From 6dc511ded0d43846ea9f8d947408aa3fc228ce0c Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 30 Sep 2025 01:45:08 +0000 Subject: [PATCH] Bump marker-pdf from 1.7.5 to 1.10.0 Bumps [marker-pdf](https://github.com/VikParuchuri/marker) from 1.7.5 to 1.10.0. - [Release notes](https://github.com/VikParuchuri/marker/releases) - [Commits](https://github.com/VikParuchuri/marker/compare/v1.7.5...v1.10.0) --- updated-dependencies: - dependency-name: marker-pdf dependency-version: 1.10.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] --- poetry.lock | 139 +++++++++++++++++++++++++++------------------------- 1 file changed, 71 insertions(+), 68 deletions(-) diff --git a/poetry.lock b/poetry.lock index e08a7e97..11d71636 100644 --- a/poetry.lock +++ b/poetry.lock @@ -732,21 +732,21 @@ files = [ [[package]] name = "hf-xet" -version = "1.1.2" +version = "1.1.10" description = "Fast transfer of large files with the Hugging Face Hub." optional = true python-versions = ">=3.8" groups = ["main"] markers = "extra == \"pdf\" and (platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"arm64\" or platform_machine == \"aarch64\")" files = [ - {file = "hf_xet-1.1.2-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:dfd1873fd648488c70735cb60f7728512bca0e459e61fcd107069143cd798469"}, - {file = "hf_xet-1.1.2-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:29b584983b2d977c44157d9241dcf0fd50acde0b7bff8897fe4386912330090d"}, - {file = "hf_xet-1.1.2-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b29ac84298147fe9164cc55ad994ba47399f90b5d045b0b803b99cf5f06d8ec"}, - {file = "hf_xet-1.1.2-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:d921ba32615676e436a0d15e162331abc9ed43d440916b1d836dc27ce1546173"}, - {file = "hf_xet-1.1.2-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:d9b03c34e13c44893ab6e8fea18ee8d2a6878c15328dd3aabedbdd83ee9f2ed3"}, - {file = "hf_xet-1.1.2-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:01b18608955b3d826307d37da8bd38b28a46cd2d9908b3a3655d1363274f941a"}, - {file = "hf_xet-1.1.2-cp37-abi3-win_amd64.whl", hash = "sha256:3562902c81299b09f3582ddfb324400c6a901a2f3bc854f83556495755f4954c"}, - {file = "hf_xet-1.1.2.tar.gz", hash = "sha256:3712d6d4819d3976a1c18e36db9f503e296283f9363af818f50703506ed63da3"}, + {file = "hf_xet-1.1.10-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:686083aca1a6669bc85c21c0563551cbcdaa5cf7876a91f3d074a030b577231d"}, + {file = "hf_xet-1.1.10-cp37-abi3-macosx_11_0_arm64.whl", hash = "sha256:71081925383b66b24eedff3013f8e6bbd41215c3338be4b94ba75fd75b21513b"}, + {file = "hf_xet-1.1.10-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b6bceb6361c80c1cc42b5a7b4e3efd90e64630bcf11224dcac50ef30a47e435"}, + {file = "hf_xet-1.1.10-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:eae7c1fc8a664e54753ffc235e11427ca61f4b0477d757cc4eb9ae374b69f09c"}, + {file = "hf_xet-1.1.10-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:0a0005fd08f002180f7a12d4e13b22be277725bc23ed0529f8add5c7a6309c06"}, + {file = "hf_xet-1.1.10-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:f900481cf6e362a6c549c61ff77468bd59d6dd082f3170a36acfef2eb6a6793f"}, + {file = "hf_xet-1.1.10-cp37-abi3-win_amd64.whl", hash = "sha256:5f54b19cc347c13235ae7ee98b330c26dd65ef1df47e5316ffb1e87713ca7045"}, + {file = "hf_xet-1.1.10.tar.gz", hash = "sha256:408aef343800a2102374a883f283ff29068055c111f003ff840733d3b715bb97"}, ] [package.extras] @@ -803,21 +803,21 @@ zstd = ["zstandard (>=0.18.0)"] [[package]] name = "huggingface-hub" -version = "0.32.3" +version = "0.35.3" description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub" optional = true python-versions = ">=3.8.0" groups = ["main"] markers = "extra == \"pdf\"" files = [ - {file = "huggingface_hub-0.32.3-py3-none-any.whl", hash = "sha256:e46f7ea7fe2b5e5f67cc4e37eb201140091946a314d7c2b134a9673dadd80b6a"}, - {file = "huggingface_hub-0.32.3.tar.gz", hash = "sha256:752c889ebf3a63cbd39803f6d87ccc135a463bbcb36abfa2faff0ccbf1cec087"}, + {file = "huggingface_hub-0.35.3-py3-none-any.whl", hash = "sha256:0e3a01829c19d86d03793e4577816fe3bdfc1602ac62c7fb220d593d351224ba"}, + {file = "huggingface_hub-0.35.3.tar.gz", hash = "sha256:350932eaa5cc6a4747efae85126ee220e4ef1b54e29d31c3b45c5612ddf0b32a"}, ] [package.dependencies] filelock = "*" fsspec = ">=2023.5.0" -hf-xet = {version = ">=1.1.2,<2.0.0", markers = "platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"arm64\" or platform_machine == \"aarch64\""} +hf-xet = {version = ">=1.1.3,<2.0.0", markers = "platform_machine == \"x86_64\" or platform_machine == \"amd64\" or platform_machine == \"arm64\" or platform_machine == \"aarch64\""} packaging = ">=20.9" pyyaml = ">=5.1" requests = "*" @@ -825,19 +825,19 @@ tqdm = ">=4.42.1" typing-extensions = ">=3.7.4.3" [package.extras] -all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "authlib (>=1.3.2)", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "libcst (==1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.9.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"] +all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "authlib (>=1.3.2)", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "libcst (>=1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures (<16.0)", "pytest-vcr", "pytest-xdist", "ruff (>=0.9.0)", "soundfile", "ty", "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", "authlib (>=1.3.2)", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "libcst (==1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.9.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"] +dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "authlib (>=1.3.2)", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "libcst (>=1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures (<16.0)", "pytest-vcr", "pytest-xdist", "ruff (>=0.9.0)", "soundfile", "ty", "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)"] hf-xet = ["hf-xet (>=1.1.2,<2.0.0)"] inference = ["aiohttp"] mcp = ["aiohttp", "mcp (>=1.8.0)", "typer"] oauth = ["authlib (>=1.3.2)", "fastapi", "httpx", "itsdangerous"] -quality = ["libcst (==1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "ruff (>=0.9.0)"] +quality = ["libcst (>=1.4.0)", "mypy (==1.15.0) ; python_version >= \"3.9\"", "mypy (>=1.14.1,<1.15.0) ; python_version == \"3.8\"", "ruff (>=0.9.0)", "ty"] tensorflow = ["graphviz", "pydot", "tensorflow"] tensorflow-testing = ["keras (<3.0)", "tensorflow"] -testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "authlib (>=1.3.2)", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"] +testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "authlib (>=1.3.2)", "fastapi", "gradio (>=4.0.0)", "httpx", "itsdangerous", "jedi", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures (<16.0)", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"] torch = ["safetensors[torch]", "torch"] typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"] @@ -1355,15 +1355,15 @@ wavedrom = ["wavedrom"] [[package]] name = "markdownify" -version = "0.13.1" +version = "1.2.0" description = "Convert HTML to markdown." optional = true python-versions = "*" groups = ["main"] markers = "extra == \"pdf\"" files = [ - {file = "markdownify-0.13.1-py3-none-any.whl", hash = "sha256:1d181d43d20902bcc69d7be85b5316ed174d0dda72ff56e14ae4c95a4a407d22"}, - {file = "markdownify-0.13.1.tar.gz", hash = "sha256:ab257f9e6bd4075118828a28c9d02f8a4bfeb7421f558834aa79b2dfeb32a098"}, + {file = "markdownify-1.2.0-py3-none-any.whl", hash = "sha256:48e150a1c4993d4d50f282f725c0111bd9eb25645d41fa2f543708fd44161351"}, + {file = "markdownify-1.2.0.tar.gz", hash = "sha256:f6c367c54eb24ee953921804dfe6d6575c5e5b42c643955e7242034435de634c"}, ] [package.dependencies] @@ -1372,15 +1372,15 @@ six = ">=1.15,<2" [[package]] name = "marker-pdf" -version = "1.7.5" +version = "1.10.0" description = "Convert documents to markdown with high speed and accuracy." optional = true python-versions = "<4.0,>=3.10" groups = ["main"] markers = "extra == \"pdf\"" files = [ - {file = "marker_pdf-1.7.5-py3-none-any.whl", hash = "sha256:92dcaa5cd561730ea3ab80e315dbed0c84980947e5685187b202d4e476ddcf3e"}, - {file = "marker_pdf-1.7.5.tar.gz", hash = "sha256:54845fe5f8080ebdf41f59d006c0ca792a4cdef814c18a0f82426a4f62a038cd"}, + {file = "marker_pdf-1.10.0-py3-none-any.whl", hash = "sha256:4f5ba471e69805f0553d00b07b67121a1ff83c8f47b8afca992255f0b5a25f34"}, + {file = "marker_pdf-1.10.0.tar.gz", hash = "sha256:1cd131cc62236b555cfb6d5504336ca6628c456f9787c30d184a241dd26db3a7"}, ] [package.dependencies] @@ -1390,7 +1390,7 @@ filetype = ">=1.2.0,<2.0.0" ftfy = ">=6.1.1,<7.0.0" google-genai = ">=1.0.0,<2.0.0" markdown2 = ">=2.5.2,<3.0.0" -markdownify = ">=0.13.1,<0.14.0" +markdownify = ">=1.1.0,<2.0.0" openai = ">=1.65.2,<2.0.0" pdftext = ">=0.6.3,<0.7.0" Pillow = ">=10.1.0,<11.0.0" @@ -1401,7 +1401,7 @@ python-dotenv = ">=1.0.0,<2.0.0" rapidfuzz = ">=3.8.1,<4.0.0" regex = ">=2024.4.28,<2025.0.0" scikit-learn = ">=1.6.1,<2.0.0" -surya-ocr = ">=0.14.6,<0.15.0" +surya-ocr = ">=0.17.0,<0.18.0" torch = ">=2.7.0,<3.0.0" tqdm = ">=4.66.1,<5.0.0" transformers = ">=4.45.2,<5.0.0" @@ -3681,22 +3681,22 @@ files = [ [[package]] name = "surya-ocr" -version = "0.14.6" +version = "0.17.0" description = "OCR, layout, reading order, and table recognition in 90+ languages" optional = true python-versions = "<4.0,>=3.10" groups = ["main"] markers = "extra == \"pdf\"" files = [ - {file = "surya_ocr-0.14.6-py3-none-any.whl", hash = "sha256:4c89c3a4606838db1d0f6b565eb4e49db8823982212beb581bb819d5bbbb9519"}, - {file = "surya_ocr-0.14.6.tar.gz", hash = "sha256:c85a0bd9dd00c86ab44ed265c0ed15601106dbaf2d0d0a067fa7bb533137d5f0"}, + {file = "surya_ocr-0.17.0-py3-none-any.whl", hash = "sha256:a728adb1aadd26493f1b937ec411f4b041fa93c8e3524c42b4c627c2e4744d5c"}, + {file = "surya_ocr-0.17.0.tar.gz", hash = "sha256:3110ec9a2be0d4296968ced02ee4d33941f34c145a2d6ac508f75122014ed170"}, ] [package.dependencies] click = ">=8.1.8,<9.0.0" einops = ">=0.8.1,<0.9.0" filetype = ">=1.2.0,<2.0.0" -opencv-python-headless = ">=4.11.0.86,<5.0.0.0" +opencv-python-headless = "4.11.0.86" pillow = ">=10.2.0,<11.0.0" platformdirs = ">=4.3.6,<5.0.0" pre-commit = ">=4.2.0,<5.0.0" @@ -3705,7 +3705,7 @@ pydantic-settings = ">=2.1.0,<3.0.0" pypdfium2 = "4.30.0" python-dotenv = ">=1.0.0,<2.0.0" torch = ">=2.7.0,<3.0.0" -transformers = ">=4.51.2,<5.0.0" +transformers = ">=4.56.1" [[package]] name = "sympy" @@ -3741,37 +3741,37 @@ files = [ [[package]] name = "tokenizers" -version = "0.21.1" +version = "0.22.1" description = "" optional = true python-versions = ">=3.9" groups = ["main"] markers = "extra == \"pdf\"" files = [ - {file = "tokenizers-0.21.1-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:e78e413e9e668ad790a29456e677d9d3aa50a9ad311a40905d6861ba7692cf41"}, - {file = "tokenizers-0.21.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:cd51cd0a91ecc801633829fcd1fda9cf8682ed3477c6243b9a095539de4aecf3"}, - {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28da6b72d4fb14ee200a1bd386ff74ade8992d7f725f2bde2c495a9a98cf4d9f"}, - {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:34d8cfde551c9916cb92014e040806122295a6800914bab5865deb85623931cf"}, - {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aaa852d23e125b73d283c98f007e06d4595732104b65402f46e8ef24b588d9f8"}, - {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a21a15d5c8e603331b8a59548bbe113564136dc0f5ad8306dd5033459a226da0"}, - {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2fdbd4c067c60a0ac7eca14b6bd18a5bebace54eb757c706b47ea93204f7a37c"}, - {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2dd9a0061e403546f7377df940e866c3e678d7d4e9643d0461ea442b4f89e61a"}, - {file = "tokenizers-0.21.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:db9484aeb2e200c43b915a1a0150ea885e35f357a5a8fabf7373af333dcc8dbf"}, - {file = "tokenizers-0.21.1-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:ed248ab5279e601a30a4d67bdb897ecbe955a50f1e7bb62bd99f07dd11c2f5b6"}, - {file = "tokenizers-0.21.1-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:9ac78b12e541d4ce67b4dfd970e44c060a2147b9b2a21f509566d556a509c67d"}, - {file = "tokenizers-0.21.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:e5a69c1a4496b81a5ee5d2c1f3f7fbdf95e90a0196101b0ee89ed9956b8a168f"}, - {file = "tokenizers-0.21.1-cp39-abi3-win32.whl", hash = "sha256:1039a3a5734944e09de1d48761ade94e00d0fa760c0e0551151d4dd851ba63e3"}, - {file = "tokenizers-0.21.1-cp39-abi3-win_amd64.whl", hash = "sha256:0f0dcbcc9f6e13e675a66d7a5f2f225a736745ce484c1a4e07476a89ccdad382"}, - {file = "tokenizers-0.21.1.tar.gz", hash = "sha256:a1bb04dc5b448985f86ecd4b05407f5a8d97cb2c0532199b2a302a604a0165ab"}, + {file = "tokenizers-0.22.1-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:59fdb013df17455e5f950b4b834a7b3ee2e0271e6378ccb33aa74d178b513c73"}, + {file = "tokenizers-0.22.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:8d4e484f7b0827021ac5f9f71d4794aaef62b979ab7608593da22b1d2e3c4edc"}, + {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:19d2962dd28bc67c1f205ab180578a78eef89ac60ca7ef7cbe9635a46a56422a"}, + {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:38201f15cdb1f8a6843e6563e6e79f4abd053394992b9bbdf5213ea3469b4ae7"}, + {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d1cbe5454c9a15df1b3443c726063d930c16f047a3cc724b9e6e1a91140e5a21"}, + {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e7d094ae6312d69cc2a872b54b91b309f4f6fbce871ef28eb27b52a98e4d0214"}, + {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:afd7594a56656ace95cdd6df4cca2e4059d294c5cfb1679c57824b605556cb2f"}, + {file = "tokenizers-0.22.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2ef6063d7a84994129732b47e7915e8710f27f99f3a3260b8a38fc7ccd083f4"}, + {file = "tokenizers-0.22.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ba0a64f450b9ef412c98f6bcd2a50c6df6e2443b560024a09fa6a03189726879"}, + {file = "tokenizers-0.22.1-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:331d6d149fa9c7d632cde4490fb8bbb12337fa3a0232e77892be656464f4b446"}, + {file = "tokenizers-0.22.1-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:607989f2ea68a46cb1dfbaf3e3aabdf3f21d8748312dbeb6263d1b3b66c5010a"}, + {file = "tokenizers-0.22.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a0f307d490295717726598ef6fa4f24af9d484809223bbc253b201c740a06390"}, + {file = "tokenizers-0.22.1-cp39-abi3-win32.whl", hash = "sha256:b5120eed1442765cd90b903bb6cfef781fd8fe64e34ccaecbae4c619b7b12a82"}, + {file = "tokenizers-0.22.1-cp39-abi3-win_amd64.whl", hash = "sha256:65fd6e3fb11ca1e78a6a93602490f134d1fdeb13bcef99389d5102ea318ed138"}, + {file = "tokenizers-0.22.1.tar.gz", hash = "sha256:61de6522785310a309b3407bac22d99c4db5dba349935e99e4d15ea2226af2d9"}, ] [package.dependencies] -huggingface-hub = ">=0.16.4,<1.0" +huggingface-hub = ">=0.16.4,<2.0" [package.extras] dev = ["tokenizers[testing]"] docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"] -testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests", "ruff"] +testing = ["black (==22.3)", "datasets", "numpy", "pytest", "pytest-asyncio", "requests", "ruff"] [[package]] name = "tomli" @@ -3903,74 +3903,77 @@ telegram = ["requests"] [[package]] name = "transformers" -version = "4.52.4" +version = "4.56.2" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" optional = true python-versions = ">=3.9.0" groups = ["main"] markers = "extra == \"pdf\"" files = [ - {file = "transformers-4.52.4-py3-none-any.whl", hash = "sha256:203f5c19416d5877e36e88633943761719538a25d9775977a24fe77a1e5adfc7"}, - {file = "transformers-4.52.4.tar.gz", hash = "sha256:aff3764441c1adc192a08dba49740d3cbbcb72d850586075aed6bd89b98203e6"}, + {file = "transformers-4.56.2-py3-none-any.whl", hash = "sha256:79c03d0e85b26cb573c109ff9eafa96f3c8d4febfd8a0774e8bba32702dd6dde"}, + {file = "transformers-4.56.2.tar.gz", hash = "sha256:5e7c623e2d7494105c726dd10f6f90c2c99a55ebe86eef7233765abd0cb1c529"}, ] [package.dependencies] filelock = "*" -huggingface-hub = ">=0.30.0,<1.0" +huggingface-hub = ">=0.34.0,<1.0" numpy = ">=1.17" packaging = ">=20.0" pyyaml = ">=5.1" regex = "!=2019.12.17" requests = "*" safetensors = ">=0.4.3" -tokenizers = ">=0.21,<0.22" +tokenizers = ">=0.22.0,<=0.23.0" tqdm = ">=4.27" [package.extras] accelerate = ["accelerate (>=0.26.0)"] -all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "av", "codecarbon (>=2.8.1)", "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,<0.14.0)", "kernels (>=0.4.4,<0.5)", "librosa", "num2words", "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 (<=1.0.11)", "tokenizers (>=0.21,<0.22)", "torch (>=2.1,<2.7)", "torchaudio", "torchvision"] +all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "av", "codecarbon (>=2.8.1)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "jinja2 (>=3.1.0)", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "kernels (>=0.6.1,<=0.9)", "librosa", "mistral-common[opencv] (>=1.6.3)", "num2words", "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 (!=1.0.18,<=1.0.19)", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "torchaudio", "torchvision"] audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] benchmark = ["optimum-benchmark (>=0.3.0)"] +chat-template = ["jinja2 (>=3.1.0)"] codecarbon = ["codecarbon (>=2.8.1)"] deepspeed = ["accelerate (>=0.26.0)", "deepspeed (>=0.9.3)"] -deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.26.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "nltk (<=3.8.1)", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "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 (>=0.26.0)", "av", "beautifulsoup4", "codecarbon (>=2.8.1)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "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,<0.14.0)", "kernels (>=0.4.4,<0.5)", "libcst", "librosa", "nltk (<=3.8.1)", "num2words", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "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 (<=1.0.11)", "tokenizers (>=0.21,<0.22)", "torch (>=2.1,<2.7)", "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,<0.14.0)", "libcst", "librosa", "nltk (<=3.8.1)", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "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 (>=0.21,<0.22)", "urllib3 (<2.0.0)"] -dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "beautifulsoup4", "codecarbon (>=2.8.1)", "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", "kernels (>=0.4.4,<0.5)", "libcst", "librosa", "nltk (<=3.8.1)", "num2words", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "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 (<=1.0.11)", "tokenizers (>=0.21,<0.22)", "torch (>=2.1,<2.7)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] +deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.26.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "libcst", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "optuna", "parameterized (>=0.9)", "protobuf", "psutil", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "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 (>=0.26.0)", "av", "beautifulsoup4", "codecarbon (>=2.8.1)", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "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)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "jinja2 (>=3.1.0)", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "kernels (>=0.6.1,<=0.9)", "libcst", "librosa", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "num2words", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "pandas (<2.3.0)", "parameterized (>=0.9)", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "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 (!=1.0.18,<=1.0.19)", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "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 (>=2.15.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "kenlm", "keras-nlp (>=0.3.1,<0.14.0)", "libcst", "librosa", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "pandas (<2.3.0)", "parameterized (>=0.9)", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "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 (>=0.22.0,<=0.23.0)", "urllib3 (<2.0.0)"] +dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.26.0)", "beautifulsoup4", "codecarbon (>=2.8.1)", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "kenlm", "kernels (>=0.6.1,<=0.9)", "libcst", "librosa", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "num2words", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "pandas (<2.3.0)", "parameterized (>=0.9)", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rich", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "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 (!=1.0.18,<=1.0.19)", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "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"] hf-xet = ["hf-xet"] -hub-kernels = ["kernels (>=0.4.4,<0.5)"] -integrations = ["kernels (>=0.4.4,<0.5)", "optuna", "ray[tune] (>=2.7.0)", "sigopt"] +hub-kernels = ["kernels (>=0.6.1,<=0.9)"] +integrations = ["kernels (>=0.6.1,<=0.9)", "optuna", "ray[tune] (>=2.7.0)", "sigopt"] ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "rhoknp (>=1.1.0,<1.3.1)", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"] +mistral-common = ["mistral-common[opencv] (>=1.6.3)"] modelcreation = ["cookiecutter (==1.7.3)"] natten = ["natten (>=0.14.6,<0.15.0)"] num2words = ["num2words"] onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"] onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"] +open-telemetry = ["opentelemetry-api", "opentelemetry-exporter-otlp", "opentelemetry-sdk"] optuna = ["optuna"] -quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "isort (>=5.5.4)", "libcst", "rich", "ruff (==0.11.2)", "urllib3 (<2.0.0)"] +quality = ["GitPython (<3.1.19)", "datasets (>=2.15.0)", "libcst", "pandas (<2.3.0)", "rich", "ruff (==0.11.2)", "urllib3 (<2.0.0)"] ray = ["ray[tune] (>=2.7.0)"] -retrieval = ["datasets (!=2.5.0)", "faiss-cpu"] +retrieval = ["datasets (>=2.15.0)", "faiss-cpu"] ruff = ["ruff (==0.11.2)"] sagemaker = ["sagemaker (>=2.31.0)"] sentencepiece = ["protobuf", "sentencepiece (>=0.1.91,!=0.1.92)"] -serving = ["fastapi", "pydantic", "starlette", "uvicorn"] +serving = ["accelerate (>=0.26.0)", "fastapi", "openai (>=1.98.0)", "pydantic (>=2)", "starlette", "torch (>=2.2)", "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", "nltk (<=3.8.1)", "parameterized", "psutil", "pydantic", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] +testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (>=2.15.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "libcst", "mistral-common[opencv] (>=1.6.3)", "nltk (<=3.8.1)", "parameterized (>=0.9)", "psutil", "pydantic (>=2)", "pytest (>=7.2.0)", "pytest-asyncio", "pytest-order", "pytest-rerunfailures", "pytest-rich", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.11.2)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"] tf = ["keras-nlp (>=0.3.1,<0.14.0)", "onnxconverter-common", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] tf-cpu = ["keras (>2.9,<2.16)", "keras-nlp (>=0.3.1,<0.14.0)", "onnxconverter-common", "tensorflow-cpu (>2.9,<2.16)", "tensorflow-probability (<0.24)", "tensorflow-text (<2.16)", "tf2onnx"] tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] tiktoken = ["blobfile", "tiktoken"] -timm = ["timm (<=1.0.11)"] -tokenizers = ["tokenizers (>=0.21,<0.22)"] -torch = ["accelerate (>=0.26.0)", "torch (>=2.1,<2.7)"] +timm = ["timm (!=1.0.18,<=1.0.19)"] +tokenizers = ["tokenizers (>=0.22.0,<=0.23.0)"] +torch = ["accelerate (>=0.26.0)", "torch (>=2.2)"] torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"] -torchhub = ["filelock", "huggingface-hub (>=0.30.0,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.21,<0.22)", "torch (>=2.1,<2.7)", "tqdm (>=4.27)"] +torchhub = ["filelock", "huggingface-hub (>=0.34.0,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.22.0,<=0.23.0)", "torch (>=2.2)", "tqdm (>=4.27)"] video = ["av"] vision = ["Pillow (>=10.0.1,<=15.0)"]