summary refs log tree commit diff
path: root/pkgs/development/python-modules/tokenizers
diff options
context:
space:
mode:
Diffstat (limited to 'pkgs/development/python-modules/tokenizers')
-rw-r--r--pkgs/development/python-modules/tokenizers/Cargo.lock511
-rw-r--r--pkgs/development/python-modules/tokenizers/default.nix4
2 files changed, 338 insertions, 177 deletions
diff --git a/pkgs/development/python-modules/tokenizers/Cargo.lock b/pkgs/development/python-modules/tokenizers/Cargo.lock
index 841e6b5e095..ced7f153873 100644
--- a/pkgs/development/python-modules/tokenizers/Cargo.lock
+++ b/pkgs/development/python-modules/tokenizers/Cargo.lock
@@ -4,20 +4,59 @@ version = 3
 
 [[package]]
 name = "aho-corasick"
-version = "0.7.20"
+version = "1.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc936419f96fa211c1b9166887b38e5e40b19958e5b895be7c1f93adec7071ac"
+checksum = "ea5d730647d4fadd988536d06fecce94b7b4f2a7efdae548f1cf4b63205518ab"
 dependencies = [
  "memchr",
 ]
 
 [[package]]
-name = "aho-corasick"
-version = "1.0.5"
+name = "anstream"
+version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c378d78423fdad8089616f827526ee33c19f2fddbd5de1629152c9593ba4783"
+checksum = "2ab91ebe16eb252986481c5b62f6098f3b698a45e34b5b98200cf20dd2484a44"
 dependencies = [
- "memchr",
+ "anstyle",
+ "anstyle-parse",
+ "anstyle-query",
+ "anstyle-wincon",
+ "colorchoice",
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7079075b41f533b8c61d2a4d073c4676e1f8b249ff94a393b0595db304e0dd87"
+
+[[package]]
+name = "anstyle-parse"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "317b9a89c1868f5ea6ff1d9539a69f45dffc21ce321ac1fd1160dfa48c8e2140"
+dependencies = [
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle-query"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5ca11d4be1bab0c8bc8734a9aa7bf4ee8316d462a08c6ac5052f888fef5b494b"
+dependencies = [
+ "windows-sys 0.48.0",
+]
+
+[[package]]
+name = "anstyle-wincon"
+version = "3.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0699d10d2f4d628a98ee7b57b289abbc98ff3bad977cb3152709d4bf2330628"
+dependencies = [
+ "anstyle",
+ "windows-sys 0.48.0",
 ]
 
 [[package]]
@@ -46,12 +85,9 @@ checksum = "b4682ae6287fcf752ecaabbfcc7b6f9b72aa33933dc23a554d853aea8eea8635"
 
 [[package]]
 name = "cc"
-version = "1.0.83"
+version = "1.0.79"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f1174fb0b6ec23863f8b971027804a42614e347eafb0a95bf0b12cdae21fc4d0"
-dependencies = [
- "libc",
-]
+checksum = "50d30906286121d95be3d479533b458f87493b30a4b5f79a607db8f5d11aa91f"
 
 [[package]]
 name = "cfg-if"
@@ -60,13 +96,62 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
 
 [[package]]
-name = "crossbeam-channel"
-version = "0.5.8"
+name = "clap"
+version = "4.4.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a33c2bf77f2df06183c3aa30d1e96c0695a313d4f9c453cc3762a6db39f99200"
+checksum = "d04704f56c2cde07f43e8e2c154b43f216dc5c92fc98ada720177362f953b956"
 dependencies = [
- "cfg-if",
- "crossbeam-utils",
+ "clap_builder",
+ "clap_derive",
+]
+
+[[package]]
+name = "clap_builder"
+version = "4.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0e231faeaca65ebd1ea3c737966bf858971cd38c3849107aa3ea7de90a804e45"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "clap_lex",
+ "strsim",
+]
+
+[[package]]
+name = "clap_derive"
+version = "4.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0862016ff20d69b84ef8247369fabf5c008a7417002411897d40ee1f4532b873"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.25",
+]
+
+[[package]]
+name = "clap_lex"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cd7cc57abe963c6d3b9d8be5b06ba7c8957a930305ca90304f24ef040aa6f961"
+
+[[package]]
+name = "colorchoice"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"
+
+[[package]]
+name = "console"
+version = "0.15.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c926e00cc70edefdc64d3a5ff31cc65bb97a3460097762bd23afb4d8145fccf8"
+dependencies = [
+ "encode_unicode",
+ "lazy_static",
+ "libc",
+ "unicode-width",
+ "windows-sys 0.45.0",
 ]
 
 [[package]]
@@ -170,9 +255,15 @@ dependencies = [
 
 [[package]]
 name = "either"
-version = "1.9.0"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7fcaabb2fef8c910e7f4c7ce9f67a1283a1715879a7c230ca9d6d1ae31f16d91"
+
+[[package]]
+name = "encode_unicode"
+version = "0.3.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a26ae43d7bcc3b814de94796a5e736d4029efb0ee900c12e2d54c993ad1a1e07"
+checksum = "a357d28ed41a50f9c765dbfe56cbc04a64e53e5fc58ba79fbc34c10ef3df831f"
 
 [[package]]
 name = "env_logger"
@@ -189,13 +280,13 @@ dependencies = [
 
 [[package]]
 name = "errno"
-version = "0.3.3"
+version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "136526188508e25c6fef639d7927dfb3e0e3084488bf202267829cf7fc23dbdd"
+checksum = "4bcfec3a70f97c962c307b2d2c56e358cf1d00b558d74262b5f929ee8cc7e73a"
 dependencies = [
  "errno-dragonfly",
  "libc",
- "windows-sys",
+ "windows-sys 0.48.0",
 ]
 
 [[package]]
@@ -210,15 +301,18 @@ dependencies = [
 
 [[package]]
 name = "esaxx-rs"
-version = "0.1.8"
+version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1f748b253ceca9fed5f42f8b5ceb3851e93102199bc25b64b65369f76e5c0a35"
+checksum = "d817e038c30374a4bcb22f94d0a8a0e216958d4c3dcde369b1439fec4bdda6e6"
+dependencies = [
+ "cc",
+]
 
 [[package]]
 name = "fastrand"
-version = "2.0.0"
+version = "2.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6999dc1837253364c2ebb0704ba97994bd874e8f195d665c50b7548f6ea92764"
+checksum = "25cbce373ec4653f1a01a31e8a5e5ec0c622dc27ff9c4e6606eefef5cbbed4a5"
 
 [[package]]
 name = "fnv"
@@ -238,6 +332,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "heck"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "95505c38b4572b2d910cecb0281560f54b440a19336cbbcb27bf6ce6adc6f5a8"
+
+[[package]]
 name = "hermit-abi"
 version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -256,45 +356,58 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
 
 [[package]]
+name = "indicatif"
+version = "0.17.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fb28741c9db9a713d93deb3bb9515c20788cef5815265bee4980e87bde7e0f25"
+dependencies = [
+ "console",
+ "instant",
+ "number_prefix",
+ "portable-atomic",
+ "unicode-width",
+]
+
+[[package]]
 name = "indoc"
 version = "1.0.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bfa799dd5ed20a7e349f3b4639aa80d74549c81716d9ec4f994c9b5815598306"
 
 [[package]]
-name = "is-terminal"
-version = "0.4.9"
+name = "instant"
+version = "0.1.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb0889898416213fab133e1d33a0e5858a48177452750691bde3666d0fdbaf8b"
+checksum = "7a5bbe824c507c5da5956355e86a746d82e0e1464f65d862cc5e71da70e94b2c"
 dependencies = [
- "hermit-abi",
- "rustix",
- "windows-sys",
+ "cfg-if",
 ]
 
 [[package]]
-name = "itertools"
-version = "0.8.2"
+name = "is-terminal"
+version = "0.4.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f56a2d0bc861f9165be4eb3442afd3c236d8a98afd426f65d92324ae1091a484"
+checksum = "cb0889898416213fab133e1d33a0e5858a48177452750691bde3666d0fdbaf8b"
 dependencies = [
- "either",
+ "hermit-abi",
+ "rustix",
+ "windows-sys 0.48.0",
 ]
 
 [[package]]
 name = "itertools"
-version = "0.9.0"
+version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "284f18f85651fe11e8a991b2adb42cb078325c996ed026d994719efcfca1d54b"
+checksum = "b1c173a5686ce8bfa551b3563d0c2170bf24ca44da99c7ca4bfdab5418c3fe57"
 dependencies = [
  "either",
 ]
 
 [[package]]
 name = "itoa"
-version = "1.0.9"
+version = "1.0.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "af150ab688ff2122fcef229be89cb50dd66af9e01a4ff320cc137eecc9bacc38"
+checksum = "62b02a5381cc465bd3041d84623d0fa3b66738b52b8e2fc3bab8ad63ab032f4a"
 
 [[package]]
 name = "lazy_static"
@@ -310,9 +423,9 @@ checksum = "b4668fb0ea861c1df094127ac5f1da3409a82116a4ba74fca2e58ef927159bb3"
 
 [[package]]
 name = "linux-raw-sys"
-version = "0.4.5"
+version = "0.4.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "57bcfdad1b858c2db7c38303a6d2ad4dfaf5eb53dfeb0910128b2c26d6158503"
+checksum = "3852614a3bd9ca9804678ba6be5e3b8ce76dfc902cae004e3e0c44051b6e88db"
 
 [[package]]
 name = "lock_api"
@@ -326,15 +439,15 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.20"
+version = "0.4.19"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5e6163cb8c49088c2c36f57875e58ccd8c87c7427f7fbd50ea6710b2f3f2e8f"
+checksum = "b06a4cde4c0f271a446782e3eff8de789548ce57dbc8eca9292c27f4a42004b4"
 
 [[package]]
 name = "macro_rules_attribute"
-version = "0.1.3"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf0c9b980bf4f3a37fd7b1c066941dd1b1d0152ce6ee6e8fe8c49b9f6810d862"
+checksum = "8a82271f7bc033d84bbca59a3ce3e4159938cb08a9c3aebbe54d215131518a13"
 dependencies = [
  "macro_rules_attribute-proc_macro",
  "paste",
@@ -342,18 +455,9 @@ dependencies = [
 
 [[package]]
 name = "macro_rules_attribute-proc_macro"
-version = "0.1.3"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "58093314a45e00c77d5c508f76e77c3396afbbc0d01506e7fae47b018bac2b1d"
-
-[[package]]
-name = "matrixmultiply"
-version = "0.2.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "916806ba0031cd542105d916a97c8572e1fa6dd79c9c51e7eb43a09ec2dd84c1"
-dependencies = [
- "rawpointer",
-]
+checksum = "b8dd856d451cc0da70e2ef2ce95a18e39a93b7558bedf10201ad28503f918568"
 
 [[package]]
 name = "matrixmultiply"
@@ -367,9 +471,9 @@ dependencies = [
 
 [[package]]
 name = "memchr"
-version = "2.6.3"
+version = "2.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f232d6ef707e1956a43342693d2a31e72989554d58299d7a88738cc95b0d35c"
+checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d"
 
 [[package]]
 name = "memoffset"
@@ -404,20 +508,7 @@ checksum = "371717c0a5543d6a800cac822eac735aa7d2d2fbb41002e9856a4089532dbdce"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.31",
-]
-
-[[package]]
-name = "ndarray"
-version = "0.13.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac06db03ec2f46ee0ecdca1a1c34a99c0d188a0d83439b84bf0cb4b386e4ab09"
-dependencies = [
- "matrixmultiply 0.2.4",
- "num-complex 0.2.4",
- "num-integer",
- "num-traits",
- "rawpointer",
+ "syn 2.0.25",
 ]
 
 [[package]]
@@ -426,8 +517,8 @@ version = "0.15.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "adb12d4e967ec485a5f71c6311fe28158e9d6f4bc4a447b474184d0f91a8fa32"
 dependencies = [
- "matrixmultiply 0.3.7",
- "num-complex 0.4.4",
+ "matrixmultiply",
+ "num-complex",
  "num-integer",
  "num-traits",
  "rawpointer",
@@ -445,19 +536,9 @@ dependencies = [
 
 [[package]]
 name = "num-complex"
-version = "0.2.4"
+version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b6b19411a9719e753aff12e5187b74d60d3dc449ec3f4dc21e3989c3f554bc95"
-dependencies = [
- "autocfg",
- "num-traits",
-]
-
-[[package]]
-name = "num-complex"
-version = "0.4.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ba157ca0885411de85d6ca030ba7e2a83a28636056c7c699b07c8b6f7383214"
+checksum = "02e0d21255c828d6f128a1e41534206671e8c3ea0c62f32291e808dc82cff17d"
 dependencies = [
  "num-traits",
 ]
@@ -474,22 +555,18 @@ dependencies = [
 
 [[package]]
 name = "num-traits"
-version = "0.2.16"
+version = "0.2.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f30b0abd723be7e2ffca1272140fac1a2f084c77ec3e123c192b66af1ee9e6c2"
+checksum = "578ede34cf02f8924ab9447f50c28075b4d3e5b269972345e7e0372b38c6cdcd"
 dependencies = [
  "autocfg",
 ]
 
 [[package]]
-name = "num_cpus"
-version = "1.16.0"
+name = "number_prefix"
+version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4161fcb6d602d4d2081af7c3a45852d875a03dd337a6bfdd6e06407b61342a43"
-dependencies = [
- "hermit-abi",
- "libc",
-]
+checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
 
 [[package]]
 name = "numpy"
@@ -498,8 +575,8 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "437213adf41bbccf4aeae535fbfcdad0f6fed241e1ae182ebe97fa1f3ce19389"
 dependencies = [
  "libc",
- "ndarray 0.15.6",
- "num-complex 0.4.4",
+ "ndarray",
+ "num-complex",
  "num-integer",
  "num-traits",
  "pyo3",
@@ -554,7 +631,7 @@ dependencies = [
  "libc",
  "redox_syscall",
  "smallvec",
- "windows-targets",
+ "windows-targets 0.48.1",
 ]
 
 [[package]]
@@ -570,6 +647,12 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "26072860ba924cbfa98ea39c8c19b4dd6a4a25423dbdf219c1eca91aa0cf6964"
 
 [[package]]
+name = "portable-atomic"
+version = "1.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "31114a898e107c51bb1609ffaf55a0e011cf6a4d7f1170d0015a165082c0338b"
+
+[[package]]
 name = "ppv-lite86"
 version = "0.2.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -577,9 +660,9 @@ checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
 
 [[package]]
 name = "proc-macro2"
-version = "1.0.66"
+version = "1.0.64"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "18fb31db3f9bddb2ea821cde30a9f70117e3f119938b5ee630b7403aa6e2ead9"
+checksum = "78803b62cbf1f46fde80d7c0e803111524b9877184cfe7c3033659490ac7a7da"
 dependencies = [
  "unicode-ident",
 ]
@@ -646,9 +729,9 @@ dependencies = [
 
 [[package]]
 name = "quote"
-version = "1.0.33"
+version = "1.0.29"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5267fca4496028628a95160fc423a33e8b2e6af8a5302579e322e4b520293cae"
+checksum = "573015e8ab27661678357f27dc26460738fd2b6c86e46f386fde94cb5d913105"
 dependencies = [
  "proc-macro2",
 ]
@@ -691,9 +774,9 @@ checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3"
 
 [[package]]
 name = "rayon"
-version = "1.7.0"
+version = "1.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1d2df5196e37bcc87abebc0053e20787d73847bb33134a69841207dd0a47f03b"
+checksum = "9c27db03db7734835b3f53954b534c91069375ce6ccaa2e065441e07d9b6cdb1"
 dependencies = [
  "either",
  "rayon-core",
@@ -701,25 +784,23 @@ dependencies = [
 
 [[package]]
 name = "rayon-cond"
-version = "0.1.0"
+version = "0.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fd1259362c9065e5ea39a789ef40b1e3fd934c94beb7b5ab3ac6629d3b5e7cb7"
+checksum = "059f538b55efd2309c9794130bc149c6a553db90e9d99c2030785c82f0bd7df9"
 dependencies = [
  "either",
- "itertools 0.8.2",
+ "itertools",
  "rayon",
 ]
 
 [[package]]
 name = "rayon-core"
-version = "1.11.0"
+version = "1.12.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4b8f95bd6966f5c87776639160a66bd8ab9895d9d4ab01ddba9fc60661aebe8d"
+checksum = "5ce3fb6ad83f861aac485e76e1985cd109d9a3713802152be56c3b1f0e0658ed"
 dependencies = [
- "crossbeam-channel",
  "crossbeam-deque",
  "crossbeam-utils",
- "num_cpus",
 ]
 
 [[package]]
@@ -733,11 +814,11 @@ dependencies = [
 
 [[package]]
 name = "regex"
-version = "1.9.5"
+version = "1.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "697061221ea1b4a94a624f67d0ae2bfe4e22b8a17b6a192afb11046542cc8c47"
+checksum = "b2eae68fc220f7cf2532e4494aded17545fce192d59cd996e0fe7887f4ceb575"
 dependencies = [
- "aho-corasick 1.0.5",
+ "aho-corasick",
  "memchr",
  "regex-automata",
  "regex-syntax",
@@ -745,20 +826,20 @@ dependencies = [
 
 [[package]]
 name = "regex-automata"
-version = "0.3.8"
+version = "0.3.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c2f401f4955220693b56f8ec66ee9c78abffd8d1c4f23dc41a23839eb88f0795"
+checksum = "39354c10dd07468c2e73926b23bb9c2caca74c5501e38a35da70406f1d923310"
 dependencies = [
- "aho-corasick 1.0.5",
+ "aho-corasick",
  "memchr",
  "regex-syntax",
 ]
 
 [[package]]
 name = "regex-syntax"
-version = "0.7.5"
+version = "0.7.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dbb5fb1acd8a1a18b3dd5be62d25485eb770e05afb408a9627d14d451bae12da"
+checksum = "e5ea92a5b6195c6ef2a0295ea818b312502c6fc94dde986c5553242e18fd4ce2"
 
 [[package]]
 name = "rustc-hash"
@@ -768,54 +849,54 @@ checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
 
 [[package]]
 name = "rustix"
-version = "0.38.11"
+version = "0.38.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c0c3dde1fc030af041adc40e79c0e7fbcf431dd24870053d187d7c66e4b87453"
+checksum = "d7db8590df6dfcd144d22afd1b83b36c21a18d7cbc1dc4bb5295a8712e9eb662"
 dependencies = [
  "bitflags 2.4.0",
  "errno",
  "libc",
  "linux-raw-sys",
- "windows-sys",
+ "windows-sys 0.48.0",
 ]
 
 [[package]]
 name = "ryu"
-version = "1.0.15"
+version = "1.0.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1ad4cc8da4ef723ed60bced201181d83791ad433213d8c24efffda1eec85d741"
+checksum = "fe232bdf6be8c8de797b22184ee71118d63780ea42ac85b61d1baa6d3b782ae9"
 
 [[package]]
 name = "scopeguard"
-version = "1.2.0"
+version = "1.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
+checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
 
 [[package]]
 name = "serde"
-version = "1.0.188"
+version = "1.0.171"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf9e0fcba69a370eed61bcf2b728575f726b50b55cba78064753d708ddc7549e"
+checksum = "30e27d1e4fd7659406c492fd6cfaf2066ba8773de45ca75e855590f856dc34a9"
 dependencies = [
  "serde_derive",
 ]
 
 [[package]]
 name = "serde_derive"
-version = "1.0.188"
+version = "1.0.171"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4eca7ac642d82aa35b60049a6eccb4be6be75e599bd2e9adb5f875a737654af2"
+checksum = "389894603bd18c46fa56231694f8d827779c0951a667087194cf9de94ed24682"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.31",
+ "syn 2.0.25",
 ]
 
 [[package]]
 name = "serde_json"
-version = "1.0.105"
+version = "1.0.102"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "693151e1ac27563d6dbcec9dee9fbd5da8539b20fa14ad3752b2e6d363ace360"
+checksum = "b5062a995d481b2308b6064e9af76011f2921c35f97b0468811ed9f6cd91dfed"
 dependencies = [
  "itoa",
  "ryu",
@@ -859,9 +940,9 @@ dependencies = [
 
 [[package]]
 name = "syn"
-version = "2.0.31"
+version = "2.0.25"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "718fa2415bcb8d8bd775917a1bf12a7931b6dfa890753378538118181e0cb398"
+checksum = "15e3fc8c0c74267e2df136e5e5fb656a464158aa57624053375eb9c8c6e25ae2"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -870,9 +951,9 @@ dependencies = [
 
 [[package]]
 name = "target-lexicon"
-version = "0.12.11"
+version = "0.12.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9d0e916b1148c8e263850e1ebcbd046f333e0683c724876bb0da63ea4373dc8a"
+checksum = "df8e77cb757a61f51b947ec4a7e3646efd825b73561db1c232a8ccb639e611a0"
 
 [[package]]
 name = "tempfile"
@@ -884,7 +965,7 @@ dependencies = [
  "fastrand",
  "redox_syscall",
  "rustix",
- "windows-sys",
+ "windows-sys 0.48.0",
 ]
 
 [[package]]
@@ -898,33 +979,35 @@ dependencies = [
 
 [[package]]
 name = "thiserror"
-version = "1.0.48"
+version = "1.0.49"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9d6d7a740b8a666a7e828dd00da9c0dc290dff53154ea77ac109281de90589b7"
+checksum = "1177e8c6d7ede7afde3585fd2513e611227efd6481bd78d2e82ba1ce16557ed4"
 dependencies = [
  "thiserror-impl",
 ]
 
 [[package]]
 name = "thiserror-impl"
-version = "1.0.48"
+version = "1.0.49"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "49922ecae66cc8a249b77e68d1d0623c1b2c514f0060c27cdc68bd62a1219d35"
+checksum = "10712f02019e9288794769fba95cd6847df9874d49d871d062172f9dd41bc4cc"
 dependencies = [
  "proc-macro2",
  "quote",
- "syn 2.0.31",
+ "syn 2.0.25",
 ]
 
 [[package]]
 name = "tokenizers"
-version = "0.14.0"
+version = "0.14.1"
 dependencies = [
- "aho-corasick 0.7.20",
+ "aho-corasick",
+ "clap",
  "derive_builder",
  "esaxx-rs",
  "getrandom",
- "itertools 0.9.0",
+ "indicatif",
+ "itertools",
  "lazy_static",
  "log",
  "macro_rules_attribute",
@@ -947,12 +1030,12 @@ dependencies = [
 
 [[package]]
 name = "tokenizers-python"
-version = "0.14.0"
+version = "0.14.1"
 dependencies = [
  "env_logger",
- "itertools 0.9.0",
+ "itertools",
  "libc",
- "ndarray 0.13.1",
+ "ndarray",
  "numpy",
  "onig",
  "pyo3",
@@ -965,9 +1048,9 @@ dependencies = [
 
 [[package]]
 name = "unicode-ident"
-version = "1.0.11"
+version = "1.0.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "301abaae475aa91687eb82514b328ab47a211a533026cb25fc3e519b86adfc3c"
+checksum = "22049a19f4a68748a168c0fc439f9516686aa045927ff767eca0a85101fb6e73"
 
 [[package]]
 name = "unicode-normalization-alignments"
@@ -985,6 +1068,12 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1dd624098567895118886609431a7c3b8f516e41d30e0643f03d94592a147e36"
 
 [[package]]
+name = "unicode-width"
+version = "0.1.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e51733f11c9c4f72aa0c160008246859e340b00807569a0da0e7a1079b27ba85"
+
+[[package]]
 name = "unicode_categories"
 version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -997,6 +1086,12 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e1766d682d402817b5ac4490b3c3002d91dfa0d22812f341609f97b08757359c"
 
 [[package]]
+name = "utf8parse"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"
+
+[[package]]
 name = "wasi"
 version = "0.11.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1035,66 +1130,132 @@ checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
 
 [[package]]
 name = "windows-sys"
+version = "0.45.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "75283be5efb2831d37ea142365f009c02ec203cd29a3ebecbc093d52315b66d0"
+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",
+ "windows-targets 0.48.1",
 ]
 
 [[package]]
 name = "windows-targets"
-version = "0.48.5"
+version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
+checksum = "8e5180c00cd44c9b1c88adb3693291f1cd93605ded80c250a75d472756b4d071"
 dependencies = [
- "windows_aarch64_gnullvm",
- "windows_aarch64_msvc",
- "windows_i686_gnu",
- "windows_i686_msvc",
- "windows_x86_64_gnu",
- "windows_x86_64_gnullvm",
- "windows_x86_64_msvc",
+ "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",
 ]
 
 [[package]]
+name = "windows-targets"
+version = "0.48.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "05d4b17490f70499f20b9e791dcf6a299785ce8af4d709018206dc5b4953e95f"
+dependencies = [
+ "windows_aarch64_gnullvm 0.48.0",
+ "windows_aarch64_msvc 0.48.0",
+ "windows_i686_gnu 0.48.0",
+ "windows_i686_msvc 0.48.0",
+ "windows_x86_64_gnu 0.48.0",
+ "windows_x86_64_gnullvm 0.48.0",
+ "windows_x86_64_msvc 0.48.0",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "597a5118570b68bc08d8d59125332c54f1ba9d9adeedeef5b99b02ba2b0698f8"
+
+[[package]]
 name = "windows_aarch64_gnullvm"
-version = "0.48.5"
+version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
+checksum = "91ae572e1b79dba883e0d315474df7305d12f569b400fcf90581b06062f7e1bc"
 
 [[package]]
 name = "windows_aarch64_msvc"
-version = "0.48.5"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e08e8864a60f06ef0d0ff4ba04124db8b0fb3be5776a5cd47641e942e58c4d43"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2ef27e0d7bdfcfc7b868b317c1d32c641a6fe4629c171b8928c7b08d98d7cf3"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
+checksum = "c61d927d8da41da96a81f029489353e68739737d3beca43145c8afec9a31a84f"
 
 [[package]]
 name = "windows_i686_gnu"
-version = "0.48.5"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "622a1962a7db830d6fd0a69683c80a18fda201879f0f447f065a3b7467daa241"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
+checksum = "44d840b6ec649f480a41c8d80f9c65108b92d89345dd94027bfe06ac444d1060"
 
 [[package]]
 name = "windows_i686_msvc"
-version = "0.48.5"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4542c6e364ce21bf45d69fdd2a8e455fa38d316158cfd43b3ac1c5b1b19f8e00"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
+checksum = "8de912b8b8feb55c064867cf047dda097f92d51efad5b491dfb98f6bbb70cb36"
 
 [[package]]
 name = "windows_x86_64_gnu"
-version = "0.48.5"
+version = "0.48.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ca2b8a661f7628cbd23440e50b05d705db3686f894fc9580820623656af974b1"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
+checksum = "26d41b46a36d453748aedef1486d5c7a85db22e56aff34643984ea85514e94a3"
 
 [[package]]
 name = "windows_x86_64_gnullvm"
-version = "0.48.5"
+version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
+checksum = "7896dbc1f41e08872e9d5e8f8baa8fdd2677f29468c4e156210174edc7f7b953"
 
 [[package]]
 name = "windows_x86_64_msvc"
-version = "0.48.5"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9aec5da331524158c6d1a4ac0ab1541149c0b9505fde06423b02f5ef0106b9f0"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
+checksum = "1a515f5799fe4961cb532f983ce2b23082366b898e52ffbce459c86f67c8378a"
diff --git a/pkgs/development/python-modules/tokenizers/default.nix b/pkgs/development/python-modules/tokenizers/default.nix
index 149f86a284f..d8a731825fe 100644
--- a/pkgs/development/python-modules/tokenizers/default.nix
+++ b/pkgs/development/python-modules/tokenizers/default.nix
@@ -60,7 +60,7 @@ let
 in
 buildPythonPackage rec {
   pname = "tokenizers";
-  version = "0.14.0";
+  version = "0.14.1";
   format = "pyproject";
 
   disabled = pythonOlder "3.7";
@@ -69,7 +69,7 @@ buildPythonPackage rec {
     owner = "huggingface";
     repo = pname;
     rev = "v${version}";
-    hash = "sha256-zCpKNMzIdQ0lLWdn4cENtBEMTA7+fg+N6wQGvio9llE=";
+    hash = "sha256-cq7dQLttNkV5UUhXujxKKMuzhD7hz+zTTKxUKlvz1s0=";
   };
 
   cargoDeps = rustPlatform.importCargoLock {