Wip refactor

1 files changed, 313 insertions, 1 deletions

diff --git a/poetry.lock b/poetry.lock
index bdda84d..ffeea46 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -563,6 +563,26 @@ files = [
 colorama = {version = "*", markers = "platform_system == \"Windows\""}
 
 [[package]]
+name = "cohere"
+version = "5.2.3"
+description = ""
+optional = false
+python-versions = "<4.0,>=3.8"
+files = [
+    {file = "cohere-5.2.3-py3-none-any.whl", hash = "sha256:943fd2818662b02a98dfdccc7d38d02fabd8782882e8e15ddab57a33a4dcf780"},
+    {file = "cohere-5.2.3.tar.gz", hash = "sha256:eba5a3cb6a44f241ac1fe9ef2235641996555e15ecda2544c997fd750d31a693"},
+]
+
+[package.dependencies]
+fastavro = ">=1.9.4,<2.0.0"
+httpx = ">=0.21.2"
+pydantic = ">=1.9.2"
+requests = ">=2.0.0,<3.0.0"
+tokenizers = ">=0.15.2,<0.16.0"
+types-requests = ">=2.0.0,<3.0.0"
+typing_extensions = ">=4.0.0"
+
+[[package]]
 name = "colorama"
 version = "0.4.6"
 description = "Cross-platform colored terminal text."
@@ -673,6 +693,52 @@ files = [
 tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich"]
 
 [[package]]
+name = "fastavro"
+version = "1.9.4"
+description = "Fast read/write of AVRO files"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "fastavro-1.9.4-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:60cb38f07462a7fb4e4440ed0de67d3d400ae6b3d780f81327bebde9aa55faef"},
+    {file = "fastavro-1.9.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:063d01d197fc929c20adc09ca9f0ca86d33ac25ee0963ce0b438244eee8315ae"},
+    {file = "fastavro-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87a9053fcfbc895f2a16a4303af22077e3a8fdcf1cd5d6ed47ff2ef22cbba2f0"},
+    {file = "fastavro-1.9.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:02bf1276b7326397314adf41b34a4890f6ffa59cf7e0eb20b9e4ab0a143a1598"},
+    {file = "fastavro-1.9.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:56bed9eca435389a8861e6e2d631ec7f8f5dda5b23f93517ac710665bd34ca29"},
+    {file = "fastavro-1.9.4-cp310-cp310-win_amd64.whl", hash = "sha256:0cd2099c8c672b853e0b20c13e9b62a69d3fbf67ee7c59c7271ba5df1680310d"},
+    {file = "fastavro-1.9.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:af8c6d8c43a02b5569c093fc5467469541ac408c79c36a5b0900d3dd0b3ba838"},
+    {file = "fastavro-1.9.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e4a138710bd61580324d23bc5e3df01f0b82aee0a76404d5dddae73d9e4c723f"},
+    {file = "fastavro-1.9.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:903d97418120ca6b6a7f38a731166c1ccc2c4344ee5e0470d09eb1dc3687540a"},
+    {file = "fastavro-1.9.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c443eeb99899d062dbf78c525e4614dd77e041a7688fa2710c224f4033f193ae"},
+    {file = "fastavro-1.9.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:ac26ab0774d1b2b7af6d8f4300ad20bbc4b5469e658a02931ad13ce23635152f"},
+    {file = "fastavro-1.9.4-cp311-cp311-win_amd64.whl", hash = "sha256:cf7247874c22be856ba7d1f46a0f6e0379a6025f1a48a7da640444cbac6f570b"},
+    {file = "fastavro-1.9.4-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:68912f2020e1b3d70557260b27dd85fb49a4fc6bfab18d384926127452c1da4c"},
+    {file = "fastavro-1.9.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6925ce137cdd78e109abdb0bc33aad55de6c9f2d2d3036b65453128f2f5f5b92"},
+    {file = "fastavro-1.9.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b928cd294e36e35516d0deb9e104b45be922ba06940794260a4e5dbed6c192a"},
+    {file = "fastavro-1.9.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:90c9838bc4c991ffff5dd9d88a0cc0030f938b3fdf038cdf6babde144b920246"},
+    {file = "fastavro-1.9.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:eca6e54da571b06a3c5a72dbb7212073f56c92a6fbfbf847b91c347510f8a426"},
+    {file = "fastavro-1.9.4-cp312-cp312-win_amd64.whl", hash = "sha256:a4b02839ac261100cefca2e2ad04cdfedc556cb66b5ec735e0db428e74b399de"},
+    {file = "fastavro-1.9.4-cp38-cp38-macosx_11_0_x86_64.whl", hash = "sha256:4451ee9a305a73313a1558d471299f3130e4ecc10a88bf5742aa03fb37e042e6"},
+    {file = "fastavro-1.9.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a8524fccfb379565568c045d29b2ebf71e1f2c0dd484aeda9fe784ef5febe1a8"},
+    {file = "fastavro-1.9.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:33d0a00a6e09baa20f6f038d7a2ddcb7eef0e7a9980e947a018300cb047091b8"},
+    {file = "fastavro-1.9.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:23d7e5b29c9bf6f26e8be754b2c8b919838e506f78ef724de7d22881696712fc"},
+    {file = "fastavro-1.9.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2e6ab3ee53944326460edf1125b2ad5be2fadd80f7211b13c45fa0c503b4cf8d"},
+    {file = "fastavro-1.9.4-cp38-cp38-win_amd64.whl", hash = "sha256:64d335ec2004204c501f8697c385d0a8f6b521ac82d5b30696f789ff5bc85f3c"},
+    {file = "fastavro-1.9.4-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:7e05f44c493e89e73833bd3ff3790538726906d2856f59adc8103539f4a1b232"},
+    {file = "fastavro-1.9.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:253c63993250bff4ee7b11fb46cf3a4622180a783bedc82a24c6fdcd1b10ca2a"},
+    {file = "fastavro-1.9.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:24d6942eb1db14640c2581e0ecd1bbe0afc8a83731fcd3064ae7f429d7880cb7"},
+    {file = "fastavro-1.9.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d47bb66be6091cd48cfe026adcad11c8b11d7d815a2949a1e4ccf03df981ca65"},
+    {file = "fastavro-1.9.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c293897f12f910e58a1024f9c77f565aa8e23b36aafda6ad8e7041accc57a57f"},
+    {file = "fastavro-1.9.4-cp39-cp39-win_amd64.whl", hash = "sha256:f05d2afcb10a92e2a9e580a3891f090589b3e567fdc5641f8a46a0b084f120c3"},
+    {file = "fastavro-1.9.4.tar.gz", hash = "sha256:56b8363e360a1256c94562393dc7f8611f3baf2b3159f64fb2b9c6b87b14e876"},
+]
+
+[package.extras]
+codecs = ["cramjam", "lz4", "zstandard"]
+lz4 = ["lz4"]
+snappy = ["cramjam"]
+zstandard = ["zstandard"]
+
+[[package]]
 name = "fastjsonschema"
 version = "2.19.1"
 description = "Fastest Python implementation of JSON schema"
@@ -687,6 +753,22 @@ files = [
 devel = ["colorama", "json-spec", "jsonschema", "pylint", "pytest", "pytest-benchmark", "pytest-cache", "validictory"]
 
 [[package]]
+name = "filelock"
+version = "3.13.3"
+description = "A platform independent file lock."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "filelock-3.13.3-py3-none-any.whl", hash = "sha256:5ffa845303983e7a0b7ae17636509bc97997d58afeafa72fb141a17b152284cb"},
+    {file = "filelock-3.13.3.tar.gz", hash = "sha256:a79895a25bbefdf55d1a2a0a80968f7dbb28edcd6d4234a0afb3f37ecde4b546"},
+]
+
+[package.extras]
+docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.25.2)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
+typing = ["typing-extensions (>=4.8)"]
+
+[[package]]
 name = "fqdn"
 version = "1.5.1"
 description = "Validates fully-qualified domain names against RFC 1123, so that they are acceptable to modern bowsers"
@@ -784,6 +866,41 @@ files = [
 ]
 
 [[package]]
+name = "fsspec"
+version = "2024.3.1"
+description = "File-system specification"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"},
+    {file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"},
+]
+
+[package.extras]
+abfs = ["adlfs"]
+adl = ["adlfs"]
+arrow = ["pyarrow (>=1)"]
+dask = ["dask", "distributed"]
+devel = ["pytest", "pytest-cov"]
+dropbox = ["dropbox", "dropboxdrivefs", "requests"]
+full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"]
+fuse = ["fusepy"]
+gcs = ["gcsfs"]
+git = ["pygit2"]
+github = ["requests"]
+gs = ["gcsfs"]
+gui = ["panel"]
+hdfs = ["pyarrow (>=1)"]
+http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)"]
+libarchive = ["libarchive-c"]
+oci = ["ocifs"]
+s3 = ["s3fs"]
+sftp = ["paramiko"]
+smb = ["smbprotocol"]
+ssh = ["paramiko"]
+tqdm = ["tqdm"]
+
+[[package]]
 name = "gitdb"
 version = "4.0.11"
 description = "Git Object Database"
@@ -1104,6 +1221,40 @@ http2 = ["h2 (>=3,<5)"]
 socks = ["socksio (==1.*)"]
 
 [[package]]
+name = "huggingface-hub"
+version = "0.22.2"
+description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "huggingface_hub-0.22.2-py3-none-any.whl", hash = "sha256:3429e25f38ccb834d310804a3b711e7e4953db5a9e420cc147a5e194ca90fd17"},
+    {file = "huggingface_hub-0.22.2.tar.gz", hash = "sha256:32e9a9a6843c92f253ff9ca16b9985def4d80a93fb357af5353f770ef74a81be"},
+]
+
+[package.dependencies]
+filelock = "*"
+fsspec = ">=2023.5.0"
+packaging = ">=20.9"
+pyyaml = ">=5.1"
+requests = "*"
+tqdm = ">=4.42.1"
+typing-extensions = ">=3.7.4.3"
+
+[package.extras]
+all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
+cli = ["InquirerPy (==0.3.4)"]
+dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "mypy (==1.5.1)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.3.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"]
+fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
+hf-transfer = ["hf-transfer (>=0.1.4)"]
+inference = ["aiohttp", "minijinja (>=1.0)"]
+quality = ["mypy (==1.5.1)", "ruff (>=0.3.0)"]
+tensorflow = ["graphviz", "pydot", "tensorflow"]
+tensorflow-testing = ["keras (<3.0)", "tensorflow"]
+testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "minijinja (>=1.0)", "numpy", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
+torch = ["safetensors", "torch"]
+typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"]
+
+[[package]]
 name = "hyperframe"
 version = "6.0.1"
 description = "HTTP/2 framing layer for Python"
@@ -3500,6 +3651,133 @@ doc = ["sphinx", "sphinx_rtd_theme"]
 test = ["flake8", "isort", "pytest"]
 
 [[package]]
+name = "tokenizers"
+version = "0.15.2"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tokenizers-0.15.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:52f6130c9cbf70544287575a985bf44ae1bda2da7e8c24e97716080593638012"},
+    {file = "tokenizers-0.15.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:054c1cc9c6d68f7ffa4e810b3d5131e0ba511b6e4be34157aa08ee54c2f8d9ee"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a9b9b070fdad06e347563b88c278995735292ded1132f8657084989a4c84a6d5"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ea621a7eef4b70e1f7a4e84dd989ae3f0eeb50fc8690254eacc08acb623e82f1"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cf7fd9a5141634fa3aa8d6b7be362e6ae1b4cda60da81388fa533e0b552c98fd"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:44f2a832cd0825295f7179eaf173381dc45230f9227ec4b44378322d900447c9"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8b9ec69247a23747669ec4b0ca10f8e3dfb3545d550258129bd62291aabe8605"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40b6a4c78da863ff26dbd5ad9a8ecc33d8a8d97b535172601cf00aee9d7ce9ce"},
+    {file = "tokenizers-0.15.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:5ab2a4d21dcf76af60e05af8063138849eb1d6553a0d059f6534357bce8ba364"},
+    {file = "tokenizers-0.15.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a47acfac7e511f6bbfcf2d3fb8c26979c780a91e06fb5b9a43831b2c0153d024"},
+    {file = "tokenizers-0.15.2-cp310-none-win32.whl", hash = "sha256:064ff87bb6acdbd693666de9a4b692add41308a2c0ec0770d6385737117215f2"},
+    {file = "tokenizers-0.15.2-cp310-none-win_amd64.whl", hash = "sha256:3b919afe4df7eb6ac7cafd2bd14fb507d3f408db7a68c43117f579c984a73843"},
+    {file = "tokenizers-0.15.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:89cd1cb93e4b12ff39bb2d626ad77e35209de9309a71e4d3d4672667b4b256e7"},
+    {file = "tokenizers-0.15.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:cfed5c64e5be23d7ee0f0e98081a25c2a46b0b77ce99a4f0605b1ec43dd481fa"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a907d76dcfda37023ba203ab4ceeb21bc5683436ebefbd895a0841fd52f6f6f2"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20ea60479de6fc7b8ae756b4b097572372d7e4032e2521c1bbf3d90c90a99ff0"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:48e2b9335be2bc0171df9281385c2ed06a15f5cf121c44094338306ab7b33f2c"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:112a1dd436d2cc06e6ffdc0b06d55ac019a35a63afd26475205cb4b1bf0bfbff"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4620cca5c2817177ee8706f860364cc3a8845bc1e291aaf661fb899e5d1c45b0"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ccd73a82751c523b3fc31ff8194702e4af4db21dc20e55b30ecc2079c5d43cb7"},
+    {file = "tokenizers-0.15.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:107089f135b4ae7817affe6264f8c7a5c5b4fd9a90f9439ed495f54fcea56fb4"},
+    {file = "tokenizers-0.15.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0ff110ecc57b7aa4a594396525a3451ad70988e517237fe91c540997c4e50e29"},
+    {file = "tokenizers-0.15.2-cp311-none-win32.whl", hash = "sha256:6d76f00f5c32da36c61f41c58346a4fa7f0a61be02f4301fd30ad59834977cc3"},
+    {file = "tokenizers-0.15.2-cp311-none-win_amd64.whl", hash = "sha256:cc90102ed17271cf0a1262babe5939e0134b3890345d11a19c3145184b706055"},
+    {file = "tokenizers-0.15.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:f86593c18d2e6248e72fb91c77d413a815153b8ea4e31f7cd443bdf28e467670"},
+    {file = "tokenizers-0.15.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0774bccc6608eca23eb9d620196687c8b2360624619623cf4ba9dc9bd53e8b51"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d0222c5b7c9b26c0b4822a82f6a7011de0a9d3060e1da176f66274b70f846b98"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3835738be1de66624fff2f4f6f6684775da4e9c00bde053be7564cbf3545cc66"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:0143e7d9dcd811855c1ce1ab9bf5d96d29bf5e528fd6c7824d0465741e8c10fd"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:db35825f6d54215f6b6009a7ff3eedee0848c99a6271c870d2826fbbedf31a38"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3f5e64b0389a2be47091d8cc53c87859783b837ea1a06edd9d8e04004df55a5c"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e0480c452217edd35eca56fafe2029fb4d368b7c0475f8dfa3c5c9c400a7456"},
+    {file = "tokenizers-0.15.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a33ab881c8fe70474980577e033d0bc9a27b7ab8272896e500708b212995d834"},
+    {file = "tokenizers-0.15.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a308a607ca9de2c64c1b9ba79ec9a403969715a1b8ba5f998a676826f1a7039d"},
+    {file = "tokenizers-0.15.2-cp312-none-win32.whl", hash = "sha256:b8fcfa81bcb9447df582c5bc96a031e6df4da2a774b8080d4f02c0c16b42be0b"},
+    {file = "tokenizers-0.15.2-cp312-none-win_amd64.whl", hash = "sha256:38d7ab43c6825abfc0b661d95f39c7f8af2449364f01d331f3b51c94dcff7221"},
+    {file = "tokenizers-0.15.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:38bfb0204ff3246ca4d5e726e8cc8403bfc931090151e6eede54d0e0cf162ef0"},
+    {file = "tokenizers-0.15.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:9c861d35e8286a53e06e9e28d030b5a05bcbf5ac9d7229e561e53c352a85b1fc"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:936bf3842db5b2048eaa53dade907b1160f318e7c90c74bfab86f1e47720bdd6"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:620beacc3373277700d0e27718aa8b25f7b383eb8001fba94ee00aeea1459d89"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2735ecbbf37e52db4ea970e539fd2d450d213517b77745114f92867f3fc246eb"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:473c83c5e2359bb81b0b6fde870b41b2764fcdd36d997485e07e72cc3a62264a"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:968fa1fb3c27398b28a4eca1cbd1e19355c4d3a6007f7398d48826bbe3a0f728"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:865c60ae6eaebdde7da66191ee9b7db52e542ed8ee9d2c653b6d190a9351b980"},
+    {file = "tokenizers-0.15.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:7c0d8b52664ab2d4a8d6686eb5effc68b78608a9008f086a122a7b2996befbab"},
+    {file = "tokenizers-0.15.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:f33dfbdec3784093a9aebb3680d1f91336c56d86cc70ddf88708251da1fe9064"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:d44ba80988ff9424e33e0a49445072ac7029d8c0e1601ad25a0ca5f41ed0c1d6"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:dce74266919b892f82b1b86025a613956ea0ea62a4843d4c4237be2c5498ed3a"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0ef06b9707baeb98b316577acb04f4852239d856b93e9ec3a299622f6084e4be"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c73e2e74bbb07910da0d37c326869f34113137b23eadad3fc00856e6b3d9930c"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4eeb12daf02a59e29f578a865f55d87cd103ce62bd8a3a5874f8fdeaa82e336b"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9ba9f6895af58487ca4f54e8a664a322f16c26bbb442effd01087eba391a719e"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ccec77aa7150e38eec6878a493bf8c263ff1fa8a62404e16c6203c64c1f16a26"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3f40604f5042ff210ba82743dda2b6aa3e55aa12df4e9f2378ee01a17e2855e"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:5645938a42d78c4885086767c70923abad047163d809c16da75d6b290cb30bbe"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:05a77cbfebe28a61ab5c3891f9939cc24798b63fa236d84e5f29f3a85a200c00"},
+    {file = "tokenizers-0.15.2-cp37-none-win32.whl", hash = "sha256:361abdc068e8afe9c5b818769a48624687fb6aaed49636ee39bec4e95e1a215b"},
+    {file = "tokenizers-0.15.2-cp37-none-win_amd64.whl", hash = "sha256:7ef789f83eb0f9baeb4d09a86cd639c0a5518528f9992f38b28e819df397eb06"},
+    {file = "tokenizers-0.15.2-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:4fe1f74a902bee74a3b25aff180fbfbf4f8b444ab37c4d496af7afd13a784ed2"},
+    {file = "tokenizers-0.15.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4c4b89038a684f40a6b15d6b09f49650ac64d951ad0f2a3ea9169687bbf2a8ba"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d05a1b06f986d41aed5f2de464c003004b2df8aaf66f2b7628254bcbfb72a438"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:508711a108684111ec8af89d3a9e9e08755247eda27d0ba5e3c50e9da1600f6d"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:daa348f02d15160cb35439098ac96e3a53bacf35885072611cd9e5be7d333daa"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:494fdbe5932d3416de2a85fc2470b797e6f3226c12845cadf054dd906afd0442"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c2d60f5246f4da9373f75ff18d64c69cbf60c3bca597290cea01059c336d2470"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93268e788825f52de4c7bdcb6ebc1fcd4a5442c02e730faa9b6b08f23ead0e24"},
+    {file = "tokenizers-0.15.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6fc7083ab404019fc9acafe78662c192673c1e696bd598d16dc005bd663a5cf9"},
+    {file = "tokenizers-0.15.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:41e39b41e5531d6b2122a77532dbea60e171ef87a3820b5a3888daa847df4153"},
+    {file = "tokenizers-0.15.2-cp38-none-win32.whl", hash = "sha256:06cd0487b1cbfabefb2cc52fbd6b1f8d4c37799bd6c6e1641281adaa6b2504a7"},
+    {file = "tokenizers-0.15.2-cp38-none-win_amd64.whl", hash = "sha256:5179c271aa5de9c71712e31cb5a79e436ecd0d7532a408fa42a8dbfa4bc23fd9"},
+    {file = "tokenizers-0.15.2-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:82f8652a74cc107052328b87ea8b34291c0f55b96d8fb261b3880216a9f9e48e"},
+    {file = "tokenizers-0.15.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:02458bee6f5f3139f1ebbb6d042b283af712c0981f5bc50edf771d6b762d5e4f"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:c9a09cd26cca2e1c349f91aa665309ddb48d71636370749414fbf67bc83c5343"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:158be8ea8554e5ed69acc1ce3fbb23a06060bd4bbb09029431ad6b9a466a7121"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1ddba9a2b0c8c81633eca0bb2e1aa5b3a15362b1277f1ae64176d0f6eba78ab1"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3ef5dd1d39797044642dbe53eb2bc56435308432e9c7907728da74c69ee2adca"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:454c203164e07a860dbeb3b1f4a733be52b0edbb4dd2e5bd75023ffa8b49403a"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0cf6b7f1d4dc59af960e6ffdc4faffe6460bbfa8dce27a58bf75755ffdb2526d"},
+    {file = "tokenizers-0.15.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2ef09bbc16519f6c25d0c7fc0c6a33a6f62923e263c9d7cca4e58b8c61572afb"},
+    {file = "tokenizers-0.15.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c9a2ebdd2ad4ec7a68e7615086e633857c85e2f18025bd05d2a4399e6c5f7169"},
+    {file = "tokenizers-0.15.2-cp39-none-win32.whl", hash = "sha256:918fbb0eab96fe08e72a8c2b5461e9cce95585d82a58688e7f01c2bd546c79d0"},
+    {file = "tokenizers-0.15.2-cp39-none-win_amd64.whl", hash = "sha256:524e60da0135e106b254bd71f0659be9f89d83f006ea9093ce4d1fab498c6d0d"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:6a9b648a58281c4672212fab04e60648fde574877d0139cd4b4f93fe28ca8944"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:7c7d18b733be6bbca8a55084027f7be428c947ddf871c500ee603e375013ffba"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:13ca3611de8d9ddfbc4dc39ef54ab1d2d4aaa114ac8727dfdc6a6ec4be017378"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:237d1bf3361cf2e6463e6c140628e6406766e8b27274f5fcc62c747ae3c6f094"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:67a0fe1e49e60c664915e9fb6b0cb19bac082ab1f309188230e4b2920230edb3"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:4e022fe65e99230b8fd89ebdfea138c24421f91c1a4f4781a8f5016fd5cdfb4d"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:d857be2df69763362ac699f8b251a8cd3fac9d21893de129bc788f8baaef2693"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:708bb3e4283177236309e698da5fcd0879ce8fd37457d7c266d16b550bcbbd18"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64c35e09e9899b72a76e762f9854e8750213f67567787d45f37ce06daf57ca78"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c1257f4394be0d3b00de8c9e840ca5601d0a4a8438361ce9c2b05c7d25f6057b"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:02272fe48280e0293a04245ca5d919b2c94a48b408b55e858feae9618138aeda"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:dc3ad9ebc76eabe8b1d7c04d38be884b8f9d60c0cdc09b0aa4e3bcf746de0388"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:32e16bdeffa7c4f46bf2152172ca511808b952701d13e7c18833c0b73cb5c23f"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:fb16ba563d59003028b678d2361a27f7e4ae0ab29c7a80690efa20d829c81fdb"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:2277c36d2d6cdb7876c274547921a42425b6810d38354327dd65a8009acf870c"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:1cf75d32e8d250781940d07f7eece253f2fe9ecdb1dc7ba6e3833fa17b82fcbc"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1b3b31884dc8e9b21508bb76da80ebf7308fdb947a17affce815665d5c4d028"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b10122d8d8e30afb43bb1fe21a3619f62c3e2574bff2699cf8af8b0b6c5dc4a3"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:d88b96ff0fe8e91f6ef01ba50b0d71db5017fa4e3b1d99681cec89a85faf7bf7"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:37aaec5a52e959892870a7c47cef80c53797c0db9149d458460f4f31e2fb250e"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e2ea752f2b0fe96eb6e2f3adbbf4d72aaa1272079b0dfa1145507bd6a5d537e6"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:4b19a808d8799fda23504a5cd31d2f58e6f52f140380082b352f877017d6342b"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64c86e5e068ac8b19204419ed8ca90f9d25db20578f5881e337d203b314f4104"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:de19c4dc503c612847edf833c82e9f73cd79926a384af9d801dcf93f110cea4e"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea09acd2fe3324174063d61ad620dec3bcf042b495515f27f638270a7d466e8b"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:cf27fd43472e07b57cf420eee1e814549203d56de00b5af8659cb99885472f1f"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:7ca22bd897537a0080521445d91a58886c8c04084a6a19e6c78c586e0cfa92a5"},
+    {file = "tokenizers-0.15.2.tar.gz", hash = "sha256:e6e9c6e019dd5484be5beafc775ae6c925f4c69a3487040ed09b45e13df2cb91"},
+]
+
+[package.dependencies]
+huggingface_hub = ">=0.16.4,<1.0"
+
+[package.extras]
+dev = ["tokenizers[testing]"]
+docs = ["setuptools_rust", "sphinx", "sphinx_rtd_theme"]
+testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
+
+[[package]]
 name = "toml"
 version = "0.10.2"
 description = "Python Library for Tom's Obvious, Minimal Language"
@@ -3542,6 +3820,26 @@ files = [
 ]
 
 [[package]]
+name = "tqdm"
+version = "4.66.2"
+description = "Fast, Extensible Progress Meter"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tqdm-4.66.2-py3-none-any.whl", hash = "sha256:1ee4f8a893eb9bef51c6e35730cebf234d5d0b6bd112b0271e10ed7c24a02bd9"},
+    {file = "tqdm-4.66.2.tar.gz", hash = "sha256:6cd52cdf0fef0e0f543299cfc96fec90d7b8a7e88745f411ec33eb44d5ed3531"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"]
+notebook = ["ipywidgets (>=6)"]
+slack = ["slack-sdk"]
+telegram = ["requests"]
+
+[[package]]
 name = "traitlets"
 version = "5.14.2"
 description = "Traitlets Python configuration system"
@@ -3568,6 +3866,20 @@ files = [
 ]
 
 [[package]]
+name = "types-requests"
+version = "2.31.0.20240406"
+description = "Typing stubs for requests"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "types-requests-2.31.0.20240406.tar.gz", hash = "sha256:4428df33c5503945c74b3f42e82b181e86ec7b724620419a2966e2de604ce1a1"},
+    {file = "types_requests-2.31.0.20240406-py3-none-any.whl", hash = "sha256:6216cdac377c6b9a040ac1c0404f7284bd13199c0e1bb235f4324627e8898cf5"},
+]
+
+[package.dependencies]
+urllib3 = ">=2"
+
+[[package]]
 name = "typing-extensions"
 version = "4.10.0"
 description = "Backported and Experimental Type Hints for Python 3.8+"
@@ -3849,4 +4161,4 @@ multidict = ">=4.0"
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.11"
-content-hash = "8be3bd74ef26bad03e2d8bcf1ef2f277270082c6ab48274504e6f29392c78914"
+content-hash = "44ec0d87aaee06d7909d51fceddf741a2f6d971b3de9309089b3d154abfe518d"