "log",
 ]
 
 [[package]]
 name = "errno"
-version = "0.3.6"
+version = "0.3.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7c18ee0ed65a5f1f81cac6b1d213b69c35fa47d4252ad41f1486dbd8226fe36e"
+checksum = "a258e46cdc063eb8519c00b9fc845fc47bcfca4130e2f08e88665ceda8474245"
 dependencies = [
  "libc",
- "windows-sys 0.48.0",
+ "windows-sys",
 ]
 
 [[package]]
@@ -302,9 +261,9 @@ dependencies = [
 
 [[package]]
 name = "fastrand"
-version = "2.0.1"
+version = "2.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "25cbce373ec4653f1a01a31e8a5e5ec0c622dc27ff9c4e6606eefef5cbbed4a5"
+checksum = "658bd65b1cf4c852a3cc96f18a8ce7b5640f6b703f905c7d74532294c2a63984"
 
 [[package]]
 name = "fnv"
@@ -314,9 +273,9 @@ checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
 [[package]]
 name = "getrandom"
-version = "0.2.11"
+version = "0.2.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fe9006bed769170c11f845cf00c7c1e9092aeb3f268e007c3e760ac68008070f"
+checksum = "94b22e06ecb0110981051723910cbf0b5f5e09a2062dd7663334ee79a9d1286c"
 dependencies = [
  "cfg-if",
  "libc",
@@ -329,12 +288,6 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
 
-[[package]]
-name = "hermit-abi"
-version = "0.3.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d77f7ec81a6d05a3abb01ab6eb7590f6083d08449fe5a1c8b1e620283546ccb7"
-
 [[package]]
 name = "humantime"
 version = "2.1.0"
@@ -349,9 +302,9 @@ checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
 
 [[package]]
 name = "indicatif"
-version = "0.17.7"
+version = "0.17.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fb28741c9db9a713d93deb3bb9515c20788cef5815265bee4980e87bde7e0f25"
+checksum = "763a5a8f45087d6bcea4222e7b72c291a054edf80e4ef6efd2a4979878c7bea3"
 dependencies = [
  "console",
  "instant",
@@ -362,9 +315,9 @@ dependencies = [
 
 [[package]]
 name = "indoc"
-version = "1.0.9"
+version = "2.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bfa799dd5ed20a7e349f3b4639aa80d74549c81716d9ec4f994c9b5815598306"
+checksum = "b248f5224d1d606005e02c97f5aa4e88eeb230488bcc03bc9ca4d7991399f2b5"
 
 [[package]]
 name = "instant"
@@ -375,17 +328,6 @@ dependencies = [
  "cfg-if",
 ]
 
-[[package]]
-name = "is-terminal"
-version = "0.4.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb0889898416213fab133e1d33a0e5858a48177452750691bde3666d0fdbaf8b"
-dependencies = [
- "hermit-abi",
- "rustix",
- "windows-sys 0.48.0",
-]
-
 [[package]]
 name = "itertools"
 version = "0.11.0"
@@ -396,10 +338,19 @@ dependencies = [
 ]
 
 [[package]]
-name = "itoa"
-version = "1.0.9"
+name = "itertools"
+version = "0.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "af150ab688ff2122fcef229be89cb50dd66af9e01a4ff320cc137eecc9bacc38"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "itoa"
+version = "1.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b"
 
 [[package]]
 name = "lazy_static"
@@ -409,15 +360,15 @@ checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
 
 [[package]]
 name = "libc"
-version = "0.2.150"
+version = "0.2.153"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "89d92a4743f9a61002fae18374ed11e7973f530cb3a3255fb354818118b2203c"
+checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
 
 [[package]]
 name = "linux-raw-sys"
-version = "0.4.11"
+version = "0.4.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "969488b55f8ac402214f3f5fd243ebb7206cf82de60d3172994707a4bcc2b829"
+checksum = "01cda141df6706de531b6c46c3a33ecca755538219bd484262fa09410c13539c"
 
 [[package]]
 name = "lock_api"
@@ -431,9 +382,9 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.20"
+version = "0.4.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
+checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
 
 [[package]]
 name = "macro_rules_attribute"
@@ -463,15 +414,15 @@ dependencies = [
 
 [[package]]
 name = "memchr"
-version = "2.6.4"
+version = "2.7.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f665ee40bc4a3c5590afb1e9677db74a508659dfd71e126420da8274909a0167"
+checksum = "6c8640c5d730cb13ebd907d8d04b52f55ac9a2eec55b440c8892f40d56c76c1d"
 
 [[package]]
 name = "memoffset"
-version = "0.9.0"
+version = "0.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5a634b1c61a95585bd15607c6ab0c4e5b226e695ff2800ba0cdccddf208c406c"
+checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
 dependencies = [
  "autocfg",
 ]
@@ -484,9 +435,9 @@ checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
 
 [[package]]
 name = "monostate"
-version = "0.1.9"
+version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "15f370ae88093ec6b11a710dec51321a61d420fafd1bad6e30d01bd9c920e8ee"
+checksum = "a20fffcd8ca4c69d31e036a71abc400147b41f90895df4edcb36497a1f8af8bf"
 dependencies = [
  "monostate-impl",
  "serde",
@@ -494,13 +445,13 @@ dependencies = [
 
 [[package]]
 name = "monostate-impl"
-version = "0.1.9"
+version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "371717c0a5543d6a800cac822eac735aa7d2d2fbb41002e9856a4089532dbdce"
+checksum = "bf307cbbbd777a9c10cec88ddafee572b3484caad5cce0c9236523c3803105a6"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.39",
+ "syn",
 ]
 
 [[package]]
@@ -528,28 +479,27 @@ dependencies = [
 
 [[package]]
 name = "num-complex"
-version = "0.4.4"
+version = "0.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ba157ca0885411de85d6ca030ba7e2a83a28636056c7c699b07c8b6f7383214"
+checksum = "23c6602fda94a57c990fe0df199a035d83576b496aa29f4e634a8ac6004e68a6"
 dependencies = [
  "num-traits",
 ]
 
 [[package]]
 name = "num-integer"
-version = "0.1.45"
+version = "0.1.46"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "225d3389fb3509a24c93f5c29eb6bde2586b98d9f016636dff58d7c6f7569cd9"
+checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f"
 dependencies = [
- "autocfg",
  "num-traits",
 ]
 
 [[package]]
 name = "num-traits"
-version = "0.2.17"
+version = "0.2.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "39e3200413f237f41ab11ad6d161bc7239c84dcb631773ccd7de3dfe4b5c267c"
+checksum = "da0df0e5185db44f69b44f26786fe401b6c293d1907744beaa7fa62b2e5a517a"
 dependencies = [
  "autocfg",
 ]
@@ -562,9 +512,9 @@ checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
 
 [[package]]
 name = "numpy"
-version = "0.19.0"
+version = "0.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "437213adf41bbccf4aeae535fbfcdad0f6fed241e1ae182ebe97fa1f3ce19389"
+checksum = "ec170733ca37175f5d75a5bea5911d6ff45d2cd52849ce98b685394e4f2f37f4"
 dependencies = [
  "libc",
  "ndarray",
@@ -577,9 +527,9 @@ dependencies = [
 
 [[package]]
 name = "once_cell"
-version = "1.18.0"
+version = "1.19.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dd8b5dd2ae5ed71462c540258bedcb51965123ad7e7ccf4b9a8cafaa4a63576d"
+checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
 
 [[package]]
 name = "onig"
@@ -634,15 +584,15 @@ checksum = "de3145af08024dea9fa9914f381a17b8fc6034dfb00f3a84013f7ff43f29ed4c"
 
 [[package]]
 name = "pkg-config"
-version = "0.3.27"
+version = "0.3.30"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26072860ba924cbfa98ea39c8c19b4dd6a4a25423dbdf219c1eca91aa0cf6964"
+checksum = "d231b230927b5e4ad203db57bbcbee2802f6bce620b1e4a9024a07d94e2907ec"
 
 [[package]]
 name = "portable-atomic"
-version = "1.5.1"
+version = "1.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3bccab0e7fd7cc19f820a1c8c91720af652d0c88dc9664dd72aef2614f04af3b"
+checksum = "7170ef9988bc169ba16dd36a7fa041e5c4cbeb6a35b76d4c03daded371eae7c0"
 
 [[package]]
 name = "ppv-lite86"
@@ -652,24 +602,25 @@ checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.69"
+version = "1.0.81"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "134c189feb4956b20f6f547d2cf727d4c0fe06722b20a0eec87ed445a97f92da"
+checksum = "3d1597b0c024618f09a9c3b8655b7e430397a36d23fdafec26d6965e9eec3eba"
 dependencies = [
  "unicode-ident",
 ]
 
 [[package]]
 name = "pyo3"
-version = "0.19.2"
+version = "0.21.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e681a6cfdc4adcc93b4d3cf993749a4552018ee0a9b65fc0ccfad74352c72a38"
+checksum = "a5e00b96a521718e08e03b1a622f01c8a8deb50719335de3f60b3b3950f069d8"
 dependencies = [
  "cfg-if",
  "indoc",
  "libc",
  "memoffset",
  "parking_lot",
+ "portable-atomic",
  "pyo3-build-config",
  "pyo3-ffi",
  "pyo3-macros",
@@ -678,9 +629,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.19.2"
+version = "0.21.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "076c73d0bc438f7a4ef6fdd0c3bb4732149136abd952b110ac93e4edb13a6ba5"
+checksum = "7883df5835fafdad87c0d888b266c8ec0f4c9ca48a5bed6bbb592e8dedee1b50"
 dependencies = [
  "once_cell",
  "target-lexicon",
@@ -688,9 +639,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.19.2"
+version = "0.21.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e53cee42e77ebe256066ba8aa77eff722b3bb91f3419177cf4cd0f304d3284d9"
+checksum = "01be5843dc60b916ab4dad1dca6d20b9b4e6ddc8e15f50c47fe6d85f1fb97403"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -698,32 +649,34 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros"
-version = "0.19.2"
+version = "0.21.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dfeb4c99597e136528c6dd7d5e3de5434d1ceaf487436a3f03b2d56b6fc9efd1"
+checksum = "77b34069fc0682e11b31dbd10321cbf94808394c56fd996796ce45217dfac53c"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
  "quote",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.19.2"
+version = "0.21.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "947dc12175c254889edc0c02e399476c2f652b4b9ebd123aa655c224de259536"
+checksum = "08260721f32db5e1a5beae69a55553f56b99bd0e1c3e6e0a5e8851a9d0f5a85c"
 dependencies = [
+ "heck",
  "proc-macro2",
+ "pyo3-build-config",
  "quote",
- "syn 1.0.109",
+ "syn",
 ]
 
 [[package]]
 name = "quote"
-version = "1.0.33"
+version = "1.0.36"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5267fca4496028628a95160fc423a33e8b2e6af8a5302579e322e4b520293cae"
+checksum = "0fa76aaf39101c457836aec0ce2316dbdc3ab723cdda1c6bd4e6ad4208acaca7"
 dependencies = [
  "proc-macro2",
 ]
@@ -766,9 +719,9 @@ checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3"
 
 [[package]]
 name = "rayon"
-version = "1.8.0"
+version = "1.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9c27db03db7734835b3f53954b534c91069375ce6ccaa2e065441e07d9b6cdb1"
+checksum = "b418a60154510ca1a002a752ca9714984e21e4241e804d32555251faf8b78ffa"
 dependencies = [
  "either",
  "rayon-core",
@@ -781,15 +734,15 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "059f538b55efd2309c9794130bc149c6a553db90e9d99c2030785c82f0bd7df9"
 dependencies = [
  "either",
- "itertools",
+ "itertools 0.11.0",
  "rayon",
 ]
 
 [[package]]
 name = "rayon-core"
-version = "1.12.0"
+version = "1.12.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5ce3fb6ad83f861aac485e76e1985cd109d9a3713802152be56c3b1f0e0658ed"
+checksum = "1465873a3dfdaa8ae7cb14b4383657caab0b3e8a0aa9ae8e04b044854c8dfce2"
 dependencies = [
  "crossbeam-deque",
  "crossbeam-utils",
@@ -806,38 +759,32 @@ dependencies = [
 
 [[package]]
 name = "regex"
-version = "1.10.2"
+version = "1.10.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "380b951a9c5e80ddfd6136919eef32310721aa4aacd4889a8d39124b026ab343"
+checksum = "c117dbdfde9c8308975b6a18d71f3f385c89461f7b3fb054288ecf2a2058ba4c"
 dependencies = [
  "aho-corasick",
  "memchr",
  "regex-automata",
- "regex-syntax 0.8.2",
+ "regex-syntax",
 ]
 
 [[package]]
 name = "regex-automata"
-version = "0.4.3"
+version = "0.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5f804c7828047e88b2d32e2d7fe5a105da8ee3264f01902f796c8e067dc2483f"
+checksum = "86b83b8b9847f9bf95ef68afb0b8e6cdb80f498442f5179a29fad448fcc1eaea"
 dependencies = [
  "aho-corasick",
  "memchr",
- "regex-syntax 0.8.2",
+ "regex-syntax",
 ]
 
 [[package]]
 name = "regex-syntax"
-version = "0.7.5"
+version = "0.8.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dbb5fb1acd8a1a18b3dd5be62d25485eb770e05afb408a9627d14d451bae12da"
-
-[[package]]
-name = "regex-syntax"
-version = "0.8.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c08c74e62047bb2de4ff487b251e4a92e24f48745648451635cec7d591162d9f"
+checksum = "adad44e29e4c806119491a7f06f03de4d1af22c3a680dd47f1e6e179439d1f56"
 
 [[package]]
 name = "rustc-hash"
@@ -847,22 +794,22 @@ checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
 
 [[package]]
 name = "rustix"
-version = "0.38.23"
+version = "0.38.32"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ffb93593068e9babdad10e4fce47dc9b3ac25315a72a59766ffd9e9a71996a04"
+checksum = "65e04861e65f21776e67888bfbea442b3642beaa0138fdb1dd7a84a52dffdb89"
 dependencies = [
- "bitflags 2.4.1",
+ "bitflags 2.5.0",
  "errno",
  "libc",
  "linux-raw-sys",
- "windows-sys 0.48.0",
+ "windows-sys",
 ]
 
 [[package]]
 name = "ryu"
-version = "1.0.15"
+version = "1.0.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ad4cc8da4ef723ed60bced201181d83791ad433213d8c24efffda1eec85d741"
+checksum = "e86697c916019a8588c99b5fac3cead74ec0b4b819707a682fd4d23fa0ce1ba1"
 
 [[package]]
 name = "scopeguard"
@@ -872,29 +819,29 @@ checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
 [[package]]
 name = "serde"
-version = "1.0.192"
+version = "1.0.198"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bca2a08484b285dcb282d0f67b26cadc0df8b19f8c12502c13d966bf9482f001"
+checksum = "9846a40c979031340571da2545a4e5b7c4163bdae79b301d5f86d03979451fcc"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.192"
+version = "1.0.198"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d6c7207fbec9faa48073f3e3074cbe553af6ea512d7c21ba46e434e70ea9fbc1"
+checksum = "e88edab869b01783ba905e7d0153f9fc1a6505a96e4ad3018011eedb838566d9"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.39",
+ "syn",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.108"
+version = "1.0.116"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d1c7e3eac408d115102c4c24ad393e0821bb3a5df4d506a80f85f7a742a526b"
+checksum = "3e17db7126d17feb94eb3fad46bf1a96b034e8aacbc2e775fe81505f8b0b2813"
 dependencies = [
  "itoa",
  "ryu",
@@ -903,9 +850,9 @@ dependencies = [
 
 [[package]]
 name = "smallvec"
-version = "1.11.2"
+version = "1.13.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4dccd0940a2dcdf68d092b8cbab7dc0ad8fa938bf95787e1b916b0e3d0e8e970"
+checksum = "3c5e1a9a646d36c3599cd173a41282daf47c44583ad367b8e6837255952e5c67"
 
 [[package]]
 name = "spm_precompiled"
@@ -927,20 +874,9 @@ checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
 
 [[package]]
 name = "syn"
-version = "1.0.109"
+version = "2.0.60"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "72b64191b275b66ffe2469e8af2c1cfe3bafa67b529ead792a6d0160888b4237"
-dependencies = [
- "proc-macro2",
- "quote",
- "unicode-ident",
-]
-
-[[package]]
-name = "syn"
-version = "2.0.39"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "23e78b90f2fcf45d3e842032ce32e3f2d1545ba6636271dcbf24fa306d87be7a"
+checksum = "909518bc7b1c9b779f1bbf07f2929d35af9f0f37e47c6e9ef7f9dddc1e1821f3"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -949,63 +885,52 @@ dependencies = [
 
 [[package]]
 name = "target-lexicon"
-version = "0.12.12"
+version = "0.12.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "14c39fd04924ca3a864207c66fc2cd7d22d7c016007f9ce846cbb9326331930a"
+checksum = "e1fc403891a21bcfb7c37834ba66a547a8f402146eba7265b5a6d88059c9ff2f"
 
 [[package]]
 name = "tempfile"
-version = "3.8.1"
+version = "3.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7ef1adac450ad7f4b3c28589471ade84f25f731a7a0fe30d71dfa9f60fd808e5"
+checksum = "85b77fafb263dd9d05cbeac119526425676db3784113aa9295c88498cbf8bff1"
 dependencies = [
  "cfg-if",
  "fastrand",
- "redox_syscall",
  "rustix",
- "windows-sys 0.48.0",
-]
-
-[[package]]
-name = "termcolor"
-version = "1.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ff1bc3d3f05aff0403e8ac0d92ced918ec05b666a43f83297ccef5bea8a3d449"
-dependencies = [
- "winapi-util",
+ "windows-sys",
 ]
 
 [[package]]
 name = "thiserror"
-version = "1.0.50"
+version = "1.0.58"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f9a7210f5c9a7156bb50aa36aed4c95afb51df0df00713949448cf9e97d382d2"
+checksum = "03468839009160513471e86a034bb2c5c0e4baae3b43f79ffc55c4a5427b3297"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.50"
+version = "1.0.58"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "266b2e40bc00e5a6c09c3584011e08b06f123c00362c92b975ba9843aaaa14b8"
+checksum = "c61f3ba182994efc43764a46c018c347bc492c79f024e705f46567b418f6d4f7"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.39",
+ "syn",
 ]
 
 [[package]]
 name = "tokenizers"
-version = "0.15.0"
+version = "0.19.1-rc0"
 dependencies = [
  "aho-corasick",
- "clap",
  "derive_builder",
  "esaxx-rs",
  "getrandom",
  "indicatif",
- "itertools",
+ "itertools 0.12.1",
  "lazy_static",
  "log",
  "macro_rules_attribute",
@@ -1016,7 +941,7 @@ dependencies = [
  "rayon",
  "rayon-cond",
  "regex",
- "regex-syntax 0.7.5",
+ "regex-syntax",
  "serde",
  "serde_json",
  "spm_precompiled",
@@ -1028,10 +953,10 @@ dependencies = [
 
 [[package]]
 name = "tokenizers-python"
-version = "0.15.0"
+version = "0.19.1-rc0"
 dependencies = [
  "env_logger",
- "itertools",
+ "itertools 0.12.1",
  "libc",
  "ndarray",
  "numpy",
@@ -1061,9 +986,9 @@ dependencies = [
 
 [[package]]
 name = "unicode-segmentation"
-version = "1.10.1"
+version = "1.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1dd624098567895118886609431a7c3b8f516e41d30e0643f03d94592a147e36"
+checksum = "d4c87d22b6e3f4a18d4d40ef354e97c90fcb14dd91d7dc0aa9d8a1172ebf7202"
 
 [[package]]
 name = "unicode-width"
@@ -1079,9 +1004,9 @@ checksum = "39ec24b3121d976906ece63c9daad25b85969647682eee313cb5779fdd69e14e"
 
 [[package]]
 name = "unindent"
-version = "0.1.11"
+version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e1766d682d402817b5ac4490b3c3002d91dfa0d22812f341609f97b08757359c"
+checksum = "c7de7d73e1754487cb58364ee906a499937a0dfabd86bcb980fa99ec8c8fa2ce"
 
 [[package]]
 name = "utf8parse"
@@ -1095,68 +1020,13 @@ version = "0.11.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
 
-[[package]]
-name = "winapi"
-version = "0.3.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
-dependencies = [
- "winapi-i686-pc-windows-gnu",
- "winapi-x86_64-pc-windows-gnu",
-]
-
-[[package]]
-name = "winapi-i686-pc-windows-gnu"
-version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
-
-[[package]]
-name = "winapi-util"
-version = "0.1.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f29e6f9198ba0d26b4c9f07dbe6f9ed633e1f3d5b8b414090084349e46a52596"
-dependencies = [
- "winapi",
-]
-
-[[package]]
-name = "winapi-x86_64-pc-windows-gnu"
-version = "0.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
-
 [[package]]
 name = "windows-sys"
-version = "0.45.0"
+version = "0.52.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "75283be5efb2831d37ea142365f009c02ec203cd29a3ebecbc093d52315b66d0"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
 dependencies = [
- "windows-targets 0.42.2",
-]
-
-[[package]]
-name = "windows-sys"
-version = "0.48.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
-dependencies = [
- "windows-targets 0.48.5",
-]
-
-[[package]]
-name = "windows-targets"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e5180c00cd44c9b1c88adb3693291f1cd93605ded80c250a75d472756b4d071"
-dependencies = [
- "windows_aarch64_gnullvm 0.42.2",
- "windows_aarch64_msvc 0.42.2",
- "windows_i686_gnu 0.42.2",
- "windows_i686_msvc 0.42.2",
- "windows_x86_64_gnu 0.42.2",
- "windows_x86_64_gnullvm 0.42.2",
- "windows_x86_64_msvc 0.42.2",
+ "windows-targets 0.52.5",
 ]
 
 [[package]]
@@ -1175,10 +1045,20 @@ dependencies = [
 ]
 
 [[package]]
-name = "windows_aarch64_gnullvm"
-version = "0.42.2"
+name = "windows-targets"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "597a5118570b68bc08d8d59125332c54f1ba9d9adeedeef5b99b02ba2b0698f8"
+checksum = "6f0713a46559409d202e70e28227288446bf7841d3211583a4b53e3f6d96e7eb"
+dependencies = [
+ "windows_aarch64_gnullvm 0.52.5",
+ "windows_aarch64_msvc 0.52.5",
+ "windows_i686_gnu 0.52.5",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc 0.52.5",
+ "windows_x86_64_gnu 0.52.5",
+ "windows_x86_64_gnullvm 0.52.5",
+ "windows_x86_64_msvc 0.52.5",
+]
 
 [[package]]
 name = "windows_aarch64_gnullvm"
@@ -1187,10 +1067,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
 
 [[package]]
-name = "windows_aarch64_msvc"
-version = "0.42.2"
+name = "windows_aarch64_gnullvm"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e08e8864a60f06ef0d0ff4ba04124db8b0fb3be5776a5cd47641e942e58c4d43"
+checksum = "7088eed71e8b8dda258ecc8bac5fb1153c5cffaf2578fc8ff5d61e23578d3263"
 
 [[package]]
 name = "windows_aarch64_msvc"
@@ -1199,10 +1079,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
 
 [[package]]
-name = "windows_i686_gnu"
-version = "0.42.2"
+name = "windows_aarch64_msvc"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c61d927d8da41da96a81f029489353e68739737d3beca43145c8afec9a31a84f"
+checksum = "9985fd1504e250c615ca5f281c3f7a6da76213ebd5ccc9561496568a2752afb6"
 
 [[package]]
 name = "windows_i686_gnu"
@@ -1211,10 +1091,16 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
 
 [[package]]
-name = "windows_i686_msvc"
-version = "0.42.2"
+name = "windows_i686_gnu"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44d840b6ec649f480a41c8d80f9c65108b92d89345dd94027bfe06ac444d1060"
+checksum = "88ba073cf16d5372720ec942a8ccbf61626074c6d4dd2e745299726ce8b89670"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87f4261229030a858f36b459e748ae97545d6f1ec60e5e0d6a3d32e0dc232ee9"
 
 [[package]]
 name = "windows_i686_msvc"
@@ -1223,10 +1109,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
 
 [[package]]
-name = "windows_x86_64_gnu"
-version = "0.42.2"
+name = "windows_i686_msvc"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8de912b8b8feb55c064867cf047dda097f92d51efad5b491dfb98f6bbb70cb36"
+checksum = "db3c2bf3d13d5b658be73463284eaf12830ac9a26a90c717b7f771dfe97487bf"
 
 [[package]]
 name = "windows_x86_64_gnu"
@@ -1235,10 +1121,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
 
 [[package]]
-name = "windows_x86_64_gnullvm"
-version = "0.42.2"
+name = "windows_x86_64_gnu"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26d41b46a36d453748aedef1486d5c7a85db22e56aff34643984ea85514e94a3"
+checksum = "4e4246f76bdeff09eb48875a0fd3e2af6aada79d409d33011886d3e1581517d9"
 
 [[package]]
 name = "windows_x86_64_gnullvm"
@@ -1247,13 +1133,19 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
 
 [[package]]
-name = "windows_x86_64_msvc"
-version = "0.42.2"
+name = "windows_x86_64_gnullvm"
+version = "0.52.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9aec5da331524158c6d1a4ac0ab1541149c0b9505fde06423b02f5ef0106b9f0"
+checksum = "852298e482cd67c356ddd9570386e2862b5673c85bd5f88df9ab6802b334c596"
 
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.48.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bec47e5bfd1bff0eeaf6d8b485cc1074891a197ab4225d504cb7a1ab88b02bf0"
diff --git a/pkgs/development/python-modules/tokenizers/default.nix b/pkgs/development/python-modules/tokenizers/default.nix
index a008e15b3704..057190bda983 100644
--- a/pkgs/development/python-modules/tokenizers/default.nix
+++ b/pkgs/development/python-modules/tokenizers/default.nix
@@ -63,16 +63,16 @@ let
 in
 buildPythonPackage rec {
   pname = "tokenizers";
-  version = "0.15.0";
-  format = "pyproject";
+  version = "0.19.1";
+  pyproject = true;
 
   disabled = pythonOlder "3.7";
 
   src = fetchFromGitHub {
     owner = "huggingface";
-    repo = pname;
-    rev = "v${version}";
-    hash = "sha256-+yfX12eKtgZV1OQvPOlMVTONbpFuigHcl4SjoCIZkSk=";
+    repo = "tokenizers";
+    rev = "refs/tags/v${version}";
+    hash = "sha256-sKEAt46cdme821tzz9WSKnQb3hPmFJ4zvHgBNRxjEuk=";
   };
 
   cargoDeps = rustPlatform.importCargoLock {
@@ -97,7 +97,13 @@ buildPythonPackage rec {
     Security
   ];
 
-  propagatedBuildInputs = [
+  # Cargo.lock is outdated
+  # TODO: remove at next release
+  preConfigure = ''
+    cargo update --offline
+  '';
+
+  dependencies = [
     numpy
   ];
 
@@ -123,6 +129,8 @@ buildPythonPackage rec {
 
   disabledTests = [
     # Downloads data using the datasets module
+    "test_encode_special_tokens"
+    "test_splitting"
     "TestTrainFromIterators"
     # Those tests require more data
     "test_from_pretrained"