diff --git a/pkgs/development/python-modules/tokenizers/Cargo.lock b/pkgs/development/python-modules/tokenizers/Cargo.lock
new file mode 100644
index 000000000000..165fc03a65ff
--- /dev/null
+++ b/pkgs/development/python-modules/tokenizers/Cargo.lock
@@ -0,0 +1,1334 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "ahash"
+version = "0.8.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
+dependencies = [
+ "cfg-if",
+ "getrandom",
+ "once_cell",
+ "serde",
+ "version_check",
+ "zerocopy",
+]
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "anstream"
+version = "0.6.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "301af1932e46185686725e0fad2f8f2aa7da69dd70bf6ecc44d6b703844a3933"
+dependencies = [
+ "anstyle",
+ "anstyle-parse",
+ "anstyle-query",
+ "anstyle-wincon",
+ "colorchoice",
+ "is_terminal_polyfill",
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle"
+version = "1.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "862ed96ca487e809f1c8e5a8447f6ee2cf102f846893800b20cebdf541fc6bbd"
+
+[[package]]
+name = "anstyle-parse"
+version = "0.2.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4e7644824f0aa2c7b9384579234ef10eb7efb6a0deb83f9630a49594dd9c15c2"
+dependencies = [
+ "utf8parse",
+]
+
+[[package]]
+name = "anstyle-query"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c8bdeb6047d8983be085bab0ba1472e6dc604e7041dbf6fcd5e71523014fae9"
+dependencies = [
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "anstyle-wincon"
+version = "3.0.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "403f75924867bb1033c59fbf0797484329750cfbe3c4325cd33127941fabc882"
+dependencies = [
+ "anstyle",
+ "once_cell_polyfill",
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "autocfg"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+
+[[package]]
+name = "base64"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9e1b586273c5702936fe7b7d6896644d8be71e6314cfe09d3167c95f712589e8"
+
+[[package]]
+name = "bitflags"
+version = "2.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b8e56985ec62d17e9c1001dc89c88ecd7dc08e47eba5ec7c29c7b5eeecde967"
+
+[[package]]
+name = "bumpalo"
+version = "3.18.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "793db76d6187cd04dff33004d8e6c9cc4e05cd330500379d2394209271b4aeee"
+
+[[package]]
+name = "castaway"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0abae9be0aaf9ea96a3b1b8b1b55c602ca751eba1b1500220cea4ecbafe7c0d5"
+dependencies = [
+ "rustversion",
+]
+
+[[package]]
+name = "cc"
+version = "1.2.27"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d487aa071b5f64da6f19a3e848e3578944b726ee5a4854b82172f02aa876bfdc"
+dependencies = [
+ "shlex",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9555578bc9e57714c812a1f84e4fc5b4d21fcb063490c624de019f7464c91268"
+
+[[package]]
+name = "colorchoice"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b05b61dc5112cbb17e4b6cd61790d9845d13888356391624cbe7e41efeac1e75"
+
+[[package]]
+name = "compact_str"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3fdb1325a1cece981e8a296ab8f0f9b63ae357bd0784a9faaf548cc7b480707a"
+dependencies = [
+ "castaway",
+ "cfg-if",
+ "itoa",
+ "rustversion",
+ "ryu",
+ "serde",
+ "static_assertions",
+]
+
+[[package]]
+name = "console"
+version = "0.15.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "054ccb5b10f9f2cbf51eb355ca1d05c2d279ce1804688d0db74b4733a5aeafd8"
+dependencies = [
+ "encode_unicode",
+ "libc",
+ "once_cell",
+ "unicode-width",
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "crossbeam-deque"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51"
+dependencies = [
+ "crossbeam-epoch",
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-epoch"
+version = "0.9.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
+dependencies = [
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-utils"
+version = "0.8.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
+
+[[package]]
+name = "darling"
+version = "0.20.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc7f46116c46ff9ab3eb1597a45688b6715c6e628b5c133e288e709a29bcb4ee"
+dependencies = [
+ "darling_core",
+ "darling_macro",
+]
+
+[[package]]
+name = "darling_core"
+version = "0.20.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d00b9596d185e565c2207a0b01f8bd1a135483d02d9b7b0a54b11da8d53412e"
+dependencies = [
+ "fnv",
+ "ident_case",
+ "proc-macro2",
+ "quote",
+ "strsim",
+ "syn",
+]
+
+[[package]]
+name = "darling_macro"
+version = "0.20.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc34b93ccb385b40dc71c6fceac4b2ad23662c7eeb248cf10d529b7e055b6ead"
+dependencies = [
+ "darling_core",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "dary_heap"
+version = "0.3.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "04d2cd9c18b9f454ed67da600630b021a8a80bf33f8c95896ab33aaf1c26b728"
+dependencies = [
+ "serde",
+]
+
+[[package]]
+name = "derive_builder"
+version = "0.20.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "507dfb09ea8b7fa618fcf76e953f4f5e192547945816d5358edffe39f6f94947"
+dependencies = [
+ "derive_builder_macro",
+]
+
+[[package]]
+name = "derive_builder_core"
+version = "0.20.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2d5bcf7b024d6835cfb3d473887cd966994907effbe9227e8c8219824d06c4e8"
+dependencies = [
+ "darling",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "derive_builder_macro"
+version = "0.20.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ab63b0e2bf4d5928aff72e83a7dace85d7bba5fe12dcc3c5a572d78caffd3f3c"
+dependencies = [
+ "derive_builder_core",
+ "syn",
+]
+
+[[package]]
+name = "either"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+
+[[package]]
+name = "encode_unicode"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34aa73646ffb006b8f5147f3dc182bd4bcb190227ce861fc4a4844bf8e3cb2c0"
+
+[[package]]
+name = "env_filter"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "186e05a59d4c50738528153b83b0b0194d3a29507dfec16eccd4b342903397d0"
+dependencies = [
+ "log",
+ "regex",
+]
+
+[[package]]
+name = "env_logger"
+version = "0.11.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13c863f0904021b108aa8b2f55046443e6b1ebde8fd4a15c399893aae4fa069f"
+dependencies = [
+ "anstream",
+ "anstyle",
+ "env_filter",
+ "jiff",
+ "log",
+]
+
+[[package]]
+name = "errno"
+version = "0.3.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "778e2ac28f6c47af28e4907f13ffd1e1ddbd400980a9abd7c8df189bf578a5ad"
+dependencies = [
+ "libc",
+ "windows-sys 0.60.2",
+]
+
+[[package]]
+name = "esaxx-rs"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d817e038c30374a4bcb22f94d0a8a0e216958d4c3dcde369b1439fec4bdda6e6"
+dependencies = [
+ "cc",
+]
+
+[[package]]
+name = "fastrand"
+version = "2.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
+
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
+[[package]]
+name = "getrandom"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26145e563e54f2cadc477553f1ec5ee650b00862f0a58bcd12cbdc5f0ea2d2f4"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+ "wasi",
+]
+
+[[package]]
+name = "heck"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
+
+[[package]]
+name = "ident_case"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
+
+[[package]]
+name = "indicatif"
+version = "0.17.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "183b3088984b400f4cfac3620d5e076c84da5364016b4f49473de574b2586235"
+dependencies = [
+ "console",
+ "number_prefix",
+ "portable-atomic",
+ "unicode-width",
+ "web-time",
+]
+
+[[package]]
+name = "indoc"
+version = "2.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd"
+
+[[package]]
+name = "is_terminal_polyfill"
+version = "1.70.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
+
+[[package]]
+name = "itertools"
+version = "0.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b192c782037fadd9cfa75548310488aabdbf3d2da73885b31bd0abd03351285"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "itoa"
+version = "1.0.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
+
+[[package]]
+name = "jiff"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be1f93b8b1eb69c77f24bbb0afdf66f54b632ee39af40ca21c4365a1d7347e49"
+dependencies = [
+ "jiff-static",
+ "log",
+ "portable-atomic",
+ "portable-atomic-util",
+ "serde",
+]
+
+[[package]]
+name = "jiff-static"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "03343451ff899767262ec32146f6d559dd759fdadf42ff0e227c7c48f72594b4"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "js-sys"
+version = "0.3.77"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1cfaf33c695fc6e08064efbc1f72ec937429614f25eef83af942d0e227c3a28f"
+dependencies = [
+ "once_cell",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.174"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1171693293099992e19cddea4e8b849964e9846f4acee11b3948bcc337be8776"
+
+[[package]]
+name = "linux-raw-sys"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cd945864f07fe9f5371a27ad7b52a172b4b499999f1d97574c9fa68373937e12"
+
+[[package]]
+name = "log"
+version = "0.4.27"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13dc2df351e3202783a1fe0d44375f7295ffb4049267b0f3018346dc122a1d94"
+
+[[package]]
+name = "macro_rules_attribute"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65049d7923698040cd0b1ddcced9b0eb14dd22c5f86ae59c3740eab64a676520"
+dependencies = [
+ "macro_rules_attribute-proc_macro",
+ "paste",
+]
+
+[[package]]
+name = "macro_rules_attribute-proc_macro"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "670fdfda89751bc4a84ac13eaa63e205cf0fd22b4c9a5fbfa085b63c1f1d3a30"
+
+[[package]]
+name = "matrixmultiply"
+version = "0.3.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a06de3016e9fae57a36fd14dba131fccf49f74b40b7fbdb472f96e361ec71a08"
+dependencies = [
+ "autocfg",
+ "rawpointer",
+]
+
+[[package]]
+name = "memchr"
+version = "2.7.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a282da65faaf38286cf3be983213fcf1d2e2a58700e808f83f4ea9a4804bc0"
+
+[[package]]
+name = "memoffset"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
+[[package]]
+name = "monostate"
+version = "0.1.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "aafe1be9d0c75642e3e50fedc7ecadf1ef1cbce6eb66462153fc44245343fbee"
+dependencies = [
+ "monostate-impl",
+ "serde",
+]
+
+[[package]]
+name = "monostate-impl"
+version = "0.1.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c402a4092d5e204f32c9e155431046831fa712637043c58cb73bc6bc6c9663b5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "ndarray"
+version = "0.16.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "882ed72dce9365842bf196bdeedf5055305f11fc8c03dee7bb0194a6cad34841"
+dependencies = [
+ "matrixmultiply",
+ "num-complex",
+ "num-integer",
+ "num-traits",
+ "portable-atomic",
+ "portable-atomic-util",
+ "rawpointer",
+]
+
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
+[[package]]
+name = "num-complex"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-integer"
+version = "0.1.46"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "number_prefix"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830b246a0e5f20af87141b25c173cd1b609bd7779a4617d6ec582abaf90870f3"
+
+[[package]]
+name = "numpy"
+version = "0.25.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29f1dee9aa8d3f6f8e8b9af3803006101bb3653866ef056d530d53ae68587191"
+dependencies = [
+ "libc",
+ "ndarray",
+ "num-complex",
+ "num-integer",
+ "num-traits",
+ "pyo3",
+ "pyo3-build-config",
+ "rustc-hash",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
+
+[[package]]
+name = "once_cell_polyfill"
+version = "1.70.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4895175b425cb1f87721b59f0f286c2092bd4af812243672510e1ac53e2e0ad"
+
+[[package]]
+name = "onig"
+version = "6.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "336b9c63443aceef14bea841b899035ae3abe89b7c486aaf4c5bd8aafedac3f0"
+dependencies = [
+ "bitflags",
+ "libc",
+ "once_cell",
+ "onig_sys",
+]
+
+[[package]]
+name = "onig_sys"
+version = "69.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7f86c6eef3d6df15f23bcfb6af487cbd2fed4e5581d58d5bf1f5f8b7f6727dc"
+dependencies = [
+ "cc",
+ "pkg-config",
+]
+
+[[package]]
+name = "paste"
+version = "1.0.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a"
+
+[[package]]
+name = "pkg-config"
+version = "0.3.32"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c"
+
+[[package]]
+name = "portable-atomic"
+version = "1.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f84267b20a16ea918e43c6a88433c2d54fa145c92a811b5b047ccbe153674483"
+
+[[package]]
+name = "portable-atomic-util"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d8a2f0d8d040d7848a709caf78912debcc3f33ee4b3cac47d73d1e1069e83507"
+dependencies = [
+ "portable-atomic",
+]
+
+[[package]]
+name = "ppv-lite86"
+version = "0.2.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9"
+dependencies = [
+ "zerocopy",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.95"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "02b3e5e68a3a1a02aad3ec490a98007cbc13c37cbe84a3cd7b8e406d76e7f778"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "pyo3"
+version = "0.25.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8970a78afe0628a3e3430376fc5fd76b6b45c4d43360ffd6cdd40bdde72b682a"
+dependencies = [
+ "indoc",
+ "libc",
+ "memoffset",
+ "once_cell",
+ "portable-atomic",
+ "pyo3-build-config",
+ "pyo3-ffi",
+ "pyo3-macros",
+ "unindent",
+]
+
+[[package]]
+name = "pyo3-build-config"
+version = "0.25.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "458eb0c55e7ece017adeba38f2248ff3ac615e53660d7c71a238d7d2a01c7598"
+dependencies = [
+ "once_cell",
+ "target-lexicon",
+]
+
+[[package]]
+name = "pyo3-ffi"
+version = "0.25.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7114fe5457c61b276ab77c5055f206295b812608083644a5c5b2640c3102565c"
+dependencies = [
+ "libc",
+ "pyo3-build-config",
+]
+
+[[package]]
+name = "pyo3-macros"
+version = "0.25.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a8725c0a622b374d6cb051d11a0983786448f7785336139c3c94f5aa6bef7e50"
+dependencies = [
+ "proc-macro2",
+ "pyo3-macros-backend",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "pyo3-macros-backend"
+version = "0.25.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4109984c22491085343c05b0dbc54ddc405c3cf7b4374fc533f5c3313a572ccc"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "pyo3-build-config",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.40"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1885c039570dc00dcb4ff087a89e185fd56bae234ddc7f056a945bf36467248d"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
+[[package]]
+name = "rand"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9fbfd9d094a40bf3ae768db9361049ace4c0e04a4fd6b359518bd7b73a73dd97"
+dependencies = [
+ "rand_chacha",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
+dependencies = [
+ "ppv-lite86",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.9.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "99d9a13982dcf210057a8a78572b2217b667c3beacbf3a0d8b454f6f82837d38"
+dependencies = [
+ "getrandom",
+]
+
+[[package]]
+name = "rawpointer"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3"
+
+[[package]]
+name = "rayon"
+version = "1.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b418a60154510ca1a002a752ca9714984e21e4241e804d32555251faf8b78ffa"
+dependencies = [
+ "either",
+ "rayon-core",
+]
+
+[[package]]
+name = "rayon-cond"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2964d0cf57a3e7a06e8183d14a8b527195c706b7983549cd5462d5aa3747438f"
+dependencies = [
+ "either",
+ "itertools",
+ "rayon",
+]
+
+[[package]]
+name = "rayon-core"
+version = "1.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1465873a3dfdaa8ae7cb14b4383657caab0b3e8a0aa9ae8e04b044854c8dfce2"
+dependencies = [
+ "crossbeam-deque",
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "regex"
+version = "1.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b544ef1b4eac5dc2db33ea63606ae9ffcfac26c1416a2806ae0bf5f56b201191"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "809e8dc61f6de73b46c85f4c96486310fe304c434cfa43669d7b40f711150908"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c"
+
+[[package]]
+name = "rustc-hash"
+version = "2.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "357703d41365b4b27c590e3ed91eabb1b663f07c4c084095e60cbed4362dff0d"
+
+[[package]]
+name = "rustix"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c71e83d6afe7ff64890ec6b71d6a69bb8a610ab78ce364b3352876bb4c801266"
+dependencies = [
+ "bitflags",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "rustversion"
+version = "1.0.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a0d197bd2c9dc6e53b84da9556a69ba4cdfab8619eb41a8bd1cc2027a0f6b1d"
+
+[[package]]
+name = "ryu"
+version = "1.0.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f"
+
+[[package]]
+name = "serde"
+version = "1.0.219"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.219"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.140"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373"
+dependencies = [
+ "itoa",
+ "memchr",
+ "ryu",
+ "serde",
+]
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "smallvec"
+version = "1.15.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03"
+
+[[package]]
+name = "spm_precompiled"
+version = "0.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5851699c4033c63636f7ea4cf7b7c1f1bf06d0cc03cfb42e711de5a5c46cf326"
+dependencies = [
+ "base64",
+ "nom",
+ "serde",
+ "unicode-segmentation",
+]
+
+[[package]]
+name = "static_assertions"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
+
+[[package]]
+name = "strsim"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
+
+[[package]]
+name = "syn"
+version = "2.0.104"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "17b6f705963418cdb9927482fa304bc562ece2fdd4f616084c50b7023b435a40"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "target-lexicon"
+version = "0.13.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e502f78cdbb8ba4718f566c418c52bc729126ffd16baee5baa718cf25dd5a69a"
+
+[[package]]
+name = "tempfile"
+version = "3.20.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e8a64e3985349f2441a1a9ef0b853f869006c3855f2cda6862a94d26ebb9d6a1"
+dependencies = [
+ "fastrand",
+ "getrandom",
+ "once_cell",
+ "rustix",
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "thiserror"
+version = "2.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "567b8a2dae586314f7be2a752ec7474332959c6460e02bde30d702a66d488708"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "2.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f7cf42b4507d8ea322120659672cf1b9dbb93f8f2d4ecfd6e51350ff5b17a1d"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "tokenizers"
+version = "0.21.2"
+dependencies = [
+ "ahash",
+ "aho-corasick",
+ "compact_str",
+ "dary_heap",
+ "derive_builder",
+ "esaxx-rs",
+ "getrandom",
+ "indicatif",
+ "itertools",
+ "log",
+ "macro_rules_attribute",
+ "monostate",
+ "onig",
+ "paste",
+ "rand",
+ "rayon",
+ "rayon-cond",
+ "regex",
+ "regex-syntax",
+ "serde",
+ "serde_json",
+ "spm_precompiled",
+ "thiserror",
+ "unicode-normalization-alignments",
+ "unicode-segmentation",
+ "unicode_categories",
+]
+
+[[package]]
+name = "tokenizers-python"
+version = "0.21.2"
+dependencies = [
+ "ahash",
+ "env_logger",
+ "itertools",
+ "libc",
+ "ndarray",
+ "numpy",
+ "pyo3",
+ "rayon",
+ "serde",
+ "serde_json",
+ "tempfile",
+ "tokenizers",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512"
+
+[[package]]
+name = "unicode-normalization-alignments"
+version = "0.1.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "43f613e4fa046e69818dd287fdc4bc78175ff20331479dab6e1b0f98d57062de"
+dependencies = [
+ "smallvec",
+]
+
+[[package]]
+name = "unicode-segmentation"
+version = "1.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493"
+
+[[package]]
+name = "unicode-width"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a1a07cc7db3810833284e8d372ccdc6da29741639ecc70c9ec107df0fa6154c"
+
+[[package]]
+name = "unicode_categories"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "39ec24b3121d976906ece63c9daad25b85969647682eee313cb5779fdd69e14e"
+
+[[package]]
+name = "unindent"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"
+
+[[package]]
+name = "utf8parse"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
+
+[[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
+[[package]]
+name = "wasi"
+version = "0.14.2+wasi-0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9683f9a5a998d873c0d21fcbe3c083009670149a8fab228644b8bd36b2c48cb3"
+dependencies = [
+ "wit-bindgen-rt",
+]
+
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1edc8929d7499fc4e8f0be2262a241556cfc54a0bea223790e71446f2aab1ef5"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+ "wasm-bindgen-macro",
+]
+
+[[package]]
+name = "wasm-bindgen-backend"
+version = "0.2.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f0a0651a5c2bc21487bde11ee802ccaf4c51935d0d3d42a6101f98161700bc6"
+dependencies = [
+ "bumpalo",
+ "log",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7fe63fc6d09ed3792bd0897b314f53de8e16568c2b3f7982f468c0bf9bd0b407"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ae87ea40c9f689fc23f209965b6fb8a99ad69aeeb0231408be24920604395de"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-backend",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.100"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a05d73b933a847d6cccdda8f838a22ff101ad9bf93e33684f39c1f5f0eece3d"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "web-time"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a6580f308b1fad9207618087a65c04e7a10bc77e02c8e84e9b00dd4b12fa0bb"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.59.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b"
+dependencies = [
+ "windows-targets 0.52.6",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.60.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2f500e4d28234f72040990ec9d39e3a6b950f9f22d3dba18416c35882612bcb"
+dependencies = [
+ "windows-targets 0.53.2",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm 0.52.6",
+ "windows_aarch64_msvc 0.52.6",
+ "windows_i686_gnu 0.52.6",
+ "windows_i686_gnullvm 0.52.6",
+ "windows_i686_msvc 0.52.6",
+ "windows_x86_64_gnu 0.52.6",
+ "windows_x86_64_gnullvm 0.52.6",
+ "windows_x86_64_msvc 0.52.6",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.53.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c66f69fcc9ce11da9966ddb31a40968cad001c5bedeb5c2b82ede4253ab48aef"
+dependencies = [
+ "windows_aarch64_gnullvm 0.53.0",
+ "windows_aarch64_msvc 0.53.0",
+ "windows_i686_gnu 0.53.0",
+ "windows_i686_gnullvm 0.53.0",
+ "windows_i686_msvc 0.53.0",
+ "windows_x86_64_gnu 0.53.0",
+ "windows_x86_64_gnullvm 0.53.0",
+ "windows_x86_64_msvc 0.53.0",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86b8d5f90ddd19cb4a147a5fa63ca848db3df085e25fee3cc10b39b6eebae764"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7651a1f62a11b8cbd5e0d42526e55f2c99886c77e007179efff86c2b137e66c"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c1dc67659d35f387f5f6c479dc4e28f1d4bb90ddd1a5d3da2e5d97b42d6272c3"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ce6ccbdedbf6d6354471319e781c0dfef054c81fbc7cf83f338a4296c0cae11"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "581fee95406bb13382d2f65cd4a908ca7b1e4c2f1917f143ba16efe98a589b5d"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2e55b5ac9ea33f2fc1716d1742db15574fd6fc8dadc51caab1c16a3d3b4190ba"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0a6e035dd0599267ce1ee132e51c27dd29437f63325753051e71dd9e42406c57"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.53.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "271414315aff87387382ec3d271b52d7ae78726f5d44ac98b4f4030c91880486"
+
+[[package]]
+name = "wit-bindgen-rt"
+version = "0.39.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "zerocopy"
+version = "0.8.26"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1039dd0d3c310cf05de012d8a39ff557cb0d23087fd44cad61df08fc31907a2f"
+dependencies = [
+ "zerocopy-derive",
+]
+
+[[package]]
+name = "zerocopy-derive"
+version = "0.8.26"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ecf5b4cc5364572d7f4c329661bcc82724222973f2cab6f050a4e5c22f75181"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
diff --git a/pkgs/development/python-modules/tokenizers/default.nix b/pkgs/development/python-modules/tokenizers/default.nix
index dcc687cb5ca2..ec5c76768f20 100644
--- a/pkgs/development/python-modules/tokenizers/default.nix
+++ b/pkgs/development/python-modules/tokenizers/default.nix
@@ -47,6 +47,10 @@ let
       url = "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt";
       hash = "sha256-B+ztN1zsFE0nyQAkHz4zlHjeyVj5L928VR8pXJkgOKM=";
     };
+    "tokenizer-llama3.json" = fetchurl {
+      url = "https://huggingface.co/Narsil/llama-tokenizer/resolve/main/tokenizer.json";
+      hash = "sha256-eePlImNfMXEwCRO7QhRkqH3mIiGCoFcLmyzLoqlksrQ=";
+    };
     "big.txt" = fetchurl {
       url = "https://norvig.com/big.txt";
       hash = "sha256-+gZsfUDw8gGsQUTmUqpiQw5YprOAXscGUPZ42lgE6Hs=";
@@ -71,33 +75,40 @@ let
 in
 buildPythonPackage rec {
   pname = "tokenizers";
-  version = "0.21.1";
+  version = "0.21.2";
   pyproject = true;
 
   src = fetchFromGitHub {
     owner = "huggingface";
     repo = "tokenizers";
     tag = "v${version}";
-    hash = "sha256-3S7ZCaZnnwyNjoZ4Y/q3ngQE2MIm2iyCCjYAkdMVG2A=";
+    hash = "sha256-HO7Zg/yLY6yxjOo5Jf6Iu2zCreCyv7IaNrWtBKrspqQ=";
   };
 
-  # TestUnigram.test_continuing_prefix_trainer_mismatch fails with:
-  # Exception: No such file or directory (os error 2)
-  # Fix submitted upstream: https://github.com/huggingface/tokenizers/pull/1747
+  # Cargo.lock shipped with 0.21.2 is invalid:
+  # error: no matching package found
+  # searched package name: `ahash`
+  # perhaps you meant:      wasi
+  # location searched: directory source `/build/tokenizers-0.21.2-vendor` (which is replacing registry `crates-io`)
+  # required by package `tokenizers-python v0.21.2 (/build/source/bindings/python)`
+  #
+  # Hence, I (@GaetanLepage) re-generated the lockfile and embedded it here for now.
+  # TODO: Try to switch back to `rustPlatform.fetchCargoVendor` at the next release.
   postPatch = ''
-    substituteInPlace tests/bindings/test_trainers.py \
-      --replace-fail '"data/' '"tests/data/'
+    ln -sf '${./Cargo.lock}' Cargo.lock
   '';
-
-  cargoDeps = rustPlatform.fetchCargoVendor {
-    inherit
-      pname
-      version
-      src
-      sourceRoot
-      ;
-    hash = "sha256-I7LlBmeVY2rWI0ta6x311iAurQKuutsClrbUgkt9xWk=";
+  cargoDeps = rustPlatform.importCargoLock {
+    lockFile = ./Cargo.lock;
   };
+  # cargoDeps = rustPlatform.fetchCargoVendor {
+  #   inherit
+  #     pname
+  #     version
+  #     src
+  #     sourceRoot
+  #     ;
+  #   hash = "sha256-EKiHjcXUjU8CWe2CB2EgAQlRcZebwe4EpD7P8lWbCjw=";
+  # };
 
   sourceRoot = "${src.name}/bindings/python";