huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Small updates.

Browse Source
This commit is contained in:
Nicolas Patry 2024-05-15 11:36:28 +00:00
parent 1bcaf8f5ca
commit e8d02188d0
7 changed files with 138 additions and 119 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

225
server/poetry.lock generated
View File

@ -359,43 +359,45 @@ files = [
[[package]] [[package]]
name = "datasets" name = "datasets"
version = "2.14.4" version = "2.19.1"
description = "HuggingFace community-driven open-source library of datasets" description = "HuggingFace community-driven open-source library of datasets"
optional = true optional = true
python-versions = ">=3.8.0" python-versions = ">=3.8.0"
files = [ files = [
{file = "datasets-2.14.4-py3-none-any.whl", hash = "sha256:29336bd316a7d827ccd4da2236596279b20ca2ac78f64c04c9483da7cbc2459b"}, {file = "datasets-2.19.1-py3-none-any.whl", hash = "sha256:f7a78d15896f45004ccac1c298f3c7121f92f91f6f2bfbd4e4f210f827e6e411"},
{file = "datasets-2.14.4.tar.gz", hash = "sha256:ef29c2b5841de488cd343cfc26ab979bff77efa4d2285af51f1ad7db5c46a83b"}, {file = "datasets-2.19.1.tar.gz", hash = "sha256:0df9ef6c5e9138cdb996a07385220109ff203c204245578b69cca905eb151d3a"},
] ]
[package.dependencies] [package.dependencies]
aiohttp = "*" aiohttp = "*"
dill = ">=0.3.0,<0.3.8" dill = ">=0.3.0,<0.3.9"
fsspec = {version = ">=2021.11.1", extras = ["http"]} filelock = "*"
huggingface-hub = ">=0.14.0,<1.0.0" fsspec = {version = ">=2023.1.0,<=2024.3.1", extras = ["http"]}
huggingface-hub = ">=0.21.2"
multiprocess = "*" multiprocess = "*"
numpy = ">=1.17" numpy = ">=1.17"
packaging = "*" packaging = "*"
pandas = "*" pandas = "*"
pyarrow = ">=8.0.0" pyarrow = ">=12.0.0"
pyarrow-hotfix = "*"
pyyaml = ">=5.1" pyyaml = ">=5.1"
requests = ">=2.19.0" requests = ">=2.19.0"
tqdm = ">=4.62.1" tqdm = ">=4.62.1"
xxhash = "*" xxhash = "*"
[package.extras] [package.extras]
apache-beam = ["apache-beam (>=2.26.0,<2.44.0)"] apache-beam = ["apache-beam (>=2.26.0)"]
audio = ["librosa", "soundfile (>=0.12.1)"] audio = ["librosa", "soundfile (>=0.12.1)"]
benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"] benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"]
dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0)", "black (>=23.1,<24.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "pyyaml (>=5.3.1)", "rarfile (>=4.0)", "ruff (>=0.0.241)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy (<2.0.0)", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch", "transformers", "zstandard"] dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
docs = ["s3fs", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow-macos", "torch", "transformers"] docs = ["s3fs", "tensorflow (>=2.6.0)", "torch", "transformers"]
jax = ["jax (>=0.2.8,!=0.3.2,<=0.3.25)", "jaxlib (>=0.1.65,<=0.3.25)"] jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"]
metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"] metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"]
quality = ["black (>=23.1,<24.0)", "pyyaml (>=5.3.1)", "ruff (>=0.0.241)"] quality = ["ruff (>=0.3.0)"]
s3 = ["s3fs"] s3 = ["s3fs"]
tensorflow = ["tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow-macos"] tensorflow = ["tensorflow (>=2.6.0)"]
tensorflow-gpu = ["tensorflow-gpu (>=2.2.0,!=2.6.0,!=2.6.1)"] tensorflow-gpu = ["tensorflow (>=2.6.0)"]
tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy (<2.0.0)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch", "transformers", "zstandard"] tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "polars[timezone] (>=0.20.0)", "protobuf (<4.0.0)", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.6.0)", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"]
torch = ["torch"] torch = ["torch"]
vision = ["Pillow (>=6.2.1)"] vision = ["Pillow (>=6.2.1)"]
@ -418,17 +420,18 @@ dev = ["PyTest", "PyTest-Cov", "bump2version (<1)", "sphinx (<2)", "tox"]
[[package]] [[package]]
name = "dill" name = "dill"
version = "0.3.7" version = "0.3.8"
description = "serialize all of Python" description = "serialize all of Python"
optional = true optional = true
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "dill-0.3.7-py3-none-any.whl", hash = "sha256:76b122c08ef4ce2eedcd4d1abd8e641114bfc6c2867f49f3c41facf65bf19f5e"}, {file = "dill-0.3.8-py3-none-any.whl", hash = "sha256:c36ca9ffb54365bdd2f8eb3eff7d2a21237f8452b57ace88b1ac615b7e815bd7"},
{file = "dill-0.3.7.tar.gz", hash = "sha256:cc1c8b182eb3013e24bd475ff2e9295af86c1a38eb1aff128dac8962a9ce3c03"}, {file = "dill-0.3.8.tar.gz", hash = "sha256:3ebe3c479ad625c4553aca177444d89b486b1d84982eeacded644afc0cf797ca"},
] ]
[package.extras] [package.extras]
graph = ["objgraph (>=1.7.2)"] graph = ["objgraph (>=1.7.2)"]
profile = ["gprof2dot (>=2022.7.29)"]
[[package]] [[package]]
name = "diskcache" name = "diskcache"
@ -871,13 +874,13 @@ files = [
[[package]] [[package]]
name = "huggingface-hub" name = "huggingface-hub"
version = "0.19.4" version = "0.23.0"
description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub" description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
optional = false optional = false
python-versions = ">=3.8.0" python-versions = ">=3.8.0"
files = [ files = [
{file = "huggingface_hub-0.19.4-py3-none-any.whl", hash = "sha256:dba013f779da16f14b606492828f3760600a1e1801432d09fe1c33e50b825bb5"}, {file = "huggingface_hub-0.23.0-py3-none-any.whl", hash = "sha256:075c30d48ee7db2bba779190dc526d2c11d422aed6f9044c5e2fdc2c432fdb91"},
{file = "huggingface_hub-0.19.4.tar.gz", hash = "sha256:176a4fc355a851c17550e7619488f383189727eab209534d7cef2114dae77b22"}, {file = "huggingface_hub-0.23.0.tar.gz", hash = "sha256:7126dedd10a4c6fac796ced4d87a8cf004efc722a5125c2c09299017fa366fa9"},
] ]
[package.dependencies] [package.dependencies]
@ -890,16 +893,17 @@ tqdm = ">=4.42.1"
typing-extensions = ">=3.7.4.3" typing-extensions = ">=3.7.4.3"
[package.extras] [package.extras]
all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "mypy (==1.5.1)", "numpy", "pydantic (>1.1,<2.0)", "pydantic (>1.1,<3.0)", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "ruff (>=0.1.3)", "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", "fastapi", "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)"] cli = ["InquirerPy (==0.3.4)"]
dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "mypy (==1.5.1)", "numpy", "pydantic (>1.1,<2.0)", "pydantic (>1.1,<3.0)", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "ruff (>=0.1.3)", "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", "fastapi", "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)"]
docs = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "hf-doc-builder", "jedi", "mypy (==1.5.1)", "numpy", "pydantic (>1.1,<2.0)", "pydantic (>1.1,<3.0)", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "ruff (>=0.1.3)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)", "watchdog"]
fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"] fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
inference = ["aiohttp", "pydantic (>1.1,<2.0)", "pydantic (>1.1,<3.0)"] hf-transfer = ["hf-transfer (>=0.1.4)"]
quality = ["mypy (==1.5.1)", "ruff (>=0.1.3)"] inference = ["aiohttp", "minijinja (>=1.0)"]
quality = ["mypy (==1.5.1)", "ruff (>=0.3.0)"]
tensorflow = ["graphviz", "pydot", "tensorflow"] tensorflow = ["graphviz", "pydot", "tensorflow"]
testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "numpy", "pydantic (>1.1,<2.0)", "pydantic (>1.1,<3.0)", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"] tensorflow-testing = ["keras (<3.0)", "tensorflow"]
torch = ["torch"] testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "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)"] typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"]
[[package]] [[package]]
@ -1282,31 +1286,27 @@ files = [
[[package]] [[package]]
name = "multiprocess" name = "multiprocess"
version = "0.70.15" version = "0.70.16"
description = "better multiprocessing and multithreading in Python" description = "better multiprocessing and multithreading in Python"
optional = true optional = true
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "multiprocess-0.70.15-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:aa36c7ed16f508091438687fe9baa393a7a8e206731d321e443745e743a0d4e5"}, {file = "multiprocess-0.70.16-pp310-pypy310_pp73-macosx_10_13_x86_64.whl", hash = "sha256:476887be10e2f59ff183c006af746cb6f1fd0eadcfd4ef49e605cbe2659920ee"},
{file = "multiprocess-0.70.15-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:20e024018c46d0d1602024c613007ac948f9754659e3853b0aa705e83f6931d8"}, {file = "multiprocess-0.70.16-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d951bed82c8f73929ac82c61f01a7b5ce8f3e5ef40f5b52553b4f547ce2b08ec"},
{file = "multiprocess-0.70.15-pp37-pypy37_pp73-manylinux_2_24_i686.whl", hash = "sha256:e576062981c91f0fe8a463c3d52506e598dfc51320a8dd8d78b987dfca91c5db"}, {file = "multiprocess-0.70.16-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:37b55f71c07e2d741374998c043b9520b626a8dddc8b3129222ca4f1a06ef67a"},
{file = "multiprocess-0.70.15-pp37-pypy37_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:e73f497e6696a0f5433ada2b3d599ae733b87a6e8b008e387c62ac9127add177"}, {file = "multiprocess-0.70.16-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:ba8c31889abf4511c7308a8c52bb4a30b9d590e7f58523302ba00237702ca054"},
{file = "multiprocess-0.70.15-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:73db2e7b32dcc7f9b0f075c2ffa45c90b6729d3f1805f27e88534c8d321a1be5"}, {file = "multiprocess-0.70.16-pp39-pypy39_pp73-macosx_10_13_x86_64.whl", hash = "sha256:0dfd078c306e08d46d7a8d06fb120313d87aa43af60d66da43ffff40b44d2f41"},
{file = "multiprocess-0.70.15-pp38-pypy38_pp73-manylinux_2_24_i686.whl", hash = "sha256:4271647bd8a49c28ecd6eb56a7fdbd3c212c45529ad5303b40b3c65fc6928e5f"}, {file = "multiprocess-0.70.16-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:e7b9d0f307cd9bd50851afaac0dba2cb6c44449efff697df7c7645f7d3f2be3a"},
{file = "multiprocess-0.70.15-pp38-pypy38_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:cf981fb998d6ec3208cb14f0cf2e9e80216e834f5d51fd09ebc937c32b960902"}, {file = "multiprocess-0.70.16-py310-none-any.whl", hash = "sha256:c4a9944c67bd49f823687463660a2d6daae94c289adff97e0f9d696ba6371d02"},
{file = "multiprocess-0.70.15-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:18f9f2c7063346d1617bd1684fdcae8d33380ae96b99427260f562e1a1228b67"}, {file = "multiprocess-0.70.16-py311-none-any.whl", hash = "sha256:af4cabb0dac72abfb1e794fa7855c325fd2b55a10a44628a3c1ad3311c04127a"},
{file = "multiprocess-0.70.15-pp39-pypy39_pp73-manylinux_2_24_i686.whl", hash = "sha256:0eac53214d664c49a34695e5824872db4006b1a465edd7459a251809c3773370"}, {file = "multiprocess-0.70.16-py312-none-any.whl", hash = "sha256:fc0544c531920dde3b00c29863377f87e1632601092ea2daca74e4beb40faa2e"},
{file = "multiprocess-0.70.15-pp39-pypy39_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:1a51dd34096db47fb21fa2b839e615b051d51b97af9a67afbcdaa67186b44883"}, {file = "multiprocess-0.70.16-py38-none-any.whl", hash = "sha256:a71d82033454891091a226dfc319d0cfa8019a4e888ef9ca910372a446de4435"},
{file = "multiprocess-0.70.15-py310-none-any.whl", hash = "sha256:7dd58e33235e83cf09d625e55cffd7b0f0eede7ee9223cdd666a87624f60c21a"}, {file = "multiprocess-0.70.16-py39-none-any.whl", hash = "sha256:a0bafd3ae1b732eac64be2e72038231c1ba97724b60b09400d68f229fcc2fbf3"},
{file = "multiprocess-0.70.15-py311-none-any.whl", hash = "sha256:134f89053d82c9ed3b73edd3a2531eb791e602d4f4156fc92a79259590bd9670"}, {file = "multiprocess-0.70.16.tar.gz", hash = "sha256:161af703d4652a0e1410be6abccecde4a7ddffd19341be0a7011b94aeb171ac1"},
{file = "multiprocess-0.70.15-py37-none-any.whl", hash = "sha256:f7d4a1629bccb433114c3b4885f69eccc200994323c80f6feee73b0edc9199c5"},
{file = "multiprocess-0.70.15-py38-none-any.whl", hash = "sha256:bee9afba476c91f9ebee7beeee0601face9eff67d822e893f9a893725fbd6316"},
{file = "multiprocess-0.70.15-py39-none-any.whl", hash = "sha256:3e0953f5d52b4c76f1c973eaf8214554d146f2be5decb48e928e55c7a2d19338"},
{file = "multiprocess-0.70.15.tar.gz", hash = "sha256:f20eed3036c0ef477b07a4177cf7c1ba520d9a2677870a4f47fe026f0cd6787e"},
] ]
[package.dependencies] [package.dependencies]
dill = ">=0.3.7" dill = ">=0.3.8"
[[package]] [[package]]
name = "nest-asyncio" name = "nest-asyncio"
@ -2034,52 +2034,63 @@ files = [
[[package]] [[package]]
name = "pyarrow" name = "pyarrow"
version = "16.0.0" version = "16.1.0"
description = "Python library for Apache Arrow" description = "Python library for Apache Arrow"
optional = true optional = true
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "pyarrow-16.0.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:22a1fdb1254e5095d629e29cd1ea98ed04b4bbfd8e42cc670a6b639ccc208b60"}, {file = "pyarrow-16.1.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:17e23b9a65a70cc733d8b738baa6ad3722298fa0c81d88f63ff94bf25eaa77b9"},
{file = "pyarrow-16.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:574a00260a4ed9d118a14770edbd440b848fcae5a3024128be9d0274dbcaf858"}, {file = "pyarrow-16.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4740cc41e2ba5d641071d0ab5e9ef9b5e6e8c7611351a5cb7c1d175eaf43674a"},
{file = "pyarrow-16.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c0815d0ddb733b8c1b53a05827a91f1b8bde6240f3b20bf9ba5d650eb9b89cdf"}, {file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:98100e0268d04e0eec47b73f20b39c45b4006f3c4233719c3848aa27a03c1aef"},
{file = "pyarrow-16.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df0080339387b5d30de31e0a149c0c11a827a10c82f0c67d9afae3981d1aabb7"}, {file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f68f409e7b283c085f2da014f9ef81e885d90dcd733bd648cfba3ef265961848"},
{file = "pyarrow-16.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:edf38cce0bf0dcf726e074159c60516447e4474904c0033f018c1f33d7dac6c5"}, {file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:a8914cd176f448e09746037b0c6b3a9d7688cef451ec5735094055116857580c"},
{file = "pyarrow-16.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:91d28f9a40f1264eab2af7905a4d95320ac2f287891e9c8b0035f264fe3c3a4b"}, {file = "pyarrow-16.1.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:48be160782c0556156d91adbdd5a4a7e719f8d407cb46ae3bb4eaee09b3111bd"},
{file = "pyarrow-16.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:99af421ee451a78884d7faea23816c429e263bd3618b22d38e7992c9ce2a7ad9"}, {file = "pyarrow-16.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:9cf389d444b0f41d9fe1444b70650fea31e9d52cfcb5f818b7888b91b586efff"},
{file = "pyarrow-16.0.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:d22d0941e6c7bafddf5f4c0662e46f2075850f1c044bf1a03150dd9e189427ce"}, {file = "pyarrow-16.1.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:d0ebea336b535b37eee9eee31761813086d33ed06de9ab6fc6aaa0bace7b250c"},
{file = "pyarrow-16.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:266ddb7e823f03733c15adc8b5078db2df6980f9aa93d6bb57ece615df4e0ba7"}, {file = "pyarrow-16.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2e73cfc4a99e796727919c5541c65bb88b973377501e39b9842ea71401ca6c1c"},
{file = "pyarrow-16.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5cc23090224b6594f5a92d26ad47465af47c1d9c079dd4a0061ae39551889efe"}, {file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bf9251264247ecfe93e5f5a0cd43b8ae834f1e61d1abca22da55b20c788417f6"},
{file = "pyarrow-16.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56850a0afe9ef37249d5387355449c0f94d12ff7994af88f16803a26d38f2016"}, {file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ddf5aace92d520d3d2a20031d8b0ec27b4395cab9f74e07cc95edf42a5cc0147"},
{file = "pyarrow-16.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:705db70d3e2293c2f6f8e84874b5b775f690465798f66e94bb2c07bab0a6bb55"}, {file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:25233642583bf658f629eb230b9bb79d9af4d9f9229890b3c878699c82f7d11e"},
{file = "pyarrow-16.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:5448564754c154997bc09e95a44b81b9e31ae918a86c0fcb35c4aa4922756f55"}, {file = "pyarrow-16.1.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:a33a64576fddfbec0a44112eaf844c20853647ca833e9a647bfae0582b2ff94b"},
{file = "pyarrow-16.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:729f7b262aa620c9df8b9967db96c1575e4cfc8c25d078a06968e527b8d6ec05"}, {file = "pyarrow-16.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:185d121b50836379fe012753cf15c4ba9638bda9645183ab36246923875f8d1b"},
{file = "pyarrow-16.0.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:fb8065dbc0d051bf2ae2453af0484d99a43135cadabacf0af588a3be81fbbb9b"}, {file = "pyarrow-16.1.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:2e51ca1d6ed7f2e9d5c3c83decf27b0d17bb207a7dea986e8dc3e24f80ff7d6f"},
{file = "pyarrow-16.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:20ce707d9aa390593ea93218b19d0eadab56390311cb87aad32c9a869b0e958c"}, {file = "pyarrow-16.1.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:06ebccb6f8cb7357de85f60d5da50e83507954af617d7b05f48af1621d331c9a"},
{file = "pyarrow-16.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5823275c8addbbb50cd4e6a6839952682a33255b447277e37a6f518d6972f4e1"}, {file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b04707f1979815f5e49824ce52d1dceb46e2f12909a48a6a753fe7cafbc44a0c"},
{file = "pyarrow-16.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ab8b9050752b16a8b53fcd9853bf07d8daf19093533e990085168f40c64d978"}, {file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d32000693deff8dc5df444b032b5985a48592c0697cb6e3071a5d59888714e2"},
{file = "pyarrow-16.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:42e56557bc7c5c10d3e42c3b32f6cff649a29d637e8f4e8b311d334cc4326730"}, {file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:8785bb10d5d6fd5e15d718ee1d1f914fe768bf8b4d1e5e9bf253de8a26cb1628"},
{file = "pyarrow-16.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:2a7abdee4a4a7cfa239e2e8d721224c4b34ffe69a0ca7981354fe03c1328789b"}, {file = "pyarrow-16.1.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:e1369af39587b794873b8a307cc6623a3b1194e69399af0efd05bb202195a5a7"},
{file = "pyarrow-16.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:ef2f309b68396bcc5a354106741d333494d6a0d3e1951271849787109f0229a6"}, {file = "pyarrow-16.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:febde33305f1498f6df85e8020bca496d0e9ebf2093bab9e0f65e2b4ae2b3444"},
{file = "pyarrow-16.0.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:ed66e5217b4526fa3585b5e39b0b82f501b88a10d36bd0d2a4d8aa7b5a48e2df"}, {file = "pyarrow-16.1.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:b5f5705ab977947a43ac83b52ade3b881eb6e95fcc02d76f501d549a210ba77f"},
{file = "pyarrow-16.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cc8814310486f2a73c661ba8354540f17eef51e1b6dd090b93e3419d3a097b3a"}, {file = "pyarrow-16.1.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:0d27bf89dfc2576f6206e9cd6cf7a107c9c06dc13d53bbc25b0bd4556f19cf5f"},
{file = "pyarrow-16.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3c2f5e239db7ed43e0ad2baf46a6465f89c824cc703f38ef0fde927d8e0955f7"}, {file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d07de3ee730647a600037bc1d7b7994067ed64d0eba797ac74b2bc77384f4c2"},
{file = "pyarrow-16.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f293e92d1db251447cb028ae12f7bc47526e4649c3a9924c8376cab4ad6b98bd"}, {file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fbef391b63f708e103df99fbaa3acf9f671d77a183a07546ba2f2c297b361e83"},
{file = "pyarrow-16.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:dd9334a07b6dc21afe0857aa31842365a62eca664e415a3f9536e3a8bb832c07"}, {file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:19741c4dbbbc986d38856ee7ddfdd6a00fc3b0fc2d928795b95410d38bb97d15"},
{file = "pyarrow-16.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:d91073d1e2fef2c121154680e2ba7e35ecf8d4969cc0af1fa6f14a8675858159"}, {file = "pyarrow-16.1.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:f2c5fb249caa17b94e2b9278b36a05ce03d3180e6da0c4c3b3ce5b2788f30eed"},
{file = "pyarrow-16.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:71d52561cd7aefd22cf52538f262850b0cc9e4ec50af2aaa601da3a16ef48877"}, {file = "pyarrow-16.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:e6b6d3cd35fbb93b70ade1336022cc1147b95ec6af7d36906ca7fe432eb09710"},
{file = "pyarrow-16.0.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:b93c9a50b965ee0bf4fef65e53b758a7e8dcc0c2d86cebcc037aaaf1b306ecc0"}, {file = "pyarrow-16.1.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:18da9b76a36a954665ccca8aa6bd9f46c1145f79c0bb8f4f244f5f8e799bca55"},
{file = "pyarrow-16.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:d831690844706e374c455fba2fb8cfcb7b797bfe53ceda4b54334316e1ac4fa4"}, {file = "pyarrow-16.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:99f7549779b6e434467d2aa43ab2b7224dd9e41bdde486020bae198978c9e05e"},
{file = "pyarrow-16.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:35692ce8ad0b8c666aa60f83950957096d92f2a9d8d7deda93fb835e6053307e"}, {file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f07fdffe4fd5b15f5ec15c8b64584868d063bc22b86b46c9695624ca3505b7b4"},
{file = "pyarrow-16.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9dd3151d098e56f16a8389c1247137f9e4c22720b01c6f3aa6dec29a99b74d80"}, {file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ddfe389a08ea374972bd4065d5f25d14e36b43ebc22fc75f7b951f24378bf0b5"},
{file = "pyarrow-16.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:bd40467bdb3cbaf2044ed7a6f7f251c8f941c8b31275aaaf88e746c4f3ca4a7a"}, {file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:3b20bd67c94b3a2ea0a749d2a5712fc845a69cb5d52e78e6449bbd295611f3aa"},
{file = "pyarrow-16.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:00a1dcb22ad4ceb8af87f7bd30cc3354788776c417f493089e0a0af981bc8d80"}, {file = "pyarrow-16.1.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:ba8ac20693c0bb0bf4b238751d4409e62852004a8cf031c73b0e0962b03e45e3"},
{file = "pyarrow-16.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:fda9a7cebd1b1d46c97b511f60f73a5b766a6de4c5236f144f41a5d5afec1f35"}, {file = "pyarrow-16.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:31a1851751433d89a986616015841977e0a188662fcffd1a5677453f1df2de0a"},
{file = "pyarrow-16.0.0.tar.gz", hash = "sha256:59bb1f1edbbf4114c72415f039f1359f1a57d166a331c3229788ccbfbb31689a"}, {file = "pyarrow-16.1.0.tar.gz", hash = "sha256:15fbb22ea96d11f0b5768504a3f961edab25eaf4197c341720c4a387f6c60315"},
] ]
[package.dependencies] [package.dependencies]
numpy = ">=1.16.6" numpy = ">=1.16.6"
[[package]]
name = "pyarrow-hotfix"
version = "0.6"
description = ""
optional = true
python-versions = ">=3.5"
files = [
{file = "pyarrow_hotfix-0.6-py3-none-any.whl", hash = "sha256:dcc9ae2d220dff0083be6a9aa8e0cdee5182ad358d4931fce825c545e5c89178"},
{file = "pyarrow_hotfix-0.6.tar.gz", hash = "sha256:79d3e030f7ff890d408a100ac16d6f00b14d44a502d7897cd9fc3e3a534e9945"},
]
[[package]] [[package]]
name = "pydantic" name = "pydantic"
version = "2.7.1" version = "2.7.1"
@ -3016,18 +3027,16 @@ telegram = ["requests"]
[[package]] [[package]]
name = "transformers" name = "transformers"
version = "4.40.2" version = "4.41.0.dev0"
description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
optional = false optional = false
python-versions = ">=3.8.0" python-versions = ">=3.8.0"
files = [ files = []
{file = "transformers-4.40.2-py3-none-any.whl", hash = "sha256:71cb94301ec211a2e1d4b8c8d18dcfaa902dfa00a089dceca167a8aa265d6f2d"}, develop = false
{file = "transformers-4.40.2.tar.gz", hash = "sha256:657b6054a2097671398d976ad46e60836e7e15f9ea9551631a96e33cb9240649"},
]
[package.dependencies] [package.dependencies]
filelock = "*" filelock = "*"
huggingface-hub = ">=0.19.3,<1.0" huggingface-hub = ">=0.23.0,<1.0"
numpy = ">=1.17" numpy = ">=1.17"
packaging = ">=20.0" packaging = ">=20.0"
pyyaml = ">=5.1" pyyaml = ">=5.1"
@ -3040,27 +3049,25 @@ tqdm = ">=4.27"
[package.extras] [package.extras]
accelerate = ["accelerate (>=0.21.0)"] 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"] 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)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "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)"] audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
codecarbon = ["codecarbon (==1.2.0)"] codecarbon = ["codecarbon (==1.2.0)"]
deepspeed = ["accelerate (>=0.21.0)", "deepspeed (>=0.9.3)"] 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"] deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "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)", "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 = ["GitPython (<3.1.19)", "GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "datasets (!=2.5.0)", "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)", "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)", "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", "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-tensorflow = ["GitPython (<3.1.19)", "GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "datasets (!=2.5.0)", "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", "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)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>2.9,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "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)"] dev-torch = ["GitPython (<3.1.19)", "GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "datasets (!=2.5.0)", "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)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "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"] 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)"]
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)"]
flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
ftfy = ["ftfy"] ftfy = ["ftfy"]
integrations = ["optuna", "ray[tune] (>=2.7.0)", "sigopt"] integrations = ["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)"] 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)"]
modelcreation = ["cookiecutter (==1.7.3)"] modelcreation = ["cookiecutter (==1.7.3)"]
natten = ["natten (>=0.14.6,<0.15.0)"] natten = ["natten (>=0.14.6,<0.15.0)"]
onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"] onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"]
onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"] onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
optuna = ["optuna"] 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)"] ray = ["ray[tune] (>=2.7.0)"]
retrieval = ["datasets (!=2.5.0)", "faiss-cpu"] retrieval = ["datasets (!=2.5.0)", "faiss-cpu"]
sagemaker = ["sagemaker (>=2.31.0)"] sagemaker = ["sagemaker (>=2.31.0)"]
@ -3069,19 +3076,25 @@ serving = ["fastapi", "pydantic", "starlette", "uvicorn"]
sigopt = ["sigopt"] sigopt = ["sigopt"]
sklearn = ["scikit-learn"] sklearn = ["scikit-learn"]
speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] 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"] testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "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 (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"] tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>2.9,<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"] 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)"] tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
timm = ["timm"] timm = ["timm"]
tokenizers = ["tokenizers (>=0.19,<0.20)"] tokenizers = ["tokenizers (>=0.19,<0.20)"]
torch = ["accelerate (>=0.21.0)", "torch"] torch = ["accelerate (>=0.21.0)", "torch"]
torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"] 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)"] video = ["av (==9.2.0)", "decord (==0.6.0)"]
vision = ["Pillow (>=10.0.1,<=15.0)"] vision = ["Pillow (>=10.0.1,<=15.0)"]
[package.source]
type = "git"
url = "https://github.com/huggingface/transformers.git"
reference = "b8aee2e"
resolved_reference = "b8aee2e918d7ba2d5e9e80162ae26b4806873307"
[[package]] [[package]]
name = "triton" name = "triton"
version = "2.3.0" version = "2.3.0"
@ -3488,4 +3501,4 @@ torch = ["torch"]
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = ">=3.9,<3.13" python-versions = ">=3.9,<3.13"
content-hash = "df83b265d0263870b5d1ae8bfd847f406abef90868fdf528ff38527b512f86c0" content-hash = "b2a29b0b6e32d0e7043e94b984c5731f2c27c5d95feccbeb80bd890db22d6c4a"

5
server/pyproject.toml
View File

@ -25,8 +25,9 @@ opentelemetry-instrumentation-grpc = "^0.36b0"
hf-transfer = "^0.1.2" hf-transfer = "^0.1.2"
sentencepiece = "^0.1.97" sentencepiece = "^0.1.97"
tokenizers = "^0.19.1" tokenizers = "^0.19.1"
huggingface-hub = "^0.19.3" huggingface-hub = "^0.23"
transformers = "^4.40" # transformers = "^4.40"
transformers = { git = "https://github.com/huggingface/transformers.git", rev="b8aee2e" }
einops = "^0.6.1" einops = "^0.6.1"
texttable = { version = "^1.6.7", optional = true } texttable = { version = "^1.6.7", optional = true }
datasets = { version = "^2.14.0", optional = true } datasets = { version = "^2.14.0", optional = true }

4
server/requirements_cuda.txt
View File

@ -13,7 +13,7 @@ grpcio-reflection==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13" grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.63.0 ; python_version >= "3.9" and python_version < "3.13" grpcio==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13" hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.19.4 ; python_version >= "3.9" and python_version < "3.13" huggingface-hub==0.23.0 ; python_version >= "3.9" and python_version < "3.13"
idna==3.7 ; python_version >= "3.9" and python_version < "3.13" idna==3.7 ; python_version >= "3.9" and python_version < "3.13"
loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13" loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13" numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
@ -40,7 +40,7 @@ sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13" setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13"
tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13" tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13" tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.40.2 ; python_version >= "3.9" and python_version < "3.13" transformers @ git+https://github.com/huggingface/transformers.git@b8aee2e918d7ba2d5e9e80162ae26b4806873307 ; python_version >= "3.9" and python_version < "3.13"
typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13" typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13" typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13" urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13"

4
server/requirements_rocm.txt
View File

@ -13,7 +13,7 @@ grpcio-reflection==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13" grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.63.0 ; python_version >= "3.9" and python_version < "3.13" grpcio==1.63.0 ; python_version >= "3.9" and python_version < "3.13"
hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13" hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.19.4 ; python_version >= "3.9" and python_version < "3.13" huggingface-hub==0.23.0 ; python_version >= "3.9" and python_version < "3.13"
idna==3.7 ; python_version >= "3.9" and python_version < "3.13" idna==3.7 ; python_version >= "3.9" and python_version < "3.13"
loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13" loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13" numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
@ -40,7 +40,7 @@ sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13" setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13"
tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13" tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13" tqdm==4.66.4 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.40.2 ; python_version >= "3.9" and python_version < "3.13" transformers @ git+https://github.com/huggingface/transformers.git@b8aee2e918d7ba2d5e9e80162ae26b4806873307 ; python_version >= "3.9" and python_version < "3.13"
typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13" typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13" typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13" urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13"

4
server/text_generation_server/layers/linear.py
View File

@ -10,9 +10,9 @@ class FastLinear(torch.nn.Module):
bias, bias,
) -> None: ) -> None:
super().__init__() super().__init__()
self.weight = torch.nn.Parameter(weight) self.weight = torch.nn.Parameter(weight, requires_grad=False)
if bias is not None: if bias is not None:
self.bias = torch.nn.Parameter(bias) self.bias = torch.nn.Parameter(bias, requires_grad=False)
else: else:
self.bias = None self.bias = None

9
server/text_generation_server/models/custom_modeling/flash_gemma_modeling.py
View File

@ -99,8 +99,13 @@ class GemmaConfig(PretrainedConfig):
class GemmaFastRMSNorm(FastRMSNorm): class GemmaFastRMSNorm(FastRMSNorm):
@classmethod @classmethod
def load(cls, prefix, weights, eps=1e-6): def load(cls, prefix, weights, eps=1e-6):
dtype = weights.dtype
weights.dtype = torch.float32
weight = weights.get_tensor(f"{prefix}.weight") + 1 weight = weights.get_tensor(f"{prefix}.weight") + 1
return cls(weight, eps) weights.dtype = dtype
new = cls(weight, eps)
new.dtype = dtype
return new
# perform the multiplication in full precision and downcast after # perform the multiplication in full precision and downcast after
def forward(self, hidden_states, residual=None): def forward(self, hidden_states, residual=None):
@ -111,7 +116,7 @@ class GemmaFastRMSNorm(FastRMSNorm):
variance = hidden_states.pow(2).mean(-1, keepdim=True) variance = hidden_states.pow(2).mean(-1, keepdim=True)
hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon) hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
hidden_states = hidden_states * self.weight hidden_states = hidden_states * self.weight
return hidden_states.to(self.weight.dtype), residual return hidden_states.to(self.dtype), residual
def load_attention(config, prefix, weights): def load_attention(config, prefix, weights):

6
server/text_generation_server/models/custom_modeling/flash_pali_gemma_modeling.py
View File

@ -34,14 +34,14 @@ class PaliGemmaForConditionalGeneration(nn.Module):
prefix="vision_tower" if not prefix else f"{prefix}.vision_tower", prefix="vision_tower" if not prefix else f"{prefix}.vision_tower",
config=config.vision_config, config=config.vision_config,
weights=weights, weights=weights,
).to(weights.device, weights.dtype) )
self.multi_modal_projector = TensorParallelColumnLinear.load( self.multi_modal_projector = TensorParallelColumnLinear.load(
config, config,
prefix="multi_modal_projector.linear", prefix="multi_modal_projector.linear",
weights=weights, weights=weights,
bias=True, bias=True,
).to(weights.device, weights.dtype) )
self.vocab_size = config.vocab_size self.vocab_size = config.vocab_size
self.config = config self.config = config
@ -53,7 +53,7 @@ class PaliGemmaForConditionalGeneration(nn.Module):
prefix="language_model" if not prefix else f"{prefix}.language_model", prefix="language_model" if not prefix else f"{prefix}.language_model",
config=config.text_config, config=config.text_config,
weights=weights, weights=weights,
).to(weights.device, weights.dtype) )
self.pad_token_id = ( self.pad_token_id = (
config.pad_token_id if config.pad_token_id is not None else -1 config.pad_token_id if config.pad_token_id is not None else -1
) )