From 09771094911e78df94a545c32f2a2b5d3508c27c Mon Sep 17 00:00:00 2001 From: michaelfeil Date: Sun, 9 Jun 2024 21:35:50 -0700 Subject: [PATCH] add clip: max model length --- .../transformer/vision/torch_vision.py | 16 +- libs/infinity_emb/poetry.lock | 231 +++--------------- libs/infinity_emb/pyproject.toml | 2 - 3 files changed, 43 insertions(+), 206 deletions(-) diff --git a/libs/infinity_emb/infinity_emb/transformer/vision/torch_vision.py b/libs/infinity_emb/infinity_emb/transformer/vision/torch_vision.py index 37f697c6..6c372713 100644 --- a/libs/infinity_emb/infinity_emb/transformer/vision/torch_vision.py +++ b/libs/infinity_emb/infinity_emb/transformer/vision/torch_vision.py @@ -28,6 +28,7 @@ def __init__(self, *, engine_args: EngineArgs): self.model = AutoModel.from_pretrained( engine_args.model_name_or_path, revision=engine_args.revision, + trust_remote_code=engine_args.trust_remote_code, ) if torch.cuda.is_available(): self.model = self.model.cuda() @@ -36,6 +37,7 @@ def __init__(self, *, engine_args: EngineArgs): self.processor = AutoProcessor.from_pretrained( engine_args.model_name_or_path, revision=engine_args.revision, + trust_remote_code=engine_args.trust_remote_code, ) self.engine_args = engine_args @@ -51,6 +53,15 @@ def __init__(self, *, engine_args: EngineArgs): assert hasattr( self.model, "get_image_features" ), f"AutoModel of {engine_args.model_name_or_path} does not have get_image_features method" + self.max_length = None + if hasattr(self.model.config, "max_length"): + self.max_length = self.model.config.max_length + elif hasattr(self.model.config, "max_position_embeddings"): + self.max_length = self.model.config.max_position_embeddings + elif hasattr(self.model.config, "text_config") and hasattr( + self.model.config.text_config, "max_length" + ): + self.max_length = self.model.config.text_config.max_length def encode_pre(self, sentences_or_images: list[Union[str, "ImageClass"]]): # return input_tuples @@ -72,6 +83,7 @@ def encode_pre(self, sentences_or_images: list[Union[str, "ImageClass"]]): return_tensors="pt", padding=True, truncation=True, + max_length=self.max_length, ) preprocessed = {k: v.to(self.model.device) for k, v in preprocessed.items()} @@ -118,5 +130,7 @@ def encode_post(self, out_features) -> list[float]: return embeddings def tokenize_lengths(self, text_list: list[str]) -> list[int]: - preprocessed = self.processor(text=text_list, truncation=True) + preprocessed = self.processor( + text=text_list, truncation=True, max_length=self.max_length + ) return [len(t) for t in preprocessed["input_ids"]] diff --git a/libs/infinity_emb/poetry.lock b/libs/infinity_emb/poetry.lock index 35961221..17030b9c 100644 --- a/libs/infinity_emb/poetry.lock +++ b/libs/infinity_emb/poetry.lock @@ -487,7 +487,7 @@ files = [ name = "coloredlogs" version = "15.0.1" description = "Colored terminal output for Python's logging module" -optional = false +optional = true python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*" files = [ {file = "coloredlogs-15.0.1-py2.py3-none-any.whl", hash = "sha256:612ee75c546f53e92e70049c9dbfcc18c935a2b9a53b66085ce9ef6a6e5c0934"}, @@ -807,34 +807,6 @@ typing-extensions = ">=4.5.0" [package.extras] all = ["email-validator (>=2.0.0)", "httpx (>=0.23.0)", "itsdangerous (>=1.1.0)", "jinja2 (>=2.11.2)", "orjson (>=3.2.1)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.5)", "pyyaml (>=5.3.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0)", "uvicorn[standard] (>=0.12.0)"] -[[package]] -name = "fastembed" -version = "0.3.0" -description = "Fast, light, accurate library built for retrieval embedding generation" -optional = false -python-versions = "<3.13,>=3.8.0" -files = [ - {file = "fastembed-0.3.0-py3-none-any.whl", hash = "sha256:c62d7c688e26daaa6413a20808cf39442292b1e9c71d4fad560ea40937b00462"}, - {file = "fastembed-0.3.0.tar.gz", hash = "sha256:6a6248d82236ca2301d0bdf696a8a0daff29625424177cb3ac4e09e48ca5d48e"}, -] - -[package.dependencies] -huggingface-hub = ">=0.20,<1.0" -loguru = ">=0.7.2,<0.8.0" -mmh3 = ">=4.0,<5.0" -numpy = [ - {version = ">=1.21", markers = "python_version < \"3.12\""}, - {version = ">=1.26", markers = "python_version >= \"3.12\""}, -] -onnx = ">=1.15.0,<2.0.0" -onnxruntime = ">=1.17.0,<2.0.0" -pillow = ">=10.3.0,<11.0.0" -PyStemmer = ">=2.2.0,<3.0.0" -requests = ">=2.31,<3.0" -snowballstemmer = ">=2.2.0,<3.0.0" -tokenizers = ">=0.15,<1.0" -tqdm = ">=4.66,<5.0" - [[package]] name = "filelock" version = "3.14.0" @@ -855,7 +827,7 @@ typing = ["typing-extensions (>=4.8)"] name = "flatbuffers" version = "24.3.25" description = "The FlatBuffers serialization format for Python" -optional = false +optional = true python-versions = "*" files = [ {file = "flatbuffers-24.3.25-py2.py3-none-any.whl", hash = "sha256:8dbdec58f935f3765e4f7f3cf635ac3a77f83568138d6a2311f524ec96364812"}, @@ -1221,7 +1193,7 @@ typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "t name = "humanfriendly" version = "10.0" description = "Human friendly output for text interfaces using Python" -optional = false +optional = true python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*" files = [ {file = "humanfriendly-10.0-py2.py3-none-any.whl", hash = "sha256:1697e1a8a8f550fd43c2865cd84542fc175a61dcb779b6fee18cf6b6ccba1477"}, @@ -1332,24 +1304,6 @@ files = [ {file = "joblib-1.4.2.tar.gz", hash = "sha256:2382c5816b2636fbd20a09e0f4e9dad4736765fdfb7dca582943b9c1366b3f0e"}, ] -[[package]] -name = "loguru" -version = "0.7.2" -description = "Python logging made (stupidly) simple" -optional = false -python-versions = ">=3.5" -files = [ - {file = "loguru-0.7.2-py3-none-any.whl", hash = "sha256:003d71e3d3ed35f0f8984898359d65b79e5b21943f78af86aa5491210429b8eb"}, - {file = "loguru-0.7.2.tar.gz", hash = "sha256:e671a53522515f34fd406340ee968cb9ecafbc4b36c679da03c18fd8d0bd51ac"}, -] - -[package.dependencies] -colorama = {version = ">=0.3.4", markers = "sys_platform == \"win32\""} -win32-setctime = {version = ">=1.0.0", markers = "sys_platform == \"win32\""} - -[package.extras] -dev = ["Sphinx (==7.2.5)", "colorama (==0.4.5)", "colorama (==0.4.6)", "exceptiongroup (==1.1.3)", "freezegun (==1.1.0)", "freezegun (==1.2.2)", "mypy (==v0.910)", "mypy (==v0.971)", "mypy (==v1.4.1)", "mypy (==v1.5.1)", "pre-commit (==3.4.0)", "pytest (==6.1.2)", "pytest (==7.4.0)", "pytest-cov (==2.12.1)", "pytest-cov (==4.1.0)", "pytest-mypy-plugins (==1.9.3)", "pytest-mypy-plugins (==3.0.0)", "sphinx-autobuild (==2021.3.14)", "sphinx-rtd-theme (==1.3.0)", "tox (==3.27.1)", "tox (==4.11.0)"] - [[package]] name = "markdown" version = "3.6" @@ -1628,103 +1582,11 @@ files = [ intel-openmp = "==2021.*" tbb = "==2021.*" -[[package]] -name = "mmh3" -version = "4.1.0" -description = "Python extension for MurmurHash (MurmurHash3), a set of fast and robust hash functions." -optional = false -python-versions = "*" -files = [ - {file = "mmh3-4.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:be5ac76a8b0cd8095784e51e4c1c9c318c19edcd1709a06eb14979c8d850c31a"}, - {file = "mmh3-4.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:98a49121afdfab67cd80e912b36404139d7deceb6773a83620137aaa0da5714c"}, - {file = "mmh3-4.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5259ac0535874366e7d1a5423ef746e0d36a9e3c14509ce6511614bdc5a7ef5b"}, - {file = "mmh3-4.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c5950827ca0453a2be357696da509ab39646044e3fa15cad364eb65d78797437"}, - {file = "mmh3-4.1.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1dd0f652ae99585b9dd26de458e5f08571522f0402155809fd1dc8852a613a39"}, - {file = "mmh3-4.1.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:99d25548070942fab1e4a6f04d1626d67e66d0b81ed6571ecfca511f3edf07e6"}, - {file = "mmh3-4.1.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:53db8d9bad3cb66c8f35cbc894f336273f63489ce4ac416634932e3cbe79eb5b"}, - {file = "mmh3-4.1.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75da0f615eb55295a437264cc0b736753f830b09d102aa4c2a7d719bc445ec05"}, - {file = "mmh3-4.1.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b926b07fd678ea84b3a2afc1fa22ce50aeb627839c44382f3d0291e945621e1a"}, - {file = "mmh3-4.1.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:c5b053334f9b0af8559d6da9dc72cef0a65b325ebb3e630c680012323c950bb6"}, - {file = "mmh3-4.1.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:5bf33dc43cd6de2cb86e0aa73a1cc6530f557854bbbe5d59f41ef6de2e353d7b"}, - {file = "mmh3-4.1.0-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:fa7eacd2b830727ba3dd65a365bed8a5c992ecd0c8348cf39a05cc77d22f4970"}, - {file = "mmh3-4.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:42dfd6742b9e3eec599f85270617debfa0bbb913c545bb980c8a4fa7b2d047da"}, - {file = "mmh3-4.1.0-cp310-cp310-win32.whl", hash = "sha256:2974ad343f0d39dcc88e93ee6afa96cedc35a9883bc067febd7ff736e207fa47"}, - {file = "mmh3-4.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:74699a8984ded645c1a24d6078351a056f5a5f1fe5838870412a68ac5e28d865"}, - {file = "mmh3-4.1.0-cp310-cp310-win_arm64.whl", hash = "sha256:f0dc874cedc23d46fc488a987faa6ad08ffa79e44fb08e3cd4d4cf2877c00a00"}, - {file = "mmh3-4.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:3280a463855b0eae64b681cd5b9ddd9464b73f81151e87bb7c91a811d25619e6"}, - {file = "mmh3-4.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:97ac57c6c3301769e757d444fa7c973ceb002cb66534b39cbab5e38de61cd896"}, - {file = "mmh3-4.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a7b6502cdb4dbd880244818ab363c8770a48cdccecf6d729ade0241b736b5ec0"}, - {file = "mmh3-4.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:52ba2da04671a9621580ddabf72f06f0e72c1c9c3b7b608849b58b11080d8f14"}, - {file = "mmh3-4.1.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5a5fef4c4ecc782e6e43fbeab09cff1bac82c998a1773d3a5ee6a3605cde343e"}, - {file = "mmh3-4.1.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5135358a7e00991f73b88cdc8eda5203bf9de22120d10a834c5761dbeb07dd13"}, - {file = "mmh3-4.1.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cff9ae76a54f7c6fe0167c9c4028c12c1f6de52d68a31d11b6790bb2ae685560"}, - {file = "mmh3-4.1.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f6f02576a4d106d7830ca90278868bf0983554dd69183b7bbe09f2fcd51cf54f"}, - {file = "mmh3-4.1.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:073d57425a23721730d3ff5485e2da489dd3c90b04e86243dd7211f889898106"}, - {file = "mmh3-4.1.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:71e32ddec7f573a1a0feb8d2cf2af474c50ec21e7a8263026e8d3b4b629805db"}, - {file = "mmh3-4.1.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:7cbb20b29d57e76a58b40fd8b13a9130db495a12d678d651b459bf61c0714cea"}, - {file = "mmh3-4.1.0-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:a42ad267e131d7847076bb7e31050f6c4378cd38e8f1bf7a0edd32f30224d5c9"}, - {file = "mmh3-4.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4a013979fc9390abadc445ea2527426a0e7a4495c19b74589204f9b71bcaafeb"}, - {file = "mmh3-4.1.0-cp311-cp311-win32.whl", hash = "sha256:1d3b1cdad7c71b7b88966301789a478af142bddcb3a2bee563f7a7d40519a00f"}, - {file = "mmh3-4.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:0dc6dc32eb03727467da8e17deffe004fbb65e8b5ee2b502d36250d7a3f4e2ec"}, - {file = "mmh3-4.1.0-cp311-cp311-win_arm64.whl", hash = "sha256:9ae3a5c1b32dda121c7dc26f9597ef7b01b4c56a98319a7fe86c35b8bc459ae6"}, - {file = "mmh3-4.1.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:0033d60c7939168ef65ddc396611077a7268bde024f2c23bdc283a19123f9e9c"}, - {file = "mmh3-4.1.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d6af3e2287644b2b08b5924ed3a88c97b87b44ad08e79ca9f93d3470a54a41c5"}, - {file = "mmh3-4.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d82eb4defa245e02bb0b0dc4f1e7ee284f8d212633389c91f7fba99ba993f0a2"}, - {file = "mmh3-4.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ba245e94b8d54765e14c2d7b6214e832557e7856d5183bc522e17884cab2f45d"}, - {file = "mmh3-4.1.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bb04e2feeabaad6231e89cd43b3d01a4403579aa792c9ab6fdeef45cc58d4ec0"}, - {file = "mmh3-4.1.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1e3b1a27def545ce11e36158ba5d5390cdbc300cfe456a942cc89d649cf7e3b2"}, - {file = "mmh3-4.1.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ce0ab79ff736d7044e5e9b3bfe73958a55f79a4ae672e6213e92492ad5e734d5"}, - {file = "mmh3-4.1.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3b02268be6e0a8eeb8a924d7db85f28e47344f35c438c1e149878bb1c47b1cd3"}, - {file = "mmh3-4.1.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:deb887f5fcdaf57cf646b1e062d56b06ef2f23421c80885fce18b37143cba828"}, - {file = "mmh3-4.1.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:99dd564e9e2b512eb117bd0cbf0f79a50c45d961c2a02402787d581cec5448d5"}, - {file = "mmh3-4.1.0-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:08373082dfaa38fe97aa78753d1efd21a1969e51079056ff552e687764eafdfe"}, - {file = "mmh3-4.1.0-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:54b9c6a2ea571b714e4fe28d3e4e2db37abfd03c787a58074ea21ee9a8fd1740"}, - {file = "mmh3-4.1.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a7b1edf24c69e3513f879722b97ca85e52f9032f24a52284746877f6a7304086"}, - {file = "mmh3-4.1.0-cp312-cp312-win32.whl", hash = "sha256:411da64b951f635e1e2284b71d81a5a83580cea24994b328f8910d40bed67276"}, - {file = "mmh3-4.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:bebc3ecb6ba18292e3d40c8712482b4477abd6981c2ebf0e60869bd90f8ac3a9"}, - {file = "mmh3-4.1.0-cp312-cp312-win_arm64.whl", hash = "sha256:168473dd608ade6a8d2ba069600b35199a9af837d96177d3088ca91f2b3798e3"}, - {file = "mmh3-4.1.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:372f4b7e1dcde175507640679a2a8790185bb71f3640fc28a4690f73da986a3b"}, - {file = "mmh3-4.1.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:438584b97f6fe13e944faf590c90fc127682b57ae969f73334040d9fa1c7ffa5"}, - {file = "mmh3-4.1.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:6e27931b232fc676675fac8641c6ec6b596daa64d82170e8597f5a5b8bdcd3b6"}, - {file = "mmh3-4.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:571a92bad859d7b0330e47cfd1850b76c39b615a8d8e7aa5853c1f971fd0c4b1"}, - {file = "mmh3-4.1.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4a69d6afe3190fa08f9e3a58e5145549f71f1f3fff27bd0800313426929c7068"}, - {file = "mmh3-4.1.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:afb127be0be946b7630220908dbea0cee0d9d3c583fa9114a07156f98566dc28"}, - {file = "mmh3-4.1.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:940d86522f36348ef1a494cbf7248ab3f4a1638b84b59e6c9e90408bd11ad729"}, - {file = "mmh3-4.1.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3dcccc4935686619a8e3d1f7b6e97e3bd89a4a796247930ee97d35ea1a39341"}, - {file = "mmh3-4.1.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:01bb9b90d61854dfc2407c5e5192bfb47222d74f29d140cb2dd2a69f2353f7cc"}, - {file = "mmh3-4.1.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:bcb1b8b951a2c0b0fb8a5426c62a22557e2ffc52539e0a7cc46eb667b5d606a9"}, - {file = "mmh3-4.1.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:6477a05d5e5ab3168e82e8b106e316210ac954134f46ec529356607900aea82a"}, - {file = "mmh3-4.1.0-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:da5892287e5bea6977364b15712a2573c16d134bc5fdcdd4cf460006cf849278"}, - {file = "mmh3-4.1.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:99180d7fd2327a6fffbaff270f760576839dc6ee66d045fa3a450f3490fda7f5"}, - {file = "mmh3-4.1.0-cp38-cp38-win32.whl", hash = "sha256:9b0d4f3949913a9f9a8fb1bb4cc6ecd52879730aab5ff8c5a3d8f5b593594b73"}, - {file = "mmh3-4.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:598c352da1d945108aee0c3c3cfdd0e9b3edef74108f53b49d481d3990402169"}, - {file = "mmh3-4.1.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:475d6d1445dd080f18f0f766277e1237fa2914e5fe3307a3b2a3044f30892103"}, - {file = "mmh3-4.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5ca07c41e6a2880991431ac717c2a049056fff497651a76e26fc22224e8b5732"}, - {file = "mmh3-4.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:0ebe052fef4bbe30c0548d12ee46d09f1b69035ca5208a7075e55adfe091be44"}, - {file = "mmh3-4.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eaefd42e85afb70f2b855a011f7b4d8a3c7e19c3f2681fa13118e4d8627378c5"}, - {file = "mmh3-4.1.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ac0ae43caae5a47afe1b63a1ae3f0986dde54b5fb2d6c29786adbfb8edc9edfb"}, - {file = "mmh3-4.1.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6218666f74c8c013c221e7f5f8a693ac9cf68e5ac9a03f2373b32d77c48904de"}, - {file = "mmh3-4.1.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ac59294a536ba447b5037f62d8367d7d93b696f80671c2c45645fa9f1109413c"}, - {file = "mmh3-4.1.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:086844830fcd1e5c84fec7017ea1ee8491487cfc877847d96f86f68881569d2e"}, - {file = "mmh3-4.1.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:e42b38fad664f56f77f6fbca22d08450f2464baa68acdbf24841bf900eb98e87"}, - {file = "mmh3-4.1.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:d08b790a63a9a1cde3b5d7d733ed97d4eb884bfbc92f075a091652d6bfd7709a"}, - {file = "mmh3-4.1.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:73ea4cc55e8aea28c86799ecacebca09e5f86500414870a8abaedfcbaf74d288"}, - {file = "mmh3-4.1.0-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:f90938ff137130e47bcec8dc1f4ceb02f10178c766e2ef58a9f657ff1f62d124"}, - {file = "mmh3-4.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:aa1f13e94b8631c8cd53259250556edcf1de71738936b60febba95750d9632bd"}, - {file = "mmh3-4.1.0-cp39-cp39-win32.whl", hash = "sha256:a3b680b471c181490cf82da2142029edb4298e1bdfcb67c76922dedef789868d"}, - {file = "mmh3-4.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:fefef92e9c544a8dbc08f77a8d1b6d48006a750c4375bbcd5ff8199d761e263b"}, - {file = "mmh3-4.1.0-cp39-cp39-win_arm64.whl", hash = "sha256:8e2c1f6a2b41723a4f82bd5a762a777836d29d664fc0095f17910bea0adfd4a6"}, - {file = "mmh3-4.1.0.tar.gz", hash = "sha256:a1cf25348b9acd229dda464a094d6170f47d2850a1fcb762a3b6172d2ce6ca4a"}, -] - -[package.extras] -test = ["mypy (>=1.0)", "pytest (>=7.0.0)"] - [[package]] name = "mpmath" version = "1.3.0" description = "Python library for arbitrary-precision floating-point arithmetic" -optional = false +optional = true python-versions = "*" files = [ {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"}, @@ -2146,7 +2008,7 @@ files = [ name = "onnx" version = "1.16.1" description = "Open Neural Network Exchange" -optional = false +optional = true python-versions = ">=3.8" files = [ {file = "onnx-1.16.1-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:bb2d392e5b7060082c2fb38eb5c44f67eb34ff5f0681bd6f45beff9abc6f7094"}, @@ -2188,7 +2050,7 @@ reference = ["Pillow", "google-re2"] name = "onnxruntime" version = "1.18.0" description = "ONNX Runtime is a runtime accelerator for Machine Learning models" -optional = false +optional = true python-versions = "*" files = [ {file = "onnxruntime-1.18.0-cp310-cp310-macosx_11_0_universal2.whl", hash = "sha256:5a3b7993a5ecf4a90f35542a4757e29b2d653da3efe06cdd3164b91167bbe10d"}, @@ -2480,7 +2342,7 @@ files = [ name = "pillow" version = "10.3.0" description = "Python Imaging Library (Fork)" -optional = false +optional = true python-versions = ">=3.8" files = [ {file = "pillow-10.3.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:90b9e29824800e90c84e4022dd5cc16eb2d9605ee13f05d47641eb183cd73d45"}, @@ -2861,23 +2723,13 @@ diagrams = ["jinja2", "railroad-diagrams"] name = "pyreadline3" version = "3.4.1" description = "A python implementation of GNU readline." -optional = false +optional = true python-versions = "*" files = [ {file = "pyreadline3-3.4.1-py3-none-any.whl", hash = "sha256:b0efb6516fd4fb07b45949053826a62fa4cb353db5be2bbb4a7aa1fdd1e345fb"}, {file = "pyreadline3-3.4.1.tar.gz", hash = "sha256:6f3d1f7b8a31ba32b73917cefc1f28cc660562f39aea8646d30bd6eff21f7bae"}, ] -[[package]] -name = "pystemmer" -version = "2.2.0.1" -description = "Snowball stemming algorithms, for information retrieval" -optional = false -python-versions = "*" -files = [ - {file = "PyStemmer-2.2.0.1.tar.gz", hash = "sha256:9f3b366f1ed06b49dc1868bf0aefd884423db80f3431be442d0f993e448cc67b"}, -] - [[package]] name = "pytest" version = "7.4.4" @@ -3187,7 +3039,7 @@ files = [ name = "safetensors" version = "0.4.3" description = "" -optional = false +optional = true python-versions = ">=3.7" files = [ {file = "safetensors-0.4.3-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:dcf5705cab159ce0130cd56057f5f3425023c407e170bca60b4868048bae64fd"}, @@ -3527,17 +3379,6 @@ files = [ {file = "sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc"}, ] -[[package]] -name = "snowballstemmer" -version = "2.2.0" -description = "This package provides 29 stemmers for 28 languages generated from Snowball algorithms." -optional = false -python-versions = "*" -files = [ - {file = "snowballstemmer-2.2.0-py2.py3-none-any.whl", hash = "sha256:c8e1716e83cc398ae16824e5572ae04e0d9fc2c6b985fb0f900f5f0c96ecba1a"}, - {file = "snowballstemmer-2.2.0.tar.gz", hash = "sha256:09b16deb8547d3412ad7b590689584cd0fe25ec8db3be37788be3810cbf19cb1"}, -] - [[package]] name = "sortedcontainers" version = "2.4.0" @@ -3582,7 +3423,7 @@ full = ["httpx (>=0.22.0)", "itsdangerous", "jinja2", "python-multipart", "pyyam name = "sympy" version = "1.12.1" description = "Computer algebra system (CAS) in Python" -optional = false +optional = true python-versions = ">=3.8" files = [ {file = "sympy-1.12.1-py3-none-any.whl", hash = "sha256:9b2cbc7f1a640289430e13d2a56f02f867a1da0190f2f99d8968c2f74da0e515"}, @@ -3633,7 +3474,7 @@ files = [ name = "tokenizers" version = "0.19.1" description = "" -optional = false +optional = true python-versions = ">=3.7" files = [ {file = "tokenizers-0.19.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:952078130b3d101e05ecfc7fc3640282d74ed26bcf691400f872563fca15ac97"}, @@ -3833,18 +3674,18 @@ telegram = ["requests"] [[package]] name = "transformers" -version = "4.40.2" +version = "4.41.2" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" -optional = false +optional = true python-versions = ">=3.8.0" files = [ - {file = "transformers-4.40.2-py3-none-any.whl", hash = "sha256:71cb94301ec211a2e1d4b8c8d18dcfaa902dfa00a089dceca167a8aa265d6f2d"}, - {file = "transformers-4.40.2.tar.gz", hash = "sha256:657b6054a2097671398d976ad46e60836e7e15f9ea9551631a96e33cb9240649"}, + {file = "transformers-4.41.2-py3-none-any.whl", hash = "sha256:05555d20e43f808de1ef211ab64803cdb513170cef70d29a888b589caebefc67"}, + {file = "transformers-4.41.2.tar.gz", hash = "sha256:80a4db216533d573e9cc7388646c31ed9480918feb7c55eb211249cb23567f87"}, ] [package.dependencies] filelock = "*" -huggingface-hub = ">=0.19.3,<1.0" +huggingface-hub = ">=0.23.0,<1.0" numpy = ">=1.17" packaging = ">=20.0" protobuf = {version = "*", optional = true, markers = "extra == \"sentencepiece\""} @@ -3859,17 +3700,15 @@ tqdm = ">=4.27" [package.extras] accelerate = ["accelerate (>=0.21.0)"] agents = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch"] -all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"] +all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"] audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] codecarbon = ["codecarbon (==1.2.0)"] deepspeed = ["accelerate (>=0.21.0)", "deepspeed (>=0.9.3)"] -deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] -dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] -dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.19,<0.20)", "urllib3 (<2.0.0)"] -dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] -docs = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "hf-doc-builder", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision"] -docs-specific = ["hf-doc-builder"] -flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)"] +deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] +dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "scipy (<1.13.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] +dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.19,<0.20)", "urllib3 (<2.0.0)"] +dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm", "tokenizers (>=0.19,<0.20)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] +flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)", "scipy (<1.13.0)"] flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] ftfy = ["ftfy"] integrations = ["optuna", "ray[tune] (>=2.7.0)", "sigopt"] @@ -3879,7 +3718,7 @@ natten = ["natten (>=0.14.6,<0.15.0)"] onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"] onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"] optuna = ["optuna"] -quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "urllib3 (<2.0.0)"] +quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "urllib3 (<2.0.0)"] ray = ["ray[tune] (>=2.7.0)"] retrieval = ["datasets (!=2.5.0)", "faiss-cpu"] sagemaker = ["sagemaker (>=2.31.0)"] @@ -3888,16 +3727,16 @@ serving = ["fastapi", "pydantic", "starlette", "uvicorn"] sigopt = ["sigopt"] sklearn = ["scikit-learn"] speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] -testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] -tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] -tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] +testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk", "parameterized", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] +tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] +tf-cpu = ["keras (>2.9,<2.16)", "keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>2.9,<2.16)", "tensorflow-probability (<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] timm = ["timm"] tokenizers = ["tokenizers (>=0.19,<0.20)"] torch = ["accelerate (>=0.21.0)", "torch"] torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"] -torchhub = ["filelock", "huggingface-hub (>=0.19.3,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.19,<0.20)", "torch", "tqdm (>=4.27)"] +torchhub = ["filelock", "huggingface-hub (>=0.23.0,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.19,<0.20)", "torch", "tqdm (>=4.27)"] video = ["av (==9.2.0)", "decord (==0.6.0)"] vision = ["Pillow (>=10.0.1,<=15.0)"] @@ -4402,20 +4241,6 @@ files = [ {file = "websockets-12.0.tar.gz", hash = "sha256:81df9cbcbb6c260de1e007e58c011bfebe2dafc8435107b0537f393dd38c8b1b"}, ] -[[package]] -name = "win32-setctime" -version = "1.1.0" -description = "A small Python utility to set file creation time on Windows" -optional = false -python-versions = ">=3.5" -files = [ - {file = "win32_setctime-1.1.0-py3-none-any.whl", hash = "sha256:231db239e959c2fe7eb1d7dc129f11172354f98361c4fa2d6d2d7e278baa8aad"}, - {file = "win32_setctime-1.1.0.tar.gz", hash = "sha256:15cf5750465118d6929ae4de4eb46e8edae9a5634350c01ba582df868e932cb2"}, -] - -[package.extras] -dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"] - [[package]] name = "xxhash" version = "3.4.1" @@ -4667,4 +4492,4 @@ vision = ["pillow"] [metadata] lock-version = "2.0" python-versions = ">=3.9,<3.13" -content-hash = "a5a271b6f3115a47f31c4f215d96b48728057c035a60160da6671879ce8f5be8" +content-hash = "627432e0249902e0e9fb16ae32b5ffac3f04766ea1df54d34bf4a28ad093a1d4" diff --git a/libs/infinity_emb/pyproject.toml b/libs/infinity_emb/pyproject.toml index 8eba524b..b4a94264 100644 --- a/libs/infinity_emb/pyproject.toml +++ b/libs/infinity_emb/pyproject.toml @@ -48,8 +48,6 @@ anyio = "*" trio = "*" coverage = {extras = ["toml"], version = "^7.3.2"} mypy = "^1.5.1" -fastembed = "*" -transformers = "4.40.2" [tool.poetry.group.codespell.dependencies] codespell = "^2.2.0"