diff --git a/Dockerfile b/Dockerfile
index 576dab8d..2a313c25 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -159,6 +159,11 @@ COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bi
 # Install launcher
 COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher
 
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+        build-essential \
+        g++ \
+        && rm -rf /var/lib/apt/lists/*
+
 # AWS Sagemaker compatbile image
 FROM base as sagemaker
 
diff --git a/server/poetry.lock b/server/poetry.lock
index 5d853ce2..9a6900bc 100644
--- a/server/poetry.lock
+++ b/server/poetry.lock
@@ -1,10 +1,15 @@
+# This file is automatically @generated by Poetry 1.5.1 and should not be changed by hand.
+
 [[package]]
 name = "accelerate"
 version = "0.19.0"
 description = "Accelerate"
-category = "main"
 optional = true
 python-versions = ">=3.7.0"
+files = [
+    {file = "accelerate-0.19.0-py3-none-any.whl", hash = "sha256:2866b0bf9fff08f51e6384c95fa96725838b70f1988d1cce42e56b820d8a91dd"},
+    {file = "accelerate-0.19.0.tar.gz", hash = "sha256:84920226b9e642e453ef37593ee55b956b08d8200dea4087c546c34e26157e76"},
+]
 
 [package.dependencies]
 numpy = ">=1.17"
@@ -18,737 +23,51 @@ dev = ["black (>=23.1,<24.0)", "datasets", "deepspeed", "evaluate", "hf-doc-buil
 quality = ["black (>=23.1,<24.0)", "hf-doc-builder (>=0.3.0)", "ruff (>=0.0.241)", "urllib3 (<2.0.0)"]
 rich = ["rich"]
 sagemaker = ["sagemaker"]
-test_dev = ["datasets", "deepspeed", "evaluate", "scikit-learn", "scipy", "tqdm", "transformers"]
-test_prod = ["parameterized", "pytest", "pytest-subtests", "pytest-xdist"]
-test_trackers = ["comet-ml", "tensorboard", "wandb"]
+test-dev = ["datasets", "deepspeed", "evaluate", "scikit-learn", "scipy", "tqdm", "transformers"]
+test-prod = ["parameterized", "pytest", "pytest-subtests", "pytest-xdist"]
+test-trackers = ["comet-ml", "tensorboard", "wandb"]
 testing = ["datasets", "deepspeed", "evaluate", "parameterized", "pytest", "pytest-subtests", "pytest-xdist", "scikit-learn", "scipy", "tqdm", "transformers"]
 
 [[package]]
 name = "backoff"
 version = "2.2.1"
 description = "Function decoration for backoff and retry"
-category = "main"
 optional = false
 python-versions = ">=3.7,<4.0"
+files = [
+    {file = "backoff-2.2.1-py3-none-any.whl", hash = "sha256:63579f9a0628e06278f7e47b7d7d5b6ce20dc65c5e96a6f3ca99a6adca0396e8"},
+    {file = "backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba"},
+]
 
 [[package]]
 name = "bitsandbytes"
 version = "0.38.1"
 description = "8-bit optimizers and matrix multiplication routines."
-category = "main"
 optional = true
 python-versions = "*"
+files = [
+    {file = "bitsandbytes-0.38.1-py3-none-any.whl", hash = "sha256:5f532e7b1353eb7049ae831da2eb62ed8a1e0444116bd51b9e088a6e0bc7a34a"},
+    {file = "bitsandbytes-0.38.1.tar.gz", hash = "sha256:ba95a806b5065ea3263558e188f07eacb32ad691842932fb0d36a879883167ce"},
+]
 
 [[package]]
 name = "certifi"
 version = "2023.5.7"
 description = "Python package for providing Mozilla's CA Bundle."
-category = "main"
 optional = false
 python-versions = ">=3.6"
+files = [
+    {file = "certifi-2023.5.7-py3-none-any.whl", hash = "sha256:c6c2e98f5c7869efca1f8916fed228dd91539f9f1b444c314c06eef02980c716"},
+    {file = "certifi-2023.5.7.tar.gz", hash = "sha256:0f0d56dc5a6ad56fd4ba36484d6cc34451e1c6548c61daad8c320169f91eddc7"},
+]
 
 [[package]]
 name = "charset-normalizer"
 version = "3.1.0"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
-category = "main"
 optional = false
 python-versions = ">=3.7.0"
-
-[[package]]
-name = "click"
-version = "8.1.3"
-description = "Composable command line interface toolkit"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-colorama = {version = "*", markers = "platform_system == \"Windows\""}
-
-[[package]]
-name = "colorama"
-version = "0.4.6"
-description = "Cross-platform colored terminal text."
-category = "main"
-optional = false
-python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
-
-[[package]]
-name = "Deprecated"
-version = "1.2.13"
-description = "Python @deprecated decorator to deprecate old python classes, functions or methods."
-category = "main"
-optional = false
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
-
-[package.dependencies]
-wrapt = ">=1.10,<2"
-
-[package.extras]
-dev = ["PyTest", "PyTest (<5)", "PyTest-Cov", "PyTest-Cov (<2.6)", "bump2version (<1)", "configparser (<5)", "importlib-metadata (<3)", "importlib-resources (<4)", "sphinx (<2)", "sphinxcontrib-websupport (<2)", "tox", "zipp (<2)"]
-
-[[package]]
-name = "exceptiongroup"
-version = "1.1.1"
-description = "Backport of PEP 654 (exception groups)"
-category = "dev"
-optional = false
-python-versions = ">=3.7"
-
-[package.extras]
-test = ["pytest (>=6)"]
-
-[[package]]
-name = "filelock"
-version = "3.12.0"
-description = "A platform independent file lock."
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.extras]
-docs = ["furo (>=2023.3.27)", "sphinx (>=6.1.3)", "sphinx-autodoc-typehints (>=1.23,!=1.23.4)"]
-testing = ["covdefaults (>=2.3)", "coverage (>=7.2.3)", "diff-cover (>=7.5)", "pytest (>=7.3.1)", "pytest-cov (>=4)", "pytest-mock (>=3.10)", "pytest-timeout (>=2.1)"]
-
-[[package]]
-name = "fsspec"
-version = "2023.5.0"
-description = "File-system specification"
-category = "main"
-optional = false
-python-versions = ">=3.8"
-
-[package.extras]
-abfs = ["adlfs"]
-adl = ["adlfs"]
-arrow = ["pyarrow (>=1)"]
-dask = ["dask", "distributed"]
-devel = ["pytest", "pytest-cov"]
-dropbox = ["dropbox", "dropboxdrivefs", "requests"]
-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"]
-fuse = ["fusepy"]
-gcs = ["gcsfs"]
-git = ["pygit2"]
-github = ["requests"]
-gs = ["gcsfs"]
-gui = ["panel"]
-hdfs = ["pyarrow (>=1)"]
-http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "requests"]
-libarchive = ["libarchive-c"]
-oci = ["ocifs"]
-s3 = ["s3fs"]
-sftp = ["paramiko"]
-smb = ["smbprotocol"]
-ssh = ["paramiko"]
-tqdm = ["tqdm"]
-
-[[package]]
-name = "googleapis-common-protos"
-version = "1.59.0"
-description = "Common protobufs used in Google APIs"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<5.0.0dev"
-
-[package.extras]
-grpc = ["grpcio (>=1.44.0,<2.0.0dev)"]
-
-[[package]]
-name = "grpc-interceptor"
-version = "0.15.2"
-description = "Simplifies gRPC interceptors"
-category = "main"
-optional = false
-python-versions = ">=3.7,<4.0"
-
-[package.dependencies]
-grpcio = ">=1.49.1,<2.0.0"
-
-[package.extras]
-testing = ["protobuf (>=4.21.9)"]
-
-[[package]]
-name = "grpcio"
-version = "1.55.0"
-description = "HTTP/2-based RPC framework"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.extras]
-protobuf = ["grpcio-tools (>=1.55.0)"]
-
-[[package]]
-name = "grpcio-reflection"
-version = "1.55.0"
-description = "Standard Protobuf Reflection Service for gRPC"
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[package.dependencies]
-grpcio = ">=1.55.0"
-protobuf = ">=4.21.6"
-
-[[package]]
-name = "grpcio-status"
-version = "1.55.0"
-description = "Status proto mapping for gRPC"
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[package.dependencies]
-googleapis-common-protos = ">=1.5.5"
-grpcio = ">=1.55.0"
-protobuf = ">=4.21.6"
-
-[[package]]
-name = "grpcio-tools"
-version = "1.55.0"
-description = "Protobuf code generator for gRPC"
-category = "dev"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-grpcio = ">=1.55.0"
-protobuf = ">=4.21.6,<5.0dev"
-setuptools = "*"
-
-[[package]]
-name = "hf-transfer"
-version = "0.1.3"
-description = ""
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[[package]]
-name = "huggingface-hub"
-version = "0.14.0"
-description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
-category = "main"
-optional = false
-python-versions = ">=3.7.0"
-
-[package.dependencies]
-filelock = "*"
-fsspec = "*"
-packaging = ">=20.9"
-pyyaml = ">=5.1"
-requests = "*"
-tqdm = ">=4.42.1"
-typing-extensions = ">=3.7.4.3"
-
-[package.extras]
-all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
-cli = ["InquirerPy (==0.3.4)"]
-dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
-fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
-quality = ["black (>=23.1,<24.0)", "mypy (==0.982)", "ruff (>=0.0.241)"]
-tensorflow = ["graphviz", "pydot", "tensorflow"]
-testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "gradio", "jedi", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "soundfile"]
-torch = ["torch"]
-typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
-
-[[package]]
-name = "idna"
-version = "3.4"
-description = "Internationalized Domain Names in Applications (IDNA)"
-category = "main"
-optional = false
-python-versions = ">=3.5"
-
-[[package]]
-name = "iniconfig"
-version = "2.0.0"
-description = "brain-dead simple config-ini parsing"
-category = "dev"
-optional = false
-python-versions = ">=3.7"
-
-[[package]]
-name = "Jinja2"
-version = "3.1.2"
-description = "A very fast and expressive template engine."
-category = "main"
-optional = true
-python-versions = ">=3.7"
-
-[package.dependencies]
-MarkupSafe = ">=2.0"
-
-[package.extras]
-i18n = ["Babel (>=2.7)"]
-
-[[package]]
-name = "loguru"
-version = "0.6.0"
-description = "Python logging made (stupidly) simple"
-category = "main"
-optional = false
-python-versions = ">=3.5"
-
-[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 (>=4.1.1)", "black (>=19.10b0)", "colorama (>=0.3.4)", "docutils (==0.16)", "flake8 (>=3.7.7)", "isort (>=5.1.1)", "pytest (>=4.6.2)", "pytest-cov (>=2.7.1)", "sphinx-autobuild (>=0.7.1)", "sphinx-rtd-theme (>=0.4.3)", "tox (>=3.9.0)"]
-
-[[package]]
-name = "MarkupSafe"
-version = "2.1.2"
-description = "Safely add untrusted strings to HTML/XML markup."
-category = "main"
-optional = true
-python-versions = ">=3.7"
-
-[[package]]
-name = "mpmath"
-version = "1.3.0"
-description = "Python library for arbitrary-precision floating-point arithmetic"
-category = "main"
-optional = true
-python-versions = "*"
-
-[package.extras]
-develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
-docs = ["sphinx"]
-gmpy = ["gmpy2 (>=2.1.0a4)"]
-tests = ["pytest (>=4.6)"]
-
-[[package]]
-name = "networkx"
-version = "3.1"
-description = "Python package for creating and manipulating graphs and networks"
-category = "main"
-optional = true
-python-versions = ">=3.8"
-
-[package.extras]
-default = ["matplotlib (>=3.4)", "numpy (>=1.20)", "pandas (>=1.3)", "scipy (>=1.8)"]
-developer = ["mypy (>=1.1)", "pre-commit (>=3.2)"]
-doc = ["nb2plots (>=0.6)", "numpydoc (>=1.5)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.13)", "sphinx (>=6.1)", "sphinx-gallery (>=0.12)", "texext (>=0.6.7)"]
-extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.10)", "sympy (>=1.10)"]
-test = ["codecov (>=2.1)", "pytest (>=7.2)", "pytest-cov (>=4.0)"]
-
-[[package]]
-name = "numpy"
-version = "1.24.3"
-description = "Fundamental package for array computing in Python"
-category = "main"
-optional = true
-python-versions = ">=3.8"
-
-[[package]]
-name = "opentelemetry-api"
-version = "1.15.0"
-description = "OpenTelemetry Python API"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-deprecated = ">=1.2.6"
-setuptools = ">=16.0"
-
-[[package]]
-name = "opentelemetry-exporter-otlp"
-version = "1.15.0"
-description = "OpenTelemetry Collector Exporters"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-opentelemetry-exporter-otlp-proto-grpc = "1.15.0"
-opentelemetry-exporter-otlp-proto-http = "1.15.0"
-
-[[package]]
-name = "opentelemetry-exporter-otlp-proto-grpc"
-version = "1.15.0"
-description = "OpenTelemetry Collector Protobuf over gRPC Exporter"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-backoff = {version = ">=1.10.0,<3.0.0", markers = "python_version >= \"3.7\""}
-googleapis-common-protos = ">=1.52,<2.0"
-grpcio = ">=1.0.0,<2.0.0"
-opentelemetry-api = ">=1.12,<2.0"
-opentelemetry-proto = "1.15.0"
-opentelemetry-sdk = ">=1.12,<2.0"
-
-[package.extras]
-test = ["pytest-grpc"]
-
-[[package]]
-name = "opentelemetry-exporter-otlp-proto-http"
-version = "1.15.0"
-description = "OpenTelemetry Collector Protobuf over HTTP Exporter"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-backoff = {version = ">=1.10.0,<3.0.0", markers = "python_version >= \"3.7\""}
-googleapis-common-protos = ">=1.52,<2.0"
-opentelemetry-api = ">=1.12,<2.0"
-opentelemetry-proto = "1.15.0"
-opentelemetry-sdk = ">=1.12,<2.0"
-requests = ">=2.7,<3.0"
-
-[package.extras]
-test = ["responses (==0.22.0)"]
-
-[[package]]
-name = "opentelemetry-instrumentation"
-version = "0.36b0"
-description = "Instrumentation Tools & Auto Instrumentation for OpenTelemetry Python"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-opentelemetry-api = ">=1.4,<2.0"
-setuptools = ">=16.0"
-wrapt = ">=1.0.0,<2.0.0"
-
-[[package]]
-name = "opentelemetry-instrumentation-grpc"
-version = "0.36b0"
-description = "OpenTelemetry gRPC instrumentation"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-opentelemetry-api = ">=1.12,<2.0"
-opentelemetry-instrumentation = "0.36b0"
-opentelemetry-sdk = ">=1.12,<2.0"
-opentelemetry-semantic-conventions = "0.36b0"
-wrapt = ">=1.0.0,<2.0.0"
-
-[package.extras]
-instruments = ["grpcio (>=1.27,<2.0)"]
-test = ["opentelemetry-instrumentation-grpc[instruments]", "opentelemetry-sdk (>=1.12,<2.0)", "opentelemetry-test-utils (==0.36b0)", "protobuf (>=3.13,<4.0)"]
-
-[[package]]
-name = "opentelemetry-proto"
-version = "1.15.0"
-description = "OpenTelemetry Python Proto"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-protobuf = ">=3.19,<5.0"
-
-[[package]]
-name = "opentelemetry-sdk"
-version = "1.15.0"
-description = "OpenTelemetry Python SDK"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-opentelemetry-api = "1.15.0"
-opentelemetry-semantic-conventions = "0.36b0"
-setuptools = ">=16.0"
-typing-extensions = ">=3.7.4"
-
-[[package]]
-name = "opentelemetry-semantic-conventions"
-version = "0.36b0"
-description = "OpenTelemetry Semantic Conventions"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[[package]]
-name = "packaging"
-version = "23.1"
-description = "Core utilities for Python packages"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[[package]]
-name = "pluggy"
-version = "1.0.0"
-description = "plugin and hook calling mechanisms for python"
-category = "dev"
-optional = false
-python-versions = ">=3.6"
-
-[package.extras]
-dev = ["pre-commit", "tox"]
-testing = ["pytest", "pytest-benchmark"]
-
-[[package]]
-name = "protobuf"
-version = "4.23.1"
-description = ""
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[[package]]
-name = "psutil"
-version = "5.9.5"
-description = "Cross-platform lib for process and system monitoring in Python."
-category = "main"
-optional = true
-python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
-
-[package.extras]
-test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
-
-[[package]]
-name = "pytest"
-version = "7.3.1"
-description = "pytest: simple powerful testing with Python"
-category = "dev"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-colorama = {version = "*", markers = "sys_platform == \"win32\""}
-exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
-iniconfig = "*"
-packaging = "*"
-pluggy = ">=0.12,<2.0"
-tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
-
-[package.extras]
-testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "xmlschema"]
-
-[[package]]
-name = "PyYAML"
-version = "6.0"
-description = "YAML parser and emitter for Python"
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[[package]]
-name = "requests"
-version = "2.31.0"
-description = "Python HTTP for Humans."
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-certifi = ">=2017.4.17"
-charset-normalizer = ">=2,<4"
-idna = ">=2.5,<4"
-urllib3 = ">=1.21.1,<3"
-
-[package.extras]
-socks = ["PySocks (>=1.5.6,!=1.5.7)"]
-use_chardet_on_py3 = ["chardet (>=3.0.2,<6)"]
-
-[[package]]
-name = "safetensors"
-version = "0.3.1"
-description = "Fast and Safe Tensor serialization"
-category = "main"
-optional = false
-python-versions = "*"
-
-[package.extras]
-all = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (>=2.11.0)", "torch (>=1.10)"]
-dev = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (>=2.11.0)", "torch (>=1.10)"]
-jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)"]
-numpy = ["numpy (>=1.21.6)"]
-paddlepaddle = ["paddlepaddle (>=2.4.1)"]
-quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"]
-tensorflow = ["tensorflow (>=2.11.0)"]
-testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "numpy (>=1.21.6)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)"]
-torch = ["torch (>=1.10)"]
-
-[[package]]
-name = "sentencepiece"
-version = "0.1.99"
-description = "SentencePiece python wrapper"
-category = "main"
-optional = false
-python-versions = "*"
-
-[[package]]
-name = "setuptools"
-version = "67.8.0"
-description = "Easily download, build, install, upgrade, and uninstall Python packages"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.extras]
-docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-hoverxref (<2)", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (==0.8.3)", "sphinx-reredirects", "sphinxcontrib-towncrier"]
-testing = ["build[virtualenv]", "filelock (>=3.4.0)", "flake8-2020", "ini2toml[lite] (>=0.9)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pip (>=19.1)", "pip-run (>=8.8)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-ruff", "pytest-timeout", "pytest-xdist", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
-testing-integration = ["build[virtualenv]", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"]
-
-[[package]]
-name = "sympy"
-version = "1.12"
-description = "Computer algebra system (CAS) in Python"
-category = "main"
-optional = true
-python-versions = ">=3.8"
-
-[package.dependencies]
-mpmath = ">=0.19"
-
-[[package]]
-name = "tokenizers"
-version = "0.13.3"
-description = "Fast and Customizable Tokenizers"
-category = "main"
-optional = false
-python-versions = "*"
-
-[package.extras]
-dev = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
-docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"]
-testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
-
-[[package]]
-name = "tomli"
-version = "2.0.1"
-description = "A lil' TOML parser"
-category = "dev"
-optional = false
-python-versions = ">=3.7"
-
-[[package]]
-name = "torch"
-version = "2.0.1"
-description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
-category = "main"
-optional = true
-python-versions = ">=3.8.0"
-
-[package.dependencies]
-filelock = "*"
-jinja2 = "*"
-networkx = "*"
-sympy = "*"
-typing-extensions = "*"
-
-[package.extras]
-opt-einsum = ["opt-einsum (>=3.3)"]
-
-[[package]]
-name = "tqdm"
-version = "4.65.0"
-description = "Fast, Extensible Progress Meter"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.dependencies]
-colorama = {version = "*", markers = "platform_system == \"Windows\""}
-
-[package.extras]
-dev = ["py-make (>=0.1.0)", "twine", "wheel"]
-notebook = ["ipywidgets (>=6)"]
-slack = ["slack-sdk"]
-telegram = ["requests"]
-
-[[package]]
-name = "typer"
-version = "0.6.1"
-description = "Typer, build great CLIs. Easy to code. Based on Python type hints."
-category = "main"
-optional = false
-python-versions = ">=3.6"
-
-[package.dependencies]
-click = ">=7.1.1,<9.0.0"
-
-[package.extras]
-all = ["colorama (>=0.4.3,<0.5.0)", "rich (>=10.11.0,<13.0.0)", "shellingham (>=1.3.0,<2.0.0)"]
-dev = ["autoflake (>=1.3.1,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)", "pre-commit (>=2.17.0,<3.0.0)"]
-doc = ["mdx-include (>=1.4.1,<2.0.0)", "mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)"]
-test = ["black (>=22.3.0,<23.0.0)", "coverage (>=5.2,<6.0)", "isort (>=5.0.6,<6.0.0)", "mypy (==0.910)", "pytest (>=4.4.0,<5.4.0)", "pytest-cov (>=2.10.0,<3.0.0)", "pytest-sugar (>=0.9.4,<0.10.0)", "pytest-xdist (>=1.32.0,<2.0.0)", "rich (>=10.11.0,<13.0.0)", "shellingham (>=1.3.0,<2.0.0)"]
-
-[[package]]
-name = "typing-extensions"
-version = "4.6.0"
-description = "Backported and Experimental Type Hints for Python 3.7+"
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[[package]]
-name = "urllib3"
-version = "2.0.2"
-description = "HTTP library with thread-safe connection pooling, file post, and more."
-category = "main"
-optional = false
-python-versions = ">=3.7"
-
-[package.extras]
-brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
-secure = ["certifi", "cryptography (>=1.9)", "idna (>=2.0.0)", "pyopenssl (>=17.1.0)", "urllib3-secure-extra"]
-socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
-zstd = ["zstandard (>=0.18.0)"]
-
-[[package]]
-name = "win32-setctime"
-version = "1.1.0"
-description = "A small Python utility to set file creation time on Windows"
-category = "main"
-optional = false
-python-versions = ">=3.5"
-
-[package.extras]
-dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"]
-
-[[package]]
-name = "wrapt"
-version = "1.15.0"
-description = "Module for decorators, wrappers and monkey patching."
-category = "main"
-optional = false
-python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
-
-[extras]
-accelerate = ["accelerate"]
-bnb = ["bitsandbytes"]
-
-[metadata]
-lock-version = "1.1"
-python-versions = "^3.9"
-content-hash = "152c8b82717e2b802aee3427152ef3e37417fb95b73c3af2f448a381f51a6a8d"
-
-[metadata.files]
-accelerate = [
-    {file = "accelerate-0.19.0-py3-none-any.whl", hash = "sha256:2866b0bf9fff08f51e6384c95fa96725838b70f1988d1cce42e56b820d8a91dd"},
-    {file = "accelerate-0.19.0.tar.gz", hash = "sha256:84920226b9e642e453ef37593ee55b956b08d8200dea4087c546c34e26157e76"},
-]
-backoff = [
-    {file = "backoff-2.2.1-py3-none-any.whl", hash = "sha256:63579f9a0628e06278f7e47b7d7d5b6ce20dc65c5e96a6f3ca99a6adca0396e8"},
-    {file = "backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba"},
-]
-bitsandbytes = [
-    {file = "bitsandbytes-0.38.1-py3-none-any.whl", hash = "sha256:5f532e7b1353eb7049ae831da2eb62ed8a1e0444116bd51b9e088a6e0bc7a34a"},
-    {file = "bitsandbytes-0.38.1.tar.gz", hash = "sha256:ba95a806b5065ea3263558e188f07eacb32ad691842932fb0d36a879883167ce"},
-]
-certifi = [
-    {file = "certifi-2023.5.7-py3-none-any.whl", hash = "sha256:c6c2e98f5c7869efca1f8916fed228dd91539f9f1b444c314c06eef02980c716"},
-    {file = "certifi-2023.5.7.tar.gz", hash = "sha256:0f0d56dc5a6ad56fd4ba36484d6cc34451e1c6548c61daad8c320169f91eddc7"},
-]
-charset-normalizer = [
+files = [
     {file = "charset-normalizer-3.1.0.tar.gz", hash = "sha256:34e0a2f9c370eb95597aae63bf85eb5e96826d81e3dcf88b8886012906f509b5"},
     {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:e0ac8959c929593fee38da1c2b64ee9778733cdf03c482c9ff1d508b6b593b2b"},
     {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d7fc3fca01da18fbabe4625d64bb612b533533ed10045a2ac3dd194bfa656b60"},
@@ -825,141 +144,301 @@ charset-normalizer = [
     {file = "charset_normalizer-3.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:830d2948a5ec37c386d3170c483063798d7879037492540f10a475e3fd6f244b"},
     {file = "charset_normalizer-3.1.0-py3-none-any.whl", hash = "sha256:3d9098b479e78c85080c98e1e35ff40b4a31d8953102bb0fd7d1b6f8a2111a3d"},
 ]
-click = [
+
+[[package]]
+name = "click"
+version = "8.1.3"
+description = "Composable command line interface toolkit"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "click-8.1.3-py3-none-any.whl", hash = "sha256:bb4d8133cb15a609f44e8213d9b391b0809795062913b383c62be0ee95b1db48"},
     {file = "click-8.1.3.tar.gz", hash = "sha256:7682dc8afb30297001674575ea00d1814d808d6a36af415a82bd481d37ba7b8e"},
 ]
-colorama = [
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+description = "Cross-platform colored terminal text."
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+files = [
     {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
-Deprecated = [
-    {file = "Deprecated-1.2.13-py2.py3-none-any.whl", hash = "sha256:64756e3e14c8c5eea9795d93c524551432a0be75629f8f29e67ab8caf076c76d"},
-    {file = "Deprecated-1.2.13.tar.gz", hash = "sha256:43ac5335da90c31c24ba028af536a91d41d53f9e6901ddb021bcc572ce44e38d"},
+
+[[package]]
+name = "deprecated"
+version = "1.2.14"
+description = "Python @deprecated decorator to deprecate old python classes, functions or methods."
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+files = [
+    {file = "Deprecated-1.2.14-py2.py3-none-any.whl", hash = "sha256:6fac8b097794a90302bdbb17b9b815e732d3c4720583ff1b198499d78470466c"},
+    {file = "Deprecated-1.2.14.tar.gz", hash = "sha256:e5323eb936458dccc2582dc6f9c322c852a775a27065ff2b0c4970b9d53d01b3"},
 ]
-exceptiongroup = [
+
+[package.dependencies]
+wrapt = ">=1.10,<2"
+
+[package.extras]
+dev = ["PyTest", "PyTest-Cov", "bump2version (<1)", "sphinx (<2)", "tox"]
+
+[[package]]
+name = "exceptiongroup"
+version = "1.1.1"
+description = "Backport of PEP 654 (exception groups)"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "exceptiongroup-1.1.1-py3-none-any.whl", hash = "sha256:232c37c63e4f682982c8b6459f33a8981039e5fb8756b2074364e5055c498c9e"},
     {file = "exceptiongroup-1.1.1.tar.gz", hash = "sha256:d484c3090ba2889ae2928419117447a14daf3c1231d5e30d0aae34f354f01785"},
 ]
-filelock = [
-    {file = "filelock-3.12.0-py3-none-any.whl", hash = "sha256:ad98852315c2ab702aeb628412cbf7e95b7ce8c3bf9565670b4eaecf1db370a9"},
-    {file = "filelock-3.12.0.tar.gz", hash = "sha256:fc03ae43288c013d2ea83c8597001b1129db351aad9c57fe2409327916b8e718"},
+
+[package.extras]
+test = ["pytest (>=6)"]
+
+[[package]]
+name = "filelock"
+version = "3.12.2"
+description = "A platform independent file lock."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "filelock-3.12.2-py3-none-any.whl", hash = "sha256:cbb791cdea2a72f23da6ac5b5269ab0a0d161e9ef0100e653b69049a7706d1ec"},
+    {file = "filelock-3.12.2.tar.gz", hash = "sha256:002740518d8aa59a26b0c76e10fb8c6e15eae825d34b6fdf670333fd7b938d81"},
 ]
-fsspec = [
-    {file = "fsspec-2023.5.0-py3-none-any.whl", hash = "sha256:51a4ad01a5bb66fcc58036e288c0d53d3975a0df2a5dc59a93b59bade0391f2a"},
-    {file = "fsspec-2023.5.0.tar.gz", hash = "sha256:b3b56e00fb93ea321bc9e5d9cf6f8522a0198b20eb24e02774d329e9c6fb84ce"},
+
+[package.extras]
+docs = ["furo (>=2023.5.20)", "sphinx (>=7.0.1)", "sphinx-autodoc-typehints (>=1.23,!=1.23.4)"]
+testing = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "diff-cover (>=7.5)", "pytest (>=7.3.1)", "pytest-cov (>=4.1)", "pytest-mock (>=3.10)", "pytest-timeout (>=2.1)"]
+
+[[package]]
+name = "fsspec"
+version = "2023.6.0"
+description = "File-system specification"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "fsspec-2023.6.0-py3-none-any.whl", hash = "sha256:1cbad1faef3e391fba6dc005ae9b5bdcbf43005c9167ce78c915549c352c869a"},
+    {file = "fsspec-2023.6.0.tar.gz", hash = "sha256:d0b2f935446169753e7a5c5c55681c54ea91996cc67be93c39a154fb3a2742af"},
 ]
-googleapis-common-protos = [
-    {file = "googleapis-common-protos-1.59.0.tar.gz", hash = "sha256:4168fcb568a826a52f23510412da405abd93f4d23ba544bb68d943b14ba3cb44"},
-    {file = "googleapis_common_protos-1.59.0-py2.py3-none-any.whl", hash = "sha256:b287dc48449d1d41af0c69f4ea26242b5ae4c3d7249a38b0984c86a4caffff1f"},
+
+[package.extras]
+abfs = ["adlfs"]
+adl = ["adlfs"]
+arrow = ["pyarrow (>=1)"]
+dask = ["dask", "distributed"]
+devel = ["pytest", "pytest-cov"]
+dropbox = ["dropbox", "dropboxdrivefs", "requests"]
+full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"]
+fuse = ["fusepy"]
+gcs = ["gcsfs"]
+git = ["pygit2"]
+github = ["requests"]
+gs = ["gcsfs"]
+gui = ["panel"]
+hdfs = ["pyarrow (>=1)"]
+http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "requests"]
+libarchive = ["libarchive-c"]
+oci = ["ocifs"]
+s3 = ["s3fs"]
+sftp = ["paramiko"]
+smb = ["smbprotocol"]
+ssh = ["paramiko"]
+tqdm = ["tqdm"]
+
+[[package]]
+name = "googleapis-common-protos"
+version = "1.59.1"
+description = "Common protobufs used in Google APIs"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "googleapis-common-protos-1.59.1.tar.gz", hash = "sha256:b35d530fe825fb4227857bc47ad84c33c809ac96f312e13182bdeaa2abe1178a"},
+    {file = "googleapis_common_protos-1.59.1-py2.py3-none-any.whl", hash = "sha256:0cbedb6fb68f1c07e18eb4c48256320777707e7d0c55063ae56c15db3224a61e"},
 ]
-grpc-interceptor = [
+
+[package.dependencies]
+protobuf = ">=3.19.5,<3.20.0 || >3.20.0,<3.20.1 || >3.20.1,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4.21.4 || >4.21.4,<4.21.5 || >4.21.5,<5.0.0.dev0"
+
+[package.extras]
+grpc = ["grpcio (>=1.44.0,<2.0.0.dev0)"]
+
+[[package]]
+name = "grpc-interceptor"
+version = "0.15.2"
+description = "Simplifies gRPC interceptors"
+optional = false
+python-versions = ">=3.7,<4.0"
+files = [
     {file = "grpc-interceptor-0.15.2.tar.gz", hash = "sha256:5c984110af4fb77d03472ec0468f9c77ddaf798e190410fb7b7f1e76c60c96a4"},
     {file = "grpc_interceptor-0.15.2-py3-none-any.whl", hash = "sha256:596dac3cb709ffb6178a4873f5148e254c871c9069f0b11040189b257969490a"},
 ]
-grpcio = [
-    {file = "grpcio-1.55.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:7b38e028a7bbc97a9ae5e418712452f298618b9d0493390770bf2de785251ae7"},
-    {file = "grpcio-1.55.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:054b7164b25712ec71339e139875a66708a2ab09be36ac75e73b2d337ab2dc1b"},
-    {file = "grpcio-1.55.0-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:1982c99c7091d1b7e3e78b1173097f705feef233e253a27e99746b11815ac897"},
-    {file = "grpcio-1.55.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8bd4f4932ef63ed32a725065aebb8585e4118a523d923db896e85c09429a36e6"},
-    {file = "grpcio-1.55.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70de2b73cf22241173cb21d308786ba4ea443e4c88441a2ce445829aa638dda8"},
-    {file = "grpcio-1.55.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:2d25d7fcb528a40578b3d0428d401745fd5c0eeeda81f35ce2f40a10d79afd19"},
-    {file = "grpcio-1.55.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:1173a05117798aca4834d3edd504e6adc25ae9967df0f44b91a612884fb2707a"},
-    {file = "grpcio-1.55.0-cp310-cp310-win32.whl", hash = "sha256:7c00263d792a244bef67a8d3b357ccbcdae6341c5961dbee494d8f967f9aee69"},
-    {file = "grpcio-1.55.0-cp310-cp310-win_amd64.whl", hash = "sha256:ab784204d9923368e0e5877d7795584b9606a51b128ee199ad8b5888d0c66592"},
-    {file = "grpcio-1.55.0-cp311-cp311-linux_armv7l.whl", hash = "sha256:c97cfae0b7a17dc1a0a3e4333f4f46daa114d85f950a67f39cc141b5425182e4"},
-    {file = "grpcio-1.55.0-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:8a910fa9b95a286f4bc1879dcf8d5ccb95b5e33bb63323fc4414d157f23afef1"},
-    {file = "grpcio-1.55.0-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:3ab9bf80c19c91847f45ff32af94c85d282545a62db39d797838244d57831d78"},
-    {file = "grpcio-1.55.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4370d2cca37301bcc69453d3dd3c1576d06d6b3e337bfec55b3aab2fe106b25c"},
-    {file = "grpcio-1.55.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dad999423b33ad5409e986587593b6062a8260b74ae8fc8162ce231c6b7a929e"},
-    {file = "grpcio-1.55.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:d396ec4d520b58f43142958cff071e5ad1c50ac87d29d086a9c6a990a09ea536"},
-    {file = "grpcio-1.55.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:b2a3b837d5837b9069783026b57aa0ff12e34d3218fdeda3f9c06d3950266d8e"},
-    {file = "grpcio-1.55.0-cp311-cp311-win32.whl", hash = "sha256:ee0de9cb6813704969e53743e0969fd95225ff24bd686c89ed12a18147f6566c"},
-    {file = "grpcio-1.55.0-cp311-cp311-win_amd64.whl", hash = "sha256:9a11b1dd4b1572e85fba5911309c15980a1ff77c555fad0ecdbe3711ef741908"},
-    {file = "grpcio-1.55.0-cp37-cp37m-linux_armv7l.whl", hash = "sha256:d0209fb3cb55c5288a1dec72dcaae2c1b501edceca10d22c0f0baa5e60e2b22c"},
-    {file = "grpcio-1.55.0-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:322d4ebc37cbc8d8596b1da6055e3e81e8cfd36816ab4b285c1163c3042e6067"},
-    {file = "grpcio-1.55.0-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:60efab181c32e029e0960f238508396dd001ba2064168f8148e6356db093967c"},
-    {file = "grpcio-1.55.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:48f6088d898e1e987d761d58dc4cd724e7457a7a86d11561fa95c3b826d025dc"},
-    {file = "grpcio-1.55.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:29ab0e879b1585be41cfbb02faed67913700ced8015da4763f1f0bdd7dfb4ab7"},
-    {file = "grpcio-1.55.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:157f5615c7b5d0968727472f6394dee01555ef4246d2f2cfb6555be857936d74"},
-    {file = "grpcio-1.55.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:67c4fda71f92225c5e74fa15bffa6be022c07111f674fe1f234c1ef4c1bb7927"},
-    {file = "grpcio-1.55.0-cp37-cp37m-win_amd64.whl", hash = "sha256:a202dcf0c512292fd7a2154e4044c70400212eaa726685ebf8af105e25693c5a"},
-    {file = "grpcio-1.55.0-cp38-cp38-linux_armv7l.whl", hash = "sha256:ce82d06cdfb8a9292fb857f00bee11a2430e4ac2742e07b46c1a3072d683256a"},
-    {file = "grpcio-1.55.0-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:51b7a27a129f743d68394f94029f88ef3da090fc13776b9dfa3c79c5f4b30525"},
-    {file = "grpcio-1.55.0-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:7c32f87bec58a8a0d4f4d5387bd61a383bd32b2caffb2de3cd579e47490b7e19"},
-    {file = "grpcio-1.55.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:89107071b5f14af6bbb855183d338a0fa94136bbeb3989c9773c6184e51a95e9"},
-    {file = "grpcio-1.55.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1041cad23f00943d8889ad15427d87bbdacbbe2df5cec951c314f2f3967d4691"},
-    {file = "grpcio-1.55.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:56631cc0bdf86d15ea1599b9697ace65e6b52c6b136d3666bf7769d3d6d087a8"},
-    {file = "grpcio-1.55.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:10af4774da9c0665a1bf519333694ac40d72d83cb514534b99db0a5e3d5c3593"},
-    {file = "grpcio-1.55.0-cp38-cp38-win32.whl", hash = "sha256:7b8665da31b5bd701b338a581de7b9631d50b4b7ee67125c2d1dc2228cc119d8"},
-    {file = "grpcio-1.55.0-cp38-cp38-win_amd64.whl", hash = "sha256:74780f570c76feb8e62a8c019b495fea435b60218682fce513ff2c71262c346c"},
-    {file = "grpcio-1.55.0-cp39-cp39-linux_armv7l.whl", hash = "sha256:6b8dbb151b116825c10f01e5b7b75e14edd0e60736a65311d0d98a4cd0489303"},
-    {file = "grpcio-1.55.0-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:a82283d6e0403d3e2e7eebb99cb0d2783e20b6791c8c94bd8d4a4233b58b1ea0"},
-    {file = "grpcio-1.55.0-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:ba32a8e9bc3eecc6bab6824b905f04c3fdc31659c3e6e06841b774e7cb4410af"},
-    {file = "grpcio-1.55.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b1e2b705d524e780998218cf429d30b6ffc54cb6e54812c9597bc5df12dbcb5b"},
-    {file = "grpcio-1.55.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fe78365c64b2c7470d31c4941e10c6654042bcbb53897b9b1e2c96d6d0da9ef9"},
-    {file = "grpcio-1.55.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:8b440ccc434c1ad5874465bfae40c0a27f562ae5f7c5b468b6689bc55e8bf1c1"},
-    {file = "grpcio-1.55.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:0d3d5c644d523dee82ffcc44ad50cd66e3bf66e7fa60ad3cdb1eb868228e4ab0"},
-    {file = "grpcio-1.55.0-cp39-cp39-win32.whl", hash = "sha256:c33dbeecc14f1a413e8af8ae1208cb383b063fa2ff2e1f309b4d3d7739b0927e"},
-    {file = "grpcio-1.55.0-cp39-cp39-win_amd64.whl", hash = "sha256:2663741acc117370fd53336267cfb24c965e9d3ea1e4933a3e4411712d3091fb"},
-    {file = "grpcio-1.55.0.tar.gz", hash = "sha256:dd15027a171ff93c97f9c704fa120bc5d0691dc7e71ae450e2ecade1a2799b53"},
+
+[package.dependencies]
+grpcio = ">=1.49.1,<2.0.0"
+
+[package.extras]
+testing = ["protobuf (>=4.21.9)"]
+
+[[package]]
+name = "grpcio"
+version = "1.54.2"
+description = "HTTP/2-based RPC framework"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "grpcio-1.54.2-cp310-cp310-linux_armv7l.whl", hash = "sha256:40e1cbf69d6741b40f750f3cccc64326f927ac6145a9914d33879e586002350c"},
+    {file = "grpcio-1.54.2-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:2288d76e4d4aa7ef3fe7a73c1c470b66ea68e7969930e746a8cd8eca6ef2a2ea"},
+    {file = "grpcio-1.54.2-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:c0e3155fc5335ec7b3b70f15230234e529ca3607b20a562b6c75fb1b1218874c"},
+    {file = "grpcio-1.54.2-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9bf88004fe086c786dc56ef8dd6cb49c026833fdd6f42cb853008bce3f907148"},
+    {file = "grpcio-1.54.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2be88c081e33f20630ac3343d8ad9f1125f32987968e9c8c75c051c9800896e8"},
+    {file = "grpcio-1.54.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:33d40954199bddbb6a78f8f6f2b2082660f381cd2583ec860a6c2fa7c8400c08"},
+    {file = "grpcio-1.54.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b52d00d1793d290c81ad6a27058f5224a7d5f527867e5b580742e1bd211afeee"},
+    {file = "grpcio-1.54.2-cp310-cp310-win32.whl", hash = "sha256:881d058c5ccbea7cc2c92085a11947b572498a27ef37d3eef4887f499054dca8"},
+    {file = "grpcio-1.54.2-cp310-cp310-win_amd64.whl", hash = "sha256:0212e2f7fdf7592e4b9d365087da30cb4d71e16a6f213120c89b4f8fb35a3ab3"},
+    {file = "grpcio-1.54.2-cp311-cp311-linux_armv7l.whl", hash = "sha256:1e623e0cf99a0ac114f091b3083a1848dbc64b0b99e181473b5a4a68d4f6f821"},
+    {file = "grpcio-1.54.2-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:66233ccd2a9371158d96e05d082043d47dadb18cbb294dc5accfdafc2e6b02a7"},
+    {file = "grpcio-1.54.2-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:4cb283f630624ebb16c834e5ac3d7880831b07cbe76cb08ab7a271eeaeb8943e"},
+    {file = "grpcio-1.54.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2a1e601ee31ef30a9e2c601d0867e236ac54c922d32ed9f727b70dd5d82600d5"},
+    {file = "grpcio-1.54.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8da84bbc61a4e92af54dc96344f328e5822d574f767e9b08e1602bb5ddc254a"},
+    {file = "grpcio-1.54.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:5008964885e8d23313c8e5ea0d44433be9bfd7e24482574e8cc43c02c02fc796"},
+    {file = "grpcio-1.54.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a2f5a1f1080ccdc7cbaf1171b2cf384d852496fe81ddedeb882d42b85727f610"},
+    {file = "grpcio-1.54.2-cp311-cp311-win32.whl", hash = "sha256:b74ae837368cfffeb3f6b498688a123e6b960951be4dec0e869de77e7fa0439e"},
+    {file = "grpcio-1.54.2-cp311-cp311-win_amd64.whl", hash = "sha256:8cdbcbd687e576d48f7886157c95052825ca9948c0ed2afdc0134305067be88b"},
+    {file = "grpcio-1.54.2-cp37-cp37m-linux_armv7l.whl", hash = "sha256:782f4f8662a2157c4190d0f99eaaebc602899e84fb1e562a944e5025929e351c"},
+    {file = "grpcio-1.54.2-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:714242ad0afa63a2e6dabd522ae22e1d76e07060b5af2ddda5474ba4f14c2c94"},
+    {file = "grpcio-1.54.2-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:f900ed4ad7a0f1f05d35f955e0943944d5a75f607a836958c6b8ab2a81730ef2"},
+    {file = "grpcio-1.54.2-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:96a41817d2c763b1d0b32675abeb9179aa2371c72aefdf74b2d2b99a1b92417b"},
+    {file = "grpcio-1.54.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70fcac7b94f4c904152809a050164650ac81c08e62c27aa9f156ac518029ebbe"},
+    {file = "grpcio-1.54.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:fd6c6c29717724acf9fc1847c4515d57e4dc12762452457b9cb37461f30a81bb"},
+    {file = "grpcio-1.54.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:c2392f5b5d84b71d853918687d806c1aa4308109e5ca158a16e16a6be71041eb"},
+    {file = "grpcio-1.54.2-cp37-cp37m-win_amd64.whl", hash = "sha256:51630c92591d6d3fe488a7c706bd30a61594d144bac7dee20c8e1ce78294f474"},
+    {file = "grpcio-1.54.2-cp38-cp38-linux_armv7l.whl", hash = "sha256:b04202453941a63b36876a7172b45366dc0cde10d5fd7855c0f4a4e673c0357a"},
+    {file = "grpcio-1.54.2-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:89dde0ac72a858a44a2feb8e43dc68c0c66f7857a23f806e81e1b7cc7044c9cf"},
+    {file = "grpcio-1.54.2-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:09d4bfd84686cd36fd11fd45a0732c7628308d094b14d28ea74a81db0bce2ed3"},
+    {file = "grpcio-1.54.2-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7fc2b4edb938c8faa4b3c3ea90ca0dd89b7565a049e8e4e11b77e60e4ed2cc05"},
+    {file = "grpcio-1.54.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61f7203e2767800edee7a1e1040aaaf124a35ce0c7fe0883965c6b762defe598"},
+    {file = "grpcio-1.54.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:e416c8baf925b5a1aff31f7f5aecc0060b25d50cce3a5a7255dc5cf2f1d4e5eb"},
+    {file = "grpcio-1.54.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:dc80c9c6b608bf98066a038e0172013a49cfa9a08d53335aefefda2c64fc68f4"},
+    {file = "grpcio-1.54.2-cp38-cp38-win32.whl", hash = "sha256:8d6192c37a30a115f4663592861f50e130caed33efc4eec24d92ec881c92d771"},
+    {file = "grpcio-1.54.2-cp38-cp38-win_amd64.whl", hash = "sha256:46a057329938b08e5f0e12ea3d7aed3ecb20a0c34c4a324ef34e00cecdb88a12"},
+    {file = "grpcio-1.54.2-cp39-cp39-linux_armv7l.whl", hash = "sha256:2296356b5c9605b73ed6a52660b538787094dae13786ba53080595d52df13a98"},
+    {file = "grpcio-1.54.2-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:c72956972e4b508dd39fdc7646637a791a9665b478e768ffa5f4fe42123d5de1"},
+    {file = "grpcio-1.54.2-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:9bdbb7624d65dc0ed2ed8e954e79ab1724526f09b1efa88dcd9a1815bf28be5f"},
+    {file = "grpcio-1.54.2-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c44e1a765b31e175c391f22e8fc73b2a2ece0e5e6ff042743d8109b5d2eff9f"},
+    {file = "grpcio-1.54.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5cc928cfe6c360c1df636cf7991ab96f059666ac7b40b75a769410cc6217df9c"},
+    {file = "grpcio-1.54.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:a08920fa1a97d4b8ee5db2f31195de4a9def1a91bc003544eb3c9e6b8977960a"},
+    {file = "grpcio-1.54.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4864f99aac207e3e45c5e26c6cbb0ad82917869abc2f156283be86c05286485c"},
+    {file = "grpcio-1.54.2-cp39-cp39-win32.whl", hash = "sha256:b38b3de8cff5bc70f8f9c615f51b48eff7313fc9aca354f09f81b73036e7ddfa"},
+    {file = "grpcio-1.54.2-cp39-cp39-win_amd64.whl", hash = "sha256:be48496b0e00460717225e7680de57c38be1d8629dc09dadcd1b3389d70d942b"},
+    {file = "grpcio-1.54.2.tar.gz", hash = "sha256:50a9f075eeda5097aa9a182bb3877fe1272875e45370368ac0ee16ab9e22d019"},
 ]
-grpcio-reflection = [
-    {file = "grpcio-reflection-1.55.0.tar.gz", hash = "sha256:46fc5e68ce7ae9bff0c0577f9e42bbb038a5afb26290fdf04943285e9db3c193"},
-    {file = "grpcio_reflection-1.55.0-py3-none-any.whl", hash = "sha256:44e0dbfbfdcf1ac8646f1d32e4be72f0c633fd4b469e8e58b3a86e37b5a72756"},
+
+[package.extras]
+protobuf = ["grpcio-tools (>=1.54.2)"]
+
+[[package]]
+name = "grpcio-reflection"
+version = "1.54.2"
+description = "Standard Protobuf Reflection Service for gRPC"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "grpcio-reflection-1.54.2.tar.gz", hash = "sha256:b2e021e1ce4f075615411edfbbd6fdcc485ba474dd6e5a3f559690582959a673"},
+    {file = "grpcio_reflection-1.54.2-py3-none-any.whl", hash = "sha256:e7759addebbd90768f3a0278320278145758c4687d9e2cd7d76e7cbd0e329274"},
 ]
-grpcio-status = [
-    {file = "grpcio-status-1.55.0.tar.gz", hash = "sha256:beeca8d5d3783e155676beaade0dae9eaea12cd9701498905dca0d35bd6b36f8"},
-    {file = "grpcio_status-1.55.0-py3-none-any.whl", hash = "sha256:6da36bab11bb252b6854b86578f484c4fed9f8169816b490b6d3a32ec2a971fe"},
+
+[package.dependencies]
+grpcio = ">=1.54.2"
+protobuf = ">=4.21.6"
+
+[[package]]
+name = "grpcio-status"
+version = "1.54.2"
+description = "Status proto mapping for gRPC"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "grpcio-status-1.54.2.tar.gz", hash = "sha256:3255cbec5b7c706caa3d4dd584606c080e6415e15631bb2f6215e2b70055836d"},
+    {file = "grpcio_status-1.54.2-py3-none-any.whl", hash = "sha256:2a7cb4838225f1b53bd0448a3008c5b5837941e1f3a0b13fa38768f08a7b68c2"},
 ]
-grpcio-tools = [
-    {file = "grpcio-tools-1.55.0.tar.gz", hash = "sha256:d796f5d7cea260ef2afed12d13ec34b13e09dd74d7f292d7428c506fa8c17a74"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:52e34e9b6496f4c1e3289ada7bc41d759e4a8ec5f2679e187067cab8532ffbf4"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:b131b2bbf25198d9e508dfa588cb215580629b514e293d5609eeee98c8941dbc"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:9933a1f18f780c42214b126ef27e273b54c9c28de3fae5b1887b413ceb374c4c"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cfc82c11ce51de6ed5836fbafbc188d9eac0737abc116978f151c40271783817"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c7a18bd5f994b7911d3e70e0abb05bea9f1b084a1725d404a8e231bf9727613b"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:87152893c7c3bef58a6a9b548db290aa318cc314c700ae7d7f2970aa567f875e"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:bc23034b1959d6cda27347b2207fee0fb0fb0aff242da228a6b7c1a18fce4116"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-win32.whl", hash = "sha256:ab64f9d6f5e3636ae6298e2d795225daa83aacb057105943728ed50a8a582237"},
-    {file = "grpcio_tools-1.55.0-cp310-cp310-win_amd64.whl", hash = "sha256:b197de69ca0431b718ffa47b32a733703fa5503da49f49dd315c866842b6cfbd"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-linux_armv7l.whl", hash = "sha256:98ff3129ff7134a95f4d2857663625771f6838ac44b7799c34259b7ea87ebe5c"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:c3c7b7eb89f963b87922ecc0c0ab2485fff05997ada66dffd53597b507a83bc8"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:51a1ccab6f67edd1a3768a75ac495907fe0cd6d6617af2f9f2033400b5858a11"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4dea66623548b52429fb03495f2c76f4c993bf9a56267c6b3d0fb62573dd52c2"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e59fd4a58688117cb5128d7785909d45a6e5f8212efeb65b6fd74bb9b8b9512"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:734ede84d613b044f72e7d9c190bd2388ebb83e85bcd3aa75afa9f30c096dbc7"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f87d99aa3826aa20c3b89493984cf278f4c9d20b3418534a46239c804fee506c"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-win32.whl", hash = "sha256:4580df5a9867f7bcbb828a5485c030ca232c1578e615caf751333c7a7980d838"},
-    {file = "grpcio_tools-1.55.0-cp311-cp311-win_amd64.whl", hash = "sha256:b674de79571357c5381bc5fa12e3b89fefef74c164ab9077ed22158c3529aa8e"},
-    {file = "grpcio_tools-1.55.0-cp37-cp37m-linux_armv7l.whl", hash = "sha256:0dead7fb37bfe7c7eb8294143015645297f4affa683783b8bbf2cd4d7f7036d4"},
-    {file = "grpcio_tools-1.55.0-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:89f6ed47415a22568bbf4a62336bfde7cafb53492a5a9f33a22243411b00f443"},
-    {file = "grpcio_tools-1.55.0-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:946266cbd639847548c9f97e38da0682746c2eadea790ceb4320b1f85387bd6d"},
-    {file = "grpcio_tools-1.55.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:36745762689df18f83273a9a004848897793f63a10a30acd18acb2d170c663a9"},
-    {file = "grpcio_tools-1.55.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:053bbdfb74f76511db47e1e18a1962432468ae9f356cc00f15d1f1353eaf32a1"},
-    {file = "grpcio_tools-1.55.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:2eacb0b1e8e5cfd0b40e12e62bd5adebbbae8c73cdf6e04fad9ddd37e32d98a4"},
-    {file = "grpcio_tools-1.55.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:9395c4fdee6b22137e878ebd461444854a3cd9c6c260c43f4a4c4a4023700129"},
-    {file = "grpcio_tools-1.55.0-cp37-cp37m-win_amd64.whl", hash = "sha256:bcf5e1858137cbe13ef10a7931a7edc745c77f8b39f032f52072443f0dd681e1"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-linux_armv7l.whl", hash = "sha256:e76f35e5e65600a75c3547855e8c9ab935c55c473f5409e7746cca8f1f7c8f4a"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:a61567f27661ab9327dc060615dc22d2bde80c56731f1e856008f1fd8ee83311"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:2ba87592f2cd689e127cd4fce76ec23b19562e230fa41ea089af8b15120aea78"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:41005002cbfa0ad39972486bde8116b2a042804119e5b998086a4dc26e625d6a"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4a6db1494955d2a5531575b5fcdc08094ea4a331a94b9cdf864d78e801c5fa23"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:07c23ed940e046c9dd471bc870eb5db4d93e518f90011cf9aebf8bfda6cd68a5"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:f900bce944b5777effecb9078e5fd3a224e42b1ca33c7546c3d043f9ef9eb4e8"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-win32.whl", hash = "sha256:3724e48c3db499b2d212c5a89d7cc4b49ccd476dc26bf8a9b855d59b6cc00796"},
-    {file = "grpcio_tools-1.55.0-cp38-cp38-win_amd64.whl", hash = "sha256:416a8b61ed4223715755b4519858419e1f4653d64572a28029f2ac63e677e3d2"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-linux_armv7l.whl", hash = "sha256:73ef9e0e0ee8ab055a621e7b42e5fb32753b0b6607900887dba6d55df5947be8"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:4a41130c97775bb0dfaf87e34b492f2eca448d02d213410005544c534f3f7c26"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:87dbc98528f88faa3f8f56a47d41dc6fda382928abbdb5537b5444eb8bb1ac1b"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7f084cd619cf66d8620a99f8586018f19b918ffb2ddb92d3e5943a06038bead8"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:350303ef3a2b25ed1b90e42764923e40b664d9f10840f7a0f06117c4dc414aff"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:fbbe2bee4af93c03ba064d40199dbf38067d2aa6ae98dfa0687a08ee980ebfd5"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b00a67a1230968c1a0424915922d17983d824ed45e8db06f9f17be6d5571faee"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-win32.whl", hash = "sha256:632364ffbd4fb0338cb03c590a2ddc258d9cd59bff0bf4199c02e3e581f802d7"},
-    {file = "grpcio_tools-1.55.0-cp39-cp39-win_amd64.whl", hash = "sha256:95428be2db12412ff23f0969386fc51d2aa6de38a57cc54c57363352f1d7a832"},
+
+[package.dependencies]
+googleapis-common-protos = ">=1.5.5"
+grpcio = ">=1.54.2"
+protobuf = ">=4.21.6"
+
+[[package]]
+name = "grpcio-tools"
+version = "1.54.2"
+description = "Protobuf code generator for gRPC"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "grpcio-tools-1.54.2.tar.gz", hash = "sha256:e11c2c2aee53f340992e8e4d6a59172cbbbd0193f1351de98c4f810a5041d5ca"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-linux_armv7l.whl", hash = "sha256:2b96f5f17d3156058be247fd25b062b4768138665694c00b056659618b8fb418"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:11939c9a8a39bd4815c7e88cb2fee48e1948775b59dbb06de8fcae5991e84f9e"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:129de5579f95d6a55dde185f188b4cbe19d1e2f1471425431d9930c31d300d70"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c4128c01cd6f5ea8f7c2db405dbfd8582cd967d36e6fa0952565436633b0e591"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5c7292dd899ad8fa09a2be96719648cee37b17909fe8c12007e3bff58ebee61"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:5ef30c2dbc63c1e0a462423ca4f95001814d26ef4fe66208e53fcf220ea3b717"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4abfc1892380abe6cef381eab86f9350cbd703bfe5d834095aa66fd91c886b6d"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-win32.whl", hash = "sha256:9acf443dcf6f68fbea3b7fb519e1716e014db1a561939f5aecc4abda74e4015d"},
+    {file = "grpcio_tools-1.54.2-cp310-cp310-win_amd64.whl", hash = "sha256:21b9d2dee80f3f77e4097252e7f0db89772335a7300b72ab3d2e5c280872b1db"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-linux_armv7l.whl", hash = "sha256:7b24fbab9e7598518ce4549e066df00aab79c2bf9bedcdde23fb5ef6a3cf532f"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:7baa210c20f71a242d9ae0e02734628f6948e8bee3bf538647894af427d28800"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:e3d0e5188ff8dbaddac2ee44731d36f09c4eccd3eac7328e547862c44f75cacd"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:27671c68c7e0e3c5ff9967f5500799f65a04e7b153b8ce10243c87c43199039d"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f39d8e8806b8857fb473ca6a9c7bd800b0673dfdb7283ff569af0345a222f32c"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:8e4c5a48f7b2e8798ce381498ee7b9a83c65b87ae66ee5022387394e5eb51771"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4f285f8ef3de422717a36bd372239ae778b8cc112ce780ca3c7fe266dadc49fb"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-win32.whl", hash = "sha256:0f952c8a5c47e9204fe8959f7e9add149e660f6579d67cf65024c32736d34caf"},
+    {file = "grpcio_tools-1.54.2-cp311-cp311-win_amd64.whl", hash = "sha256:3237149beec39e897fd62cef4aa1e1cd9422d7a95661d24bd0a79200b167e730"},
+    {file = "grpcio_tools-1.54.2-cp37-cp37m-linux_armv7l.whl", hash = "sha256:0ab1b323905d449298523db5d34fa5bf5fffd645bd872b25598e2f8a01f0ea39"},
+    {file = "grpcio_tools-1.54.2-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:7d7e6e8d62967b3f037f952620cb7381cc39a4bd31790c75fcfba56cc975d70b"},
+    {file = "grpcio_tools-1.54.2-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:7f4624ef2e76a3a5313c4e61a81be38bcc16b59a68a85d30758b84cd2102b161"},
+    {file = "grpcio_tools-1.54.2-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e543f457935ba7b763b121f1bf893974393b4d30065042f947f85a8d81081b80"},
+    {file = "grpcio_tools-1.54.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0239b929eb8b3b30b2397eef3b9abb245087754d77c3721e3be43c44796de87d"},
+    {file = "grpcio_tools-1.54.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:0de05c7698c655e9a240dc34ae91d6017b93143ac89e5b20046d7ca3bd09c27c"},
+    {file = "grpcio_tools-1.54.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:a3ce0b98fb581c471424d2cda45120f57658ed97677c6fec4d6decf5d7c1b976"},
+    {file = "grpcio_tools-1.54.2-cp37-cp37m-win_amd64.whl", hash = "sha256:37393ef90674964175923afe3859fc5a208e1ece565f642b4f76a8c0224a0993"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-linux_armv7l.whl", hash = "sha256:8e4531267736d88fde1022b36dd42ed8163e3575bcbd12bfed96662872aa93fe"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:a0b7049814442f918b522d66b1d015286afbeb9e6d141af54bbfafe31710a3c8"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:b80585e06c4f0082327eb5c9ad96fbdb2b0e7c14971ea5099fe78c22f4608451"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:39fd530cfdf58dc05125775cc233b05554d553d27478f14ae5fd8a6306f0cb28"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3bb9ec4aea0f2b3006fb002fa59e5c10f92b48fc374619fbffd14d2b0e388c3e"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:d512de051342a576bb89777476d13c5266d9334cf4badb6468aed9dc8f5bdec1"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:1b8ee3099c51ce987fa8a08e6b93fc342b10228415dd96b5c0caa0387f636a6f"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-win32.whl", hash = "sha256:6037f123905dc0141f7c8383ca616ef0195e79cd3b4d82faaee789d4045e891b"},
+    {file = "grpcio_tools-1.54.2-cp38-cp38-win_amd64.whl", hash = "sha256:10dd41862f579d185c60f629b5ee89103e216f63b576079d258d974d980bad87"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-linux_armv7l.whl", hash = "sha256:f6787d07fdab31a32c433c1ba34883dea6559d8a3fbe08fb93d834ca34136b71"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:21b1467e31e44429d2a78b50135c9cdbd4b8f6d3b5cd548bc98985d3bdc352d0"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:30a49b8b168aced2a4ff40959e6c4383ad6cfd7a20839a47a215e9837eb722dc"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8742122782953d2fd038f0a199f047a24e941cc9718b1aac90876dbdb7167739"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:503ef1351c62fb1d6747eaf74932b609d8fdd4345b3591ef910adef8fa9969d0"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:72d15de4c4b6a764a76c4ae69d99c35f7a0751223688c3f7e62dfa95eb4f61be"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:df079479fb1b9e488334312e35ebbf30cbf5ecad6c56599f1a961800b33ab7c1"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-win32.whl", hash = "sha256:49c2846dcc4803476e839d8bd4db8845e928f19130e0ea86121f2d1f43d2b452"},
+    {file = "grpcio_tools-1.54.2-cp39-cp39-win_amd64.whl", hash = "sha256:b82ca472db9c914c44e39a41e9e8bd3ed724523dd7aff5ce37592b8d16920ed9"},
 ]
-hf-transfer = [
+
+[package.dependencies]
+grpcio = ">=1.54.2"
+protobuf = ">=4.21.6,<5.0dev"
+setuptools = "*"
+
+[[package]]
+name = "hf-transfer"
+version = "0.1.3"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "hf_transfer-0.1.3-cp310-cp310-macosx_10_9_x86_64.macosx_11_0_arm64.macosx_10_9_universal2.whl", hash = "sha256:862b6ddba8e236bdc73408c20d020cfe5069cac3fd0b6de901c46f031df2b7d9"},
     {file = "hf_transfer-0.1.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:569ef1ec6fec182e706ade4ea0c63f8510fd618ed7ced7c772efaafac7245b07"},
     {file = "hf_transfer-0.1.3-cp310-none-win_amd64.whl", hash = "sha256:c9faa88b3491c50d4aa75faf18ae24040cd91aa0565c7f7ba2357dbcbf8372f6"},
@@ -980,87 +459,196 @@ hf-transfer = [
     {file = "hf_transfer-0.1.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:efb8b41360c7e3d7700c147b70688aed0a03e86fbe5bcfdee079b0e634f026f9"},
     {file = "hf_transfer-0.1.3.tar.gz", hash = "sha256:7afd7eb03efad7812a48591b639b2e3f3d1f93c1e9060c18cc63ebf08d7e193c"},
 ]
-huggingface-hub = [
-    {file = "huggingface_hub-0.14.0-py3-none-any.whl", hash = "sha256:fa6a6139fe4a8a164bfd0cda90c225fe8471b47c12811738b6db8348a2f703a0"},
-    {file = "huggingface_hub-0.14.0.tar.gz", hash = "sha256:42eeab833284e3fc1d39263cf9c3d1bb36b129acdd8195838694d165e8dd6cae"},
+
+[[package]]
+name = "huggingface-hub"
+version = "0.14.1"
+description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
+optional = false
+python-versions = ">=3.7.0"
+files = [
+    {file = "huggingface_hub-0.14.1-py3-none-any.whl", hash = "sha256:9fc619170d800ff3793ad37c9757c255c8783051e1b5b00501205eb43ccc4f27"},
+    {file = "huggingface_hub-0.14.1.tar.gz", hash = "sha256:9ab899af8e10922eac65e290d60ab956882ab0bf643e3d990b1394b6b47b7fbc"},
 ]
-idna = [
+
+[package.dependencies]
+filelock = "*"
+fsspec = "*"
+packaging = ">=20.9"
+pyyaml = ">=5.1"
+requests = "*"
+tqdm = ">=4.42.1"
+typing-extensions = ">=3.7.4.3"
+
+[package.extras]
+all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+cli = ["InquirerPy (==0.3.4)"]
+dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
+quality = ["black (>=23.1,<24.0)", "mypy (==0.982)", "ruff (>=0.0.241)"]
+tensorflow = ["graphviz", "pydot", "tensorflow"]
+testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "gradio", "jedi", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "soundfile"]
+torch = ["torch"]
+typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
+
+[[package]]
+name = "idna"
+version = "3.4"
+description = "Internationalized Domain Names in Applications (IDNA)"
+optional = false
+python-versions = ">=3.5"
+files = [
     {file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
     {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
 ]
-iniconfig = [
+
+[[package]]
+name = "iniconfig"
+version = "2.0.0"
+description = "brain-dead simple config-ini parsing"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
     {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
 ]
-Jinja2 = [
+
+[[package]]
+name = "jinja2"
+version = "3.1.2"
+description = "A very fast and expressive template engine."
+optional = true
+python-versions = ">=3.7"
+files = [
     {file = "Jinja2-3.1.2-py3-none-any.whl", hash = "sha256:6088930bfe239f0e6710546ab9c19c9ef35e29792895fed6e6e31a023a182a61"},
     {file = "Jinja2-3.1.2.tar.gz", hash = "sha256:31351a702a408a9e7595a8fc6150fc3f43bb6bf7e319770cbc0db9df9437e852"},
 ]
-loguru = [
+
+[package.dependencies]
+MarkupSafe = ">=2.0"
+
+[package.extras]
+i18n = ["Babel (>=2.7)"]
+
+[[package]]
+name = "loguru"
+version = "0.6.0"
+description = "Python logging made (stupidly) simple"
+optional = false
+python-versions = ">=3.5"
+files = [
     {file = "loguru-0.6.0-py3-none-any.whl", hash = "sha256:4e2414d534a2ab57573365b3e6d0234dfb1d84b68b7f3b948e6fb743860a77c3"},
     {file = "loguru-0.6.0.tar.gz", hash = "sha256:066bd06758d0a513e9836fd9c6b5a75bfb3fd36841f4b996bc60b547a309d41c"},
 ]
-MarkupSafe = [
-    {file = "MarkupSafe-2.1.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:665a36ae6f8f20a4676b53224e33d456a6f5a72657d9c83c2aa00765072f31f7"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:340bea174e9761308703ae988e982005aedf427de816d1afe98147668cc03036"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22152d00bf4a9c7c83960521fc558f55a1adbc0631fbb00a9471e097b19d72e1"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28057e985dace2f478e042eaa15606c7efccb700797660629da387eb289b9323"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ca244fa73f50a800cf8c3ebf7fd93149ec37f5cb9596aa8873ae2c1d23498601"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d9d971ec1e79906046aa3ca266de79eac42f1dbf3612a05dc9368125952bd1a1"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:7e007132af78ea9df29495dbf7b5824cb71648d7133cf7848a2a5dd00d36f9ff"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:7313ce6a199651c4ed9d7e4cfb4aa56fe923b1adf9af3b420ee14e6d9a73df65"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-win32.whl", hash = "sha256:c4a549890a45f57f1ebf99c067a4ad0cb423a05544accaf2b065246827ed9603"},
-    {file = "MarkupSafe-2.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:835fb5e38fd89328e9c81067fd642b3593c33e1e17e2fdbf77f5676abb14a156"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:2ec4f2d48ae59bbb9d1f9d7efb9236ab81429a764dedca114f5fdabbc3788013"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:608e7073dfa9e38a85d38474c082d4281f4ce276ac0010224eaba11e929dd53a"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:65608c35bfb8a76763f37036547f7adfd09270fbdbf96608be2bead319728fcd"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2bfb563d0211ce16b63c7cb9395d2c682a23187f54c3d79bfec33e6705473c6"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:da25303d91526aac3672ee6d49a2f3db2d9502a4a60b55519feb1a4c7714e07d"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:9cad97ab29dfc3f0249b483412c85c8ef4766d96cdf9dcf5a1e3caa3f3661cf1"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:085fd3201e7b12809f9e6e9bc1e5c96a368c8523fad5afb02afe3c051ae4afcc"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:1bea30e9bf331f3fef67e0a3877b2288593c98a21ccb2cf29b74c581a4eb3af0"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-win32.whl", hash = "sha256:7df70907e00c970c60b9ef2938d894a9381f38e6b9db73c5be35e59d92e06625"},
-    {file = "MarkupSafe-2.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:e55e40ff0cc8cc5c07996915ad367fa47da6b3fc091fdadca7f5403239c5fec3"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:a6e40afa7f45939ca356f348c8e23048e02cb109ced1eb8420961b2f40fb373a"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf877ab4ed6e302ec1d04952ca358b381a882fbd9d1b07cccbfd61783561f98a"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:63ba06c9941e46fa389d389644e2d8225e0e3e5ebcc4ff1ea8506dce646f8c8a"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f1cd098434e83e656abf198f103a8207a8187c0fc110306691a2e94a78d0abb2"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:55f44b440d491028addb3b88f72207d71eeebfb7b5dbf0643f7c023ae1fba619"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:a6f2fcca746e8d5910e18782f976489939d54a91f9411c32051b4aab2bd7c513"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:0b462104ba25f1ac006fdab8b6a01ebbfbce9ed37fd37fd4acd70c67c973e460"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-win32.whl", hash = "sha256:7668b52e102d0ed87cb082380a7e2e1e78737ddecdde129acadb0eccc5423859"},
-    {file = "MarkupSafe-2.1.2-cp37-cp37m-win_amd64.whl", hash = "sha256:6d6607f98fcf17e534162f0709aaad3ab7a96032723d8ac8750ffe17ae5a0666"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:a806db027852538d2ad7555b203300173dd1b77ba116de92da9afbc3a3be3eed"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a4abaec6ca3ad8660690236d11bfe28dfd707778e2442b45addd2f086d6ef094"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f03a532d7dee1bed20bc4884194a16160a2de9ffc6354b3878ec9682bb623c54"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4cf06cdc1dda95223e9d2d3c58d3b178aa5dacb35ee7e3bbac10e4e1faacb419"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22731d79ed2eb25059ae3df1dfc9cb1546691cc41f4e3130fe6bfbc3ecbbecfa"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:f8ffb705ffcf5ddd0e80b65ddf7bed7ee4f5a441ea7d3419e861a12eaf41af58"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:8db032bf0ce9022a8e41a22598eefc802314e81b879ae093f36ce9ddf39ab1ba"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2298c859cfc5463f1b64bd55cb3e602528db6fa0f3cfd568d3605c50678f8f03"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-win32.whl", hash = "sha256:50c42830a633fa0cf9e7d27664637532791bfc31c731a87b202d2d8ac40c3ea2"},
-    {file = "MarkupSafe-2.1.2-cp38-cp38-win_amd64.whl", hash = "sha256:bb06feb762bade6bf3c8b844462274db0c76acc95c52abe8dbed28ae3d44a147"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:99625a92da8229df6d44335e6fcc558a5037dd0a760e11d84be2260e6f37002f"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:8bca7e26c1dd751236cfb0c6c72d4ad61d986e9a41bbf76cb445f69488b2a2bd"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:40627dcf047dadb22cd25ea7ecfe9cbf3bbbad0482ee5920b582f3809c97654f"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40dfd3fefbef579ee058f139733ac336312663c6706d1163b82b3003fb1925c4"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:090376d812fb6ac5f171e5938e82e7f2d7adc2b629101cec0db8b267815c85e2"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2e7821bffe00aa6bd07a23913b7f4e01328c3d5cc0b40b36c0bd81d362faeb65"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:c0a33bc9f02c2b17c3ea382f91b4db0e6cde90b63b296422a939886a7a80de1c"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b8526c6d437855442cdd3d87eede9c425c4445ea011ca38d937db299382e6fa3"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-win32.whl", hash = "sha256:137678c63c977754abe9086a3ec011e8fd985ab90631145dfb9294ad09c102a7"},
-    {file = "MarkupSafe-2.1.2-cp39-cp39-win_amd64.whl", hash = "sha256:0576fe974b40a400449768941d5d0858cc624e3249dfd1e0c33674e5c7ca7aed"},
-    {file = "MarkupSafe-2.1.2.tar.gz", hash = "sha256:abcabc8c2b26036d62d4c746381a6f7cf60aafcc653198ad678306986b09450d"},
+
+[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 (>=4.1.1)", "black (>=19.10b0)", "colorama (>=0.3.4)", "docutils (==0.16)", "flake8 (>=3.7.7)", "isort (>=5.1.1)", "pytest (>=4.6.2)", "pytest-cov (>=2.7.1)", "sphinx-autobuild (>=0.7.1)", "sphinx-rtd-theme (>=0.4.3)", "tox (>=3.9.0)"]
+
+[[package]]
+name = "markupsafe"
+version = "2.1.3"
+description = "Safely add untrusted strings to HTML/XML markup."
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "MarkupSafe-2.1.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cd0f502fe016460680cd20aaa5a76d241d6f35a1c3350c474bac1273803893fa"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e09031c87a1e51556fdcb46e5bd4f59dfb743061cf93c4d6831bf894f125eb57"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68e78619a61ecf91e76aa3e6e8e33fc4894a2bebe93410754bd28fce0a8a4f9f"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:65c1a9bcdadc6c28eecee2c119465aebff8f7a584dd719facdd9e825ec61ab52"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:525808b8019e36eb524b8c68acdd63a37e75714eac50e988180b169d64480a00"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:962f82a3086483f5e5f64dbad880d31038b698494799b097bc59c2edf392fce6"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:aa7bd130efab1c280bed0f45501b7c8795f9fdbeb02e965371bbef3523627779"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:c9c804664ebe8f83a211cace637506669e7890fec1b4195b505c214e50dd4eb7"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-win32.whl", hash = "sha256:10bbfe99883db80bdbaff2dcf681dfc6533a614f700da1287707e8a5d78a8431"},
+    {file = "MarkupSafe-2.1.3-cp310-cp310-win_amd64.whl", hash = "sha256:1577735524cdad32f9f694208aa75e422adba74f1baee7551620e43a3141f559"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:ad9e82fb8f09ade1c3e1b996a6337afac2b8b9e365f926f5a61aacc71adc5b3c"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3c0fae6c3be832a0a0473ac912810b2877c8cb9d76ca48de1ed31e1c68386575"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b076b6226fb84157e3f7c971a47ff3a679d837cf338547532ab866c57930dbee"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bfce63a9e7834b12b87c64d6b155fdd9b3b96191b6bd334bf37db7ff1fe457f2"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:338ae27d6b8745585f87218a3f23f1512dbf52c26c28e322dbe54bcede54ccb9"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e4dd52d80b8c83fdce44e12478ad2e85c64ea965e75d66dbeafb0a3e77308fcc"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:df0be2b576a7abbf737b1575f048c23fb1d769f267ec4358296f31c2479db8f9"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5bbe06f8eeafd38e5d0a4894ffec89378b6c6a625ff57e3028921f8ff59318ac"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-win32.whl", hash = "sha256:dd15ff04ffd7e05ffcb7fe79f1b98041b8ea30ae9234aed2a9168b5797c3effb"},
+    {file = "MarkupSafe-2.1.3-cp311-cp311-win_amd64.whl", hash = "sha256:134da1eca9ec0ae528110ccc9e48041e0828d79f24121a1a146161103c76e686"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:8e254ae696c88d98da6555f5ace2279cf7cd5b3f52be2b5cf97feafe883b58d2"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb0932dc158471523c9637e807d9bfb93e06a95cbf010f1a38b98623b929ef2b"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9402b03f1a1b4dc4c19845e5c749e3ab82d5078d16a2a4c2cd2df62d57bb0707"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ca379055a47383d02a5400cb0d110cef0a776fc644cda797db0c5696cfd7e18e"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:b7ff0f54cb4ff66dd38bebd335a38e2c22c41a8ee45aa608efc890ac3e3931bc"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:c011a4149cfbcf9f03994ec2edffcb8b1dc2d2aede7ca243746df97a5d41ce48"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:56d9f2ecac662ca1611d183feb03a3fa4406469dafe241673d521dd5ae92a155"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-win32.whl", hash = "sha256:8758846a7e80910096950b67071243da3e5a20ed2546e6392603c096778d48e0"},
+    {file = "MarkupSafe-2.1.3-cp37-cp37m-win_amd64.whl", hash = "sha256:787003c0ddb00500e49a10f2844fac87aa6ce977b90b0feaaf9de23c22508b24"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:2ef12179d3a291be237280175b542c07a36e7f60718296278d8593d21ca937d4"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2c1b19b3aaacc6e57b7e25710ff571c24d6c3613a45e905b1fde04d691b98ee0"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8afafd99945ead6e075b973fefa56379c5b5c53fd8937dad92c662da5d8fd5ee"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8c41976a29d078bb235fea9b2ecd3da465df42a562910f9022f1a03107bd02be"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d080e0a5eb2529460b30190fcfcc4199bd7f827663f858a226a81bc27beaa97e"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:69c0f17e9f5a7afdf2cc9fb2d1ce6aabdb3bafb7f38017c0b77862bcec2bbad8"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:504b320cd4b7eff6f968eddf81127112db685e81f7e36e75f9f84f0df46041c3"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:42de32b22b6b804f42c5d98be4f7e5e977ecdd9ee9b660fda1a3edf03b11792d"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-win32.whl", hash = "sha256:ceb01949af7121f9fc39f7d27f91be8546f3fb112c608bc4029aef0bab86a2a5"},
+    {file = "MarkupSafe-2.1.3-cp38-cp38-win_amd64.whl", hash = "sha256:1b40069d487e7edb2676d3fbdb2b0829ffa2cd63a2ec26c4938b2d34391b4ecc"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:8023faf4e01efadfa183e863fefde0046de576c6f14659e8782065bcece22198"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6b2b56950d93e41f33b4223ead100ea0fe11f8e6ee5f641eb753ce4b77a7042b"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9dcdfd0eaf283af041973bff14a2e143b8bd64e069f4c383416ecd79a81aab58"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:05fb21170423db021895e1ea1e1f3ab3adb85d1c2333cbc2310f2a26bc77272e"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:282c2cb35b5b673bbcadb33a585408104df04f14b2d9b01d4c345a3b92861c2c"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ab4a0df41e7c16a1392727727e7998a467472d0ad65f3ad5e6e765015df08636"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:7ef3cb2ebbf91e330e3bb937efada0edd9003683db6b57bb108c4001f37a02ea"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:0a4e4a1aff6c7ac4cd55792abf96c915634c2b97e3cc1c7129578aa68ebd754e"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-win32.whl", hash = "sha256:fec21693218efe39aa7f8599346e90c705afa52c5b31ae019b2e57e8f6542bb2"},
+    {file = "MarkupSafe-2.1.3-cp39-cp39-win_amd64.whl", hash = "sha256:3fd4abcb888d15a94f32b75d8fd18ee162ca0c064f35b11134be77050296d6ba"},
+    {file = "MarkupSafe-2.1.3.tar.gz", hash = "sha256:af598ed32d6ae86f1b747b82783958b1a4ab8f617b06fe68795c7f026abbdcad"},
 ]
-mpmath = [
+
+[[package]]
+name = "mpmath"
+version = "1.3.0"
+description = "Python library for arbitrary-precision floating-point arithmetic"
+optional = true
+python-versions = "*"
+files = [
     {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
     {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
 ]
-networkx = [
+
+[package.extras]
+develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
+docs = ["sphinx"]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
+tests = ["pytest (>=4.6)"]
+
+[[package]]
+name = "networkx"
+version = "3.1"
+description = "Python package for creating and manipulating graphs and networks"
+optional = true
+python-versions = ">=3.8"
+files = [
     {file = "networkx-3.1-py3-none-any.whl", hash = "sha256:4f33f68cb2afcf86f28a45f43efc27a9386b535d567d2127f8f61d51dec58d36"},
     {file = "networkx-3.1.tar.gz", hash = "sha256:de346335408f84de0eada6ff9fafafff9bcda11f0a0dfaa931133debb146ab61"},
 ]
-numpy = [
+
+[package.extras]
+default = ["matplotlib (>=3.4)", "numpy (>=1.20)", "pandas (>=1.3)", "scipy (>=1.8)"]
+developer = ["mypy (>=1.1)", "pre-commit (>=3.2)"]
+doc = ["nb2plots (>=0.6)", "numpydoc (>=1.5)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.13)", "sphinx (>=6.1)", "sphinx-gallery (>=0.12)", "texext (>=0.6.7)"]
+extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.10)", "sympy (>=1.10)"]
+test = ["codecov (>=2.1)", "pytest (>=7.2)", "pytest-cov (>=4.0)"]
+
+[[package]]
+name = "numpy"
+version = "1.24.3"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = ">=3.8"
+files = [
     {file = "numpy-1.24.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:3c1104d3c036fb81ab923f507536daedc718d0ad5a8707c6061cdfd6d184e570"},
     {file = "numpy-1.24.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:202de8f38fc4a45a3eea4b63e2f376e5f2dc64ef0fa692838e31a808520efaf7"},
     {file = "numpy-1.24.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8535303847b89aa6b0f00aa1dc62867b5a32923e4d1681a35b5eef2d9591a463"},
@@ -1090,66 +678,216 @@ numpy = [
     {file = "numpy-1.24.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:35400e6a8d102fd07c71ed7dcadd9eb62ee9a6e84ec159bd48c28235bbb0f8e4"},
     {file = "numpy-1.24.3.tar.gz", hash = "sha256:ab344f1bf21f140adab8e47fdbc7c35a477dc01408791f8ba00d018dd0bc5155"},
 ]
-opentelemetry-api = [
+
+[[package]]
+name = "opentelemetry-api"
+version = "1.15.0"
+description = "OpenTelemetry Python API"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_api-1.15.0-py3-none-any.whl", hash = "sha256:e6c2d2e42140fd396e96edf75a7ceb11073f4efb4db87565a431cc9d0f93f2e0"},
     {file = "opentelemetry_api-1.15.0.tar.gz", hash = "sha256:79ab791b4aaad27acc3dc3ba01596db5b5aac2ef75c70622c6038051d6c2cded"},
 ]
-opentelemetry-exporter-otlp = [
+
+[package.dependencies]
+deprecated = ">=1.2.6"
+setuptools = ">=16.0"
+
+[[package]]
+name = "opentelemetry-exporter-otlp"
+version = "1.15.0"
+description = "OpenTelemetry Collector Exporters"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_exporter_otlp-1.15.0-py3-none-any.whl", hash = "sha256:79f22748b6a54808a0448093dfa189c8490e729f67c134d4c992533d9393b33e"},
     {file = "opentelemetry_exporter_otlp-1.15.0.tar.gz", hash = "sha256:4f7c49751d9720e2e726e13b0bb958ccade4e29122c305d92c033da432c8d2c5"},
 ]
-opentelemetry-exporter-otlp-proto-grpc = [
+
+[package.dependencies]
+opentelemetry-exporter-otlp-proto-grpc = "1.15.0"
+opentelemetry-exporter-otlp-proto-http = "1.15.0"
+
+[[package]]
+name = "opentelemetry-exporter-otlp-proto-grpc"
+version = "1.15.0"
+description = "OpenTelemetry Collector Protobuf over gRPC Exporter"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_exporter_otlp_proto_grpc-1.15.0-py3-none-any.whl", hash = "sha256:c2a5492ba7d140109968135d641d06ce3c5bd73c50665f787526065d57d7fd1d"},
     {file = "opentelemetry_exporter_otlp_proto_grpc-1.15.0.tar.gz", hash = "sha256:844f2a4bb9bcda34e4eb6fe36765e5031aacb36dc60ed88c90fc246942ea26e7"},
 ]
-opentelemetry-exporter-otlp-proto-http = [
+
+[package.dependencies]
+backoff = {version = ">=1.10.0,<3.0.0", markers = "python_version >= \"3.7\""}
+googleapis-common-protos = ">=1.52,<2.0"
+grpcio = ">=1.0.0,<2.0.0"
+opentelemetry-api = ">=1.12,<2.0"
+opentelemetry-proto = "1.15.0"
+opentelemetry-sdk = ">=1.12,<2.0"
+
+[package.extras]
+test = ["pytest-grpc"]
+
+[[package]]
+name = "opentelemetry-exporter-otlp-proto-http"
+version = "1.15.0"
+description = "OpenTelemetry Collector Protobuf over HTTP Exporter"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_exporter_otlp_proto_http-1.15.0-py3-none-any.whl", hash = "sha256:3ec2a02196c8a54bf5cbf7fe623a5238625638e83b6047a983bdf96e2bbb74c0"},
     {file = "opentelemetry_exporter_otlp_proto_http-1.15.0.tar.gz", hash = "sha256:11b2c814249a49b22f6cca7a06b05701f561d577b747f3660dfd67b6eb9daf9c"},
 ]
-opentelemetry-instrumentation = [
+
+[package.dependencies]
+backoff = {version = ">=1.10.0,<3.0.0", markers = "python_version >= \"3.7\""}
+googleapis-common-protos = ">=1.52,<2.0"
+opentelemetry-api = ">=1.12,<2.0"
+opentelemetry-proto = "1.15.0"
+opentelemetry-sdk = ">=1.12,<2.0"
+requests = ">=2.7,<3.0"
+
+[package.extras]
+test = ["responses (==0.22.0)"]
+
+[[package]]
+name = "opentelemetry-instrumentation"
+version = "0.36b0"
+description = "Instrumentation Tools & Auto Instrumentation for OpenTelemetry Python"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_instrumentation-0.36b0-py3-none-any.whl", hash = "sha256:83ba4ae7d5292b5b33e0f851cc5c76d8f91196b9b3527800fc13855c33383ac2"},
     {file = "opentelemetry_instrumentation-0.36b0.tar.gz", hash = "sha256:e3ddac9b3b93408ef26c8ecbf38f717042977e16381bb4cd329a5b4cf16998cf"},
 ]
-opentelemetry-instrumentation-grpc = [
+
+[package.dependencies]
+opentelemetry-api = ">=1.4,<2.0"
+setuptools = ">=16.0"
+wrapt = ">=1.0.0,<2.0.0"
+
+[[package]]
+name = "opentelemetry-instrumentation-grpc"
+version = "0.36b0"
+description = "OpenTelemetry gRPC instrumentation"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_instrumentation_grpc-0.36b0-py3-none-any.whl", hash = "sha256:eaa246ed2083c97b13bab2555cb9d170e8433230a31476c4cab8a17fa03380a4"},
     {file = "opentelemetry_instrumentation_grpc-0.36b0.tar.gz", hash = "sha256:dc89447c9eb6ea868970f6c13b4ffdac182cdd5a41dd215a0f5393ca6375be55"},
 ]
-opentelemetry-proto = [
+
+[package.dependencies]
+opentelemetry-api = ">=1.12,<2.0"
+opentelemetry-instrumentation = "0.36b0"
+opentelemetry-sdk = ">=1.12,<2.0"
+opentelemetry-semantic-conventions = "0.36b0"
+wrapt = ">=1.0.0,<2.0.0"
+
+[package.extras]
+instruments = ["grpcio (>=1.27,<2.0)"]
+test = ["opentelemetry-instrumentation-grpc[instruments]", "opentelemetry-sdk (>=1.12,<2.0)", "opentelemetry-test-utils (==0.36b0)", "protobuf (>=3.13,<4.0)"]
+
+[[package]]
+name = "opentelemetry-proto"
+version = "1.15.0"
+description = "OpenTelemetry Python Proto"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_proto-1.15.0-py3-none-any.whl", hash = "sha256:044b6d044b4d10530f250856f933442b8753a17f94ae37c207607f733fb9a844"},
     {file = "opentelemetry_proto-1.15.0.tar.gz", hash = "sha256:9c4008e40ac8cab359daac283fbe7002c5c29c77ea2674ad5626a249e64e0101"},
 ]
-opentelemetry-sdk = [
+
+[package.dependencies]
+protobuf = ">=3.19,<5.0"
+
+[[package]]
+name = "opentelemetry-sdk"
+version = "1.15.0"
+description = "OpenTelemetry Python SDK"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_sdk-1.15.0-py3-none-any.whl", hash = "sha256:555c533e9837766119bbccc7a80458c9971d853a6f1da683a2246cd5e53b4645"},
     {file = "opentelemetry_sdk-1.15.0.tar.gz", hash = "sha256:98dbffcfeebcbff12c0c974292d6ea603180a145904cf838b1fe4d5c99078425"},
 ]
-opentelemetry-semantic-conventions = [
+
+[package.dependencies]
+opentelemetry-api = "1.15.0"
+opentelemetry-semantic-conventions = "0.36b0"
+setuptools = ">=16.0"
+typing-extensions = ">=3.7.4"
+
+[[package]]
+name = "opentelemetry-semantic-conventions"
+version = "0.36b0"
+description = "OpenTelemetry Semantic Conventions"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "opentelemetry_semantic_conventions-0.36b0-py3-none-any.whl", hash = "sha256:adc05635e87b9d3e007c9f530eed487fc3ef2177d02f82f674f28ebf9aff8243"},
     {file = "opentelemetry_semantic_conventions-0.36b0.tar.gz", hash = "sha256:829dc221795467d98b773c04096e29be038d77526dc8d6ac76f546fb6279bf01"},
 ]
-packaging = [
+
+[[package]]
+name = "packaging"
+version = "23.1"
+description = "Core utilities for Python packages"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "packaging-23.1-py3-none-any.whl", hash = "sha256:994793af429502c4ea2ebf6bf664629d07c1a9fe974af92966e4b8d2df7edc61"},
     {file = "packaging-23.1.tar.gz", hash = "sha256:a392980d2b6cffa644431898be54b0045151319d1e7ec34f0cfed48767dd334f"},
 ]
-pluggy = [
+
+[[package]]
+name = "pluggy"
+version = "1.0.0"
+description = "plugin and hook calling mechanisms for python"
+optional = false
+python-versions = ">=3.6"
+files = [
     {file = "pluggy-1.0.0-py2.py3-none-any.whl", hash = "sha256:74134bbf457f031a36d68416e1509f34bd5ccc019f0bcc952c7b909d06b37bd3"},
     {file = "pluggy-1.0.0.tar.gz", hash = "sha256:4224373bacce55f955a878bf9cfa763c1e360858e330072059e10bad68531159"},
 ]
-protobuf = [
-    {file = "protobuf-4.23.1-cp310-abi3-win32.whl", hash = "sha256:410bcc0a5b279f634d3e16082ce221dfef7c3392fac723500e2e64d1806dd2be"},
-    {file = "protobuf-4.23.1-cp310-abi3-win_amd64.whl", hash = "sha256:32e78beda26d7a101fecf15d7a4a792278a0d26a31bc327ff05564a9d68ab8ee"},
-    {file = "protobuf-4.23.1-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:f9510cac91e764e86acd74e2b7f7bc5e6127a7f3fb646d7c8033cfb84fd1176a"},
-    {file = "protobuf-4.23.1-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:346990f634272caac1f09efbcfbbacb23098b1f606d172534c6fa2d9758bb436"},
-    {file = "protobuf-4.23.1-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:3ce113b3f3362493bddc9069c2163a38f240a9ed685ff83e7bcb756b05e1deb0"},
-    {file = "protobuf-4.23.1-cp37-cp37m-win32.whl", hash = "sha256:2036a3a1e7fc27f973fa0a7888dce712393af644f4695385f117886abc792e39"},
-    {file = "protobuf-4.23.1-cp37-cp37m-win_amd64.whl", hash = "sha256:3b8905eafe4439076e1f58e9d1fa327025fd2777cf90f14083092ae47f77b0aa"},
-    {file = "protobuf-4.23.1-cp38-cp38-win32.whl", hash = "sha256:5b9cd6097e6acae48a68cb29b56bc79339be84eca65b486910bb1e7a30e2b7c1"},
-    {file = "protobuf-4.23.1-cp38-cp38-win_amd64.whl", hash = "sha256:decf119d54e820f298ee6d89c72d6b289ea240c32c521f00433f9dc420595f38"},
-    {file = "protobuf-4.23.1-cp39-cp39-win32.whl", hash = "sha256:91fac0753c3c4951fbb98a93271c43cc7cf3b93cf67747b3e600bb1e5cc14d61"},
-    {file = "protobuf-4.23.1-cp39-cp39-win_amd64.whl", hash = "sha256:ac50be82491369a9ec3710565777e4da87c6d2e20404e0abb1f3a8f10ffd20f0"},
-    {file = "protobuf-4.23.1-py3-none-any.whl", hash = "sha256:65f0ac96ef67d7dd09b19a46aad81a851b6f85f89725577f16de38f2d68ad477"},
-    {file = "protobuf-4.23.1.tar.gz", hash = "sha256:95789b569418a3e32a53f43d7763be3d490a831e9c08042539462b6d972c2d7e"},
+
+[package.extras]
+dev = ["pre-commit", "tox"]
+testing = ["pytest", "pytest-benchmark"]
+
+[[package]]
+name = "protobuf"
+version = "4.23.2"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "protobuf-4.23.2-cp310-abi3-win32.whl", hash = "sha256:384dd44cb4c43f2ccddd3645389a23ae61aeb8cfa15ca3a0f60e7c3ea09b28b3"},
+    {file = "protobuf-4.23.2-cp310-abi3-win_amd64.whl", hash = "sha256:09310bce43353b46d73ba7e3bca78273b9bc50349509b9698e64d288c6372c2a"},
+    {file = "protobuf-4.23.2-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:b2cfab63a230b39ae603834718db74ac11e52bccaaf19bf20f5cce1a84cf76df"},
+    {file = "protobuf-4.23.2-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:c52cfcbfba8eb791255edd675c1fe6056f723bf832fa67f0442218f8817c076e"},
+    {file = "protobuf-4.23.2-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:86df87016d290143c7ce3be3ad52d055714ebaebb57cc659c387e76cfacd81aa"},
+    {file = "protobuf-4.23.2-cp37-cp37m-win32.whl", hash = "sha256:281342ea5eb631c86697e1e048cb7e73b8a4e85f3299a128c116f05f5c668f8f"},
+    {file = "protobuf-4.23.2-cp37-cp37m-win_amd64.whl", hash = "sha256:ce744938406de1e64b91410f473736e815f28c3b71201302612a68bf01517fea"},
+    {file = "protobuf-4.23.2-cp38-cp38-win32.whl", hash = "sha256:6c081863c379bb1741be8f8193e893511312b1d7329b4a75445d1ea9955be69e"},
+    {file = "protobuf-4.23.2-cp38-cp38-win_amd64.whl", hash = "sha256:25e3370eda26469b58b602e29dff069cfaae8eaa0ef4550039cc5ef8dc004511"},
+    {file = "protobuf-4.23.2-cp39-cp39-win32.whl", hash = "sha256:efabbbbac1ab519a514579ba9ec52f006c28ae19d97915951f69fa70da2c9e91"},
+    {file = "protobuf-4.23.2-cp39-cp39-win_amd64.whl", hash = "sha256:54a533b971288af3b9926e53850c7eb186886c0c84e61daa8444385a4720297f"},
+    {file = "protobuf-4.23.2-py3-none-any.whl", hash = "sha256:8da6070310d634c99c0db7df48f10da495cc283fd9e9234877f0cd182d43ab7f"},
+    {file = "protobuf-4.23.2.tar.gz", hash = "sha256:20874e7ca4436f683b64ebdbee2129a5a2c301579a67d1a7dda2cdf62fb7f5f7"},
 ]
-psutil = [
+
+[[package]]
+name = "psutil"
+version = "5.9.5"
+description = "Cross-platform lib for process and system monitoring in Python."
+optional = true
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+files = [
     {file = "psutil-5.9.5-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:be8929ce4313f9f8146caad4272f6abb8bf99fc6cf59344a3167ecd74f4f203f"},
     {file = "psutil-5.9.5-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:ab8ed1a1d77c95453db1ae00a3f9c50227ebd955437bcf2a574ba8adbf6a74d5"},
     {file = "psutil-5.9.5-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:4aef137f3345082a3d3232187aeb4ac4ef959ba3d7c10c33dd73763fbc063da4"},
@@ -1165,11 +903,39 @@ psutil = [
     {file = "psutil-5.9.5-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:c607bb3b57dc779d55e1554846352b4e358c10fff3abf3514a7a6601beebdb30"},
     {file = "psutil-5.9.5.tar.gz", hash = "sha256:5410638e4df39c54d957fc51ce03048acd8e6d60abc0f5107af51e5fb566eb3c"},
 ]
-pytest = [
-    {file = "pytest-7.3.1-py3-none-any.whl", hash = "sha256:3799fa815351fea3a5e96ac7e503a96fa51cc9942c3753cda7651b93c1cfa362"},
-    {file = "pytest-7.3.1.tar.gz", hash = "sha256:434afafd78b1d78ed0addf160ad2b77a30d35d4bdf8af234fe621919d9ed15e3"},
+
+[package.extras]
+test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
+
+[[package]]
+name = "pytest"
+version = "7.3.2"
+description = "pytest: simple powerful testing with Python"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "pytest-7.3.2-py3-none-any.whl", hash = "sha256:cdcbd012c9312258922f8cd3f1b62a6580fdced17db6014896053d47cddf9295"},
+    {file = "pytest-7.3.2.tar.gz", hash = "sha256:ee990a3cc55ba808b80795a79944756f315c67c12b56abd3ac993a7b8c17030b"},
 ]
-PyYAML = [
+
+[package.dependencies]
+colorama = {version = "*", markers = "sys_platform == \"win32\""}
+exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
+iniconfig = "*"
+packaging = "*"
+pluggy = ">=0.12,<2.0"
+tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
+
+[package.extras]
+testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
+
+[[package]]
+name = "pyyaml"
+version = "6.0"
+description = "YAML parser and emitter for Python"
+optional = false
+python-versions = ">=3.6"
+files = [
     {file = "PyYAML-6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4db7c7aef085872ef65a8fd7d6d09a14ae91f691dec3e87ee5ee0539d516f53"},
     {file = "PyYAML-6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9df7ed3b3d2e0ecfe09e14741b857df43adb5a3ddadc919a2d94fbdf78fea53c"},
     {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77f396e6ef4c73fdc33a9157446466f1cff553d979bd00ecb64385760c6babdc"},
@@ -1211,11 +977,132 @@ PyYAML = [
     {file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"},
     {file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"},
 ]
-requests = [
+
+[[package]]
+name = "regex"
+version = "2023.6.3"
+description = "Alternative regular expression module, to replace re."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "regex-2023.6.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:824bf3ac11001849aec3fa1d69abcb67aac3e150a933963fb12bda5151fe1bfd"},
+    {file = "regex-2023.6.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:05ed27acdf4465c95826962528f9e8d41dbf9b1aa8531a387dee6ed215a3e9ef"},
+    {file = "regex-2023.6.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0b49c764f88a79160fa64f9a7b425620e87c9f46095ef9c9920542ab2495c8bc"},
+    {file = "regex-2023.6.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8e3f1316c2293e5469f8f09dc2d76efb6c3982d3da91ba95061a7e69489a14ef"},
+    {file = "regex-2023.6.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:43e1dd9d12df9004246bacb79a0e5886b3b6071b32e41f83b0acbf293f820ee8"},
+    {file = "regex-2023.6.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4959e8bcbfda5146477d21c3a8ad81b185cd252f3d0d6e4724a5ef11c012fb06"},
+    {file = "regex-2023.6.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:af4dd387354dc83a3bff67127a124c21116feb0d2ef536805c454721c5d7993d"},
+    {file = "regex-2023.6.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:2239d95d8e243658b8dbb36b12bd10c33ad6e6933a54d36ff053713f129aa536"},
+    {file = "regex-2023.6.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:890e5a11c97cf0d0c550eb661b937a1e45431ffa79803b942a057c4fb12a2da2"},
+    {file = "regex-2023.6.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a8105e9af3b029f243ab11ad47c19b566482c150c754e4c717900a798806b222"},
+    {file = "regex-2023.6.3-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:25be746a8ec7bc7b082783216de8e9473803706723b3f6bef34b3d0ed03d57e2"},
+    {file = "regex-2023.6.3-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:3676f1dd082be28b1266c93f618ee07741b704ab7b68501a173ce7d8d0d0ca18"},
+    {file = "regex-2023.6.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:10cb847aeb1728412c666ab2e2000ba6f174f25b2bdc7292e7dd71b16db07568"},
+    {file = "regex-2023.6.3-cp310-cp310-win32.whl", hash = "sha256:dbbbfce33cd98f97f6bffb17801b0576e653f4fdb1d399b2ea89638bc8d08ae1"},
+    {file = "regex-2023.6.3-cp310-cp310-win_amd64.whl", hash = "sha256:c5f8037000eb21e4823aa485149f2299eb589f8d1fe4b448036d230c3f4e68e0"},
+    {file = "regex-2023.6.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c123f662be8ec5ab4ea72ea300359023a5d1df095b7ead76fedcd8babbedf969"},
+    {file = "regex-2023.6.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9edcbad1f8a407e450fbac88d89e04e0b99a08473f666a3f3de0fd292badb6aa"},
+    {file = "regex-2023.6.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dcba6dae7de533c876255317c11f3abe4907ba7d9aa15d13e3d9710d4315ec0e"},
+    {file = "regex-2023.6.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:29cdd471ebf9e0f2fb3cac165efedc3c58db841d83a518b082077e612d3ee5df"},
+    {file = "regex-2023.6.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:12b74fbbf6cbbf9dbce20eb9b5879469e97aeeaa874145517563cca4029db65c"},
+    {file = "regex-2023.6.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c29ca1bd61b16b67be247be87390ef1d1ef702800f91fbd1991f5c4421ebae8"},
+    {file = "regex-2023.6.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d77f09bc4b55d4bf7cc5eba785d87001d6757b7c9eec237fe2af57aba1a071d9"},
+    {file = "regex-2023.6.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ea353ecb6ab5f7e7d2f4372b1e779796ebd7b37352d290096978fea83c4dba0c"},
+    {file = "regex-2023.6.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:10590510780b7541969287512d1b43f19f965c2ece6c9b1c00fc367b29d8dce7"},
+    {file = "regex-2023.6.3-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:e2fbd6236aae3b7f9d514312cdb58e6494ee1c76a9948adde6eba33eb1c4264f"},
+    {file = "regex-2023.6.3-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:6b2675068c8b56f6bfd5a2bda55b8accbb96c02fd563704732fd1c95e2083461"},
+    {file = "regex-2023.6.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:74419d2b50ecb98360cfaa2974da8689cb3b45b9deff0dcf489c0d333bcc1477"},
+    {file = "regex-2023.6.3-cp311-cp311-win32.whl", hash = "sha256:fb5ec16523dc573a4b277663a2b5a364e2099902d3944c9419a40ebd56a118f9"},
+    {file = "regex-2023.6.3-cp311-cp311-win_amd64.whl", hash = "sha256:09e4a1a6acc39294a36b7338819b10baceb227f7f7dbbea0506d419b5a1dd8af"},
+    {file = "regex-2023.6.3-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:0654bca0cdf28a5956c83839162692725159f4cda8d63e0911a2c0dc76166525"},
+    {file = "regex-2023.6.3-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:463b6a3ceb5ca952e66550a4532cef94c9a0c80dc156c4cc343041951aec1697"},
+    {file = "regex-2023.6.3-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:87b2a5bb5e78ee0ad1de71c664d6eb536dc3947a46a69182a90f4410f5e3f7dd"},
+    {file = "regex-2023.6.3-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6343c6928282c1f6a9db41f5fd551662310e8774c0e5ebccb767002fcf663ca9"},
+    {file = "regex-2023.6.3-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b6192d5af2ccd2a38877bfef086d35e6659566a335b1492786ff254c168b1693"},
+    {file = "regex-2023.6.3-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:74390d18c75054947e4194019077e243c06fbb62e541d8817a0fa822ea310c14"},
+    {file = "regex-2023.6.3-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:742e19a90d9bb2f4a6cf2862b8b06dea5e09b96c9f2df1779e53432d7275331f"},
+    {file = "regex-2023.6.3-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:8abbc5d54ea0ee80e37fef009e3cec5dafd722ed3c829126253d3e22f3846f1e"},
+    {file = "regex-2023.6.3-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:c2b867c17a7a7ae44c43ebbeb1b5ff406b3e8d5b3e14662683e5e66e6cc868d3"},
+    {file = "regex-2023.6.3-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:d831c2f8ff278179705ca59f7e8524069c1a989e716a1874d6d1aab6119d91d1"},
+    {file = "regex-2023.6.3-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:ee2d1a9a253b1729bb2de27d41f696ae893507c7db224436abe83ee25356f5c1"},
+    {file = "regex-2023.6.3-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:61474f0b41fe1a80e8dfa70f70ea1e047387b7cd01c85ec88fa44f5d7561d787"},
+    {file = "regex-2023.6.3-cp36-cp36m-win32.whl", hash = "sha256:0b71e63226e393b534105fcbdd8740410dc6b0854c2bfa39bbda6b0d40e59a54"},
+    {file = "regex-2023.6.3-cp36-cp36m-win_amd64.whl", hash = "sha256:bbb02fd4462f37060122e5acacec78e49c0fbb303c30dd49c7f493cf21fc5b27"},
+    {file = "regex-2023.6.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b862c2b9d5ae38a68b92e215b93f98d4c5e9454fa36aae4450f61dd33ff48487"},
+    {file = "regex-2023.6.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:976d7a304b59ede34ca2921305b57356694f9e6879db323fd90a80f865d355a3"},
+    {file = "regex-2023.6.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:83320a09188e0e6c39088355d423aa9d056ad57a0b6c6381b300ec1a04ec3d16"},
+    {file = "regex-2023.6.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9427a399501818a7564f8c90eced1e9e20709ece36be701f394ada99890ea4b3"},
+    {file = "regex-2023.6.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7178bbc1b2ec40eaca599d13c092079bf529679bf0371c602edaa555e10b41c3"},
+    {file = "regex-2023.6.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:837328d14cde912af625d5f303ec29f7e28cdab588674897baafaf505341f2fc"},
+    {file = "regex-2023.6.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:2d44dc13229905ae96dd2ae2dd7cebf824ee92bc52e8cf03dcead37d926da019"},
+    {file = "regex-2023.6.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:d54af539295392611e7efbe94e827311eb8b29668e2b3f4cadcfe6f46df9c777"},
+    {file = "regex-2023.6.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:7117d10690c38a622e54c432dfbbd3cbd92f09401d622902c32f6d377e2300ee"},
+    {file = "regex-2023.6.3-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:bb60b503ec8a6e4e3e03a681072fa3a5adcbfa5479fa2d898ae2b4a8e24c4591"},
+    {file = "regex-2023.6.3-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:65ba8603753cec91c71de423a943ba506363b0e5c3fdb913ef8f9caa14b2c7e0"},
+    {file = "regex-2023.6.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:271f0bdba3c70b58e6f500b205d10a36fb4b58bd06ac61381b68de66442efddb"},
+    {file = "regex-2023.6.3-cp37-cp37m-win32.whl", hash = "sha256:9beb322958aaca059f34975b0df135181f2e5d7a13b84d3e0e45434749cb20f7"},
+    {file = "regex-2023.6.3-cp37-cp37m-win_amd64.whl", hash = "sha256:fea75c3710d4f31389eed3c02f62d0b66a9da282521075061ce875eb5300cf23"},
+    {file = "regex-2023.6.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:8f56fcb7ff7bf7404becdfc60b1e81a6d0561807051fd2f1860b0d0348156a07"},
+    {file = "regex-2023.6.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:d2da3abc88711bce7557412310dfa50327d5769a31d1c894b58eb256459dc289"},
+    {file = "regex-2023.6.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a99b50300df5add73d307cf66abea093304a07eb017bce94f01e795090dea87c"},
+    {file = "regex-2023.6.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5708089ed5b40a7b2dc561e0c8baa9535b77771b64a8330b684823cfd5116036"},
+    {file = "regex-2023.6.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:687ea9d78a4b1cf82f8479cab23678aff723108df3edeac098e5b2498879f4a7"},
+    {file = "regex-2023.6.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4d3850beab9f527f06ccc94b446c864059c57651b3f911fddb8d9d3ec1d1b25d"},
+    {file = "regex-2023.6.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e8915cc96abeb8983cea1df3c939e3c6e1ac778340c17732eb63bb96247b91d2"},
+    {file = "regex-2023.6.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:841d6e0e5663d4c7b4c8099c9997be748677d46cbf43f9f471150e560791f7ff"},
+    {file = "regex-2023.6.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:9edce5281f965cf135e19840f4d93d55b3835122aa76ccacfd389e880ba4cf82"},
+    {file = "regex-2023.6.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:b956231ebdc45f5b7a2e1f90f66a12be9610ce775fe1b1d50414aac1e9206c06"},
+    {file = "regex-2023.6.3-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:36efeba71c6539d23c4643be88295ce8c82c88bbd7c65e8a24081d2ca123da3f"},
+    {file = "regex-2023.6.3-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:cf67ca618b4fd34aee78740bea954d7c69fdda419eb208c2c0c7060bb822d747"},
+    {file = "regex-2023.6.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b4598b1897837067a57b08147a68ac026c1e73b31ef6e36deeeb1fa60b2933c9"},
+    {file = "regex-2023.6.3-cp38-cp38-win32.whl", hash = "sha256:f415f802fbcafed5dcc694c13b1292f07fe0befdb94aa8a52905bd115ff41e88"},
+    {file = "regex-2023.6.3-cp38-cp38-win_amd64.whl", hash = "sha256:d4f03bb71d482f979bda92e1427f3ec9b220e62a7dd337af0aa6b47bf4498f72"},
+    {file = "regex-2023.6.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ccf91346b7bd20c790310c4147eee6ed495a54ddb6737162a36ce9dbef3e4751"},
+    {file = "regex-2023.6.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b28f5024a3a041009eb4c333863d7894d191215b39576535c6734cd88b0fcb68"},
+    {file = "regex-2023.6.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e0bb18053dfcfed432cc3ac632b5e5e5c5b7e55fb3f8090e867bfd9b054dbcbf"},
+    {file = "regex-2023.6.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9a5bfb3004f2144a084a16ce19ca56b8ac46e6fd0651f54269fc9e230edb5e4a"},
+    {file = "regex-2023.6.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5c6b48d0fa50d8f4df3daf451be7f9689c2bde1a52b1225c5926e3f54b6a9ed1"},
+    {file = "regex-2023.6.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:051da80e6eeb6e239e394ae60704d2b566aa6a7aed6f2890a7967307267a5dc6"},
+    {file = "regex-2023.6.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a4c3b7fa4cdaa69268748665a1a6ff70c014d39bb69c50fda64b396c9116cf77"},
+    {file = "regex-2023.6.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:457b6cce21bee41ac292d6753d5e94dcbc5c9e3e3a834da285b0bde7aa4a11e9"},
+    {file = "regex-2023.6.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:aad51907d74fc183033ad796dd4c2e080d1adcc4fd3c0fd4fd499f30c03011cd"},
+    {file = "regex-2023.6.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:0385e73da22363778ef2324950e08b689abdf0b108a7d8decb403ad7f5191938"},
+    {file = "regex-2023.6.3-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:c6a57b742133830eec44d9b2290daf5cbe0a2f1d6acee1b3c7b1c7b2f3606df7"},
+    {file = "regex-2023.6.3-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:3e5219bf9e75993d73ab3d25985c857c77e614525fac9ae02b1bebd92f7cecac"},
+    {file = "regex-2023.6.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e5087a3c59eef624a4591ef9eaa6e9a8d8a94c779dade95d27c0bc24650261cd"},
+    {file = "regex-2023.6.3-cp39-cp39-win32.whl", hash = "sha256:20326216cc2afe69b6e98528160b225d72f85ab080cbdf0b11528cbbaba2248f"},
+    {file = "regex-2023.6.3-cp39-cp39-win_amd64.whl", hash = "sha256:bdff5eab10e59cf26bc479f565e25ed71a7d041d1ded04ccf9aee1d9f208487a"},
+    {file = "regex-2023.6.3.tar.gz", hash = "sha256:72d1a25bf36d2050ceb35b517afe13864865268dfb45910e2e17a84be6cbfeb0"},
+]
+
+[[package]]
+name = "requests"
+version = "2.31.0"
+description = "Python HTTP for Humans."
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
     {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
 ]
-safetensors = [
+
+[package.dependencies]
+certifi = ">=2017.4.17"
+charset-normalizer = ">=2,<4"
+idna = ">=2.5,<4"
+urllib3 = ">=1.21.1,<3"
+
+[package.extras]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
+use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
+
+[[package]]
+name = "safetensors"
+version = "0.3.1"
+description = "Fast and Safe Tensor serialization"
+optional = false
+python-versions = "*"
+files = [
     {file = "safetensors-0.3.1-cp310-cp310-macosx_10_11_x86_64.whl", hash = "sha256:2ae9b7dd268b4bae6624729dac86deb82104820e9786429b0583e5168db2f770"},
     {file = "safetensors-0.3.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:08c85c1934682f1e2cd904d38433b53cd2a98245a7cc31f5689f9322a2320bbf"},
     {file = "safetensors-0.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ba625c7af9e1c5d0d91cb83d2fba97d29ea69d4db2015d9714d24c7f6d488e15"},
@@ -1257,7 +1144,25 @@ safetensors = [
     {file = "safetensors-0.3.1-cp39-cp39-win_amd64.whl", hash = "sha256:5f4f614b8e8161cd8a9ca19c765d176a82b122fa3d3387b77862145bfe9b4e93"},
     {file = "safetensors-0.3.1.tar.gz", hash = "sha256:571da56ff8d0bec8ae54923b621cda98d36dcef10feb36fd492c4d0c2cd0e869"},
 ]
-sentencepiece = [
+
+[package.extras]
+all = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (>=2.11.0)", "torch (>=1.10)"]
+dev = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (>=2.11.0)", "torch (>=1.10)"]
+jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)"]
+numpy = ["numpy (>=1.21.6)"]
+paddlepaddle = ["paddlepaddle (>=2.4.1)"]
+quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"]
+tensorflow = ["tensorflow (>=2.11.0)"]
+testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "numpy (>=1.21.6)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)"]
+torch = ["torch (>=1.10)"]
+
+[[package]]
+name = "sentencepiece"
+version = "0.1.99"
+description = "SentencePiece python wrapper"
+optional = false
+python-versions = "*"
+files = [
     {file = "sentencepiece-0.1.99-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0eb528e70571b7c02723e5804322469b82fe7ea418c96051d0286c0fa028db73"},
     {file = "sentencepiece-0.1.99-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:77d7fafb2c4e4659cbdf303929503f37a26eabc4ff31d3a79bf1c5a1b338caa7"},
     {file = "sentencepiece-0.1.99-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:be9cf5b9e404c245aeb3d3723c737ba7a8f5d4ba262ef233a431fa6c45f732a0"},
@@ -1304,15 +1209,44 @@ sentencepiece = [
     {file = "sentencepiece-0.1.99-cp39-cp39-win_amd64.whl", hash = "sha256:350e5c74d739973f1c9643edb80f7cc904dc948578bcb1d43c6f2b173e5d18dd"},
     {file = "sentencepiece-0.1.99.tar.gz", hash = "sha256:189c48f5cb2949288f97ccdb97f0473098d9c3dcf5a3d99d4eabe719ec27297f"},
 ]
-setuptools = [
+
+[[package]]
+name = "setuptools"
+version = "67.8.0"
+description = "Easily download, build, install, upgrade, and uninstall Python packages"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "setuptools-67.8.0-py3-none-any.whl", hash = "sha256:5df61bf30bb10c6f756eb19e7c9f3b473051f48db77fddbe06ff2ca307df9a6f"},
     {file = "setuptools-67.8.0.tar.gz", hash = "sha256:62642358adc77ffa87233bc4d2354c4b2682d214048f500964dbe760ccedf102"},
 ]
-sympy = [
+
+[package.extras]
+docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-hoverxref (<2)", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (==0.8.3)", "sphinx-reredirects", "sphinxcontrib-towncrier"]
+testing = ["build[virtualenv]", "filelock (>=3.4.0)", "flake8-2020", "ini2toml[lite] (>=0.9)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pip (>=19.1)", "pip-run (>=8.8)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-ruff", "pytest-timeout", "pytest-xdist", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
+testing-integration = ["build[virtualenv]", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"]
+
+[[package]]
+name = "sympy"
+version = "1.12"
+description = "Computer algebra system (CAS) in Python"
+optional = true
+python-versions = ">=3.8"
+files = [
     {file = "sympy-1.12-py3-none-any.whl", hash = "sha256:c3588cd4295d0c0f603d0f2ae780587e64e2efeedb3521e46b9bb1d08d184fa5"},
     {file = "sympy-1.12.tar.gz", hash = "sha256:ebf595c8dac3e0fdc4152c51878b498396ec7f30e7a914d6071e674d49420fb8"},
 ]
-tokenizers = [
+
+[package.dependencies]
+mpmath = ">=0.19"
+
+[[package]]
+name = "tokenizers"
+version = "0.13.3"
+description = "Fast and Customizable Tokenizers"
+optional = false
+python-versions = "*"
+files = [
     {file = "tokenizers-0.13.3-cp310-cp310-macosx_10_11_x86_64.whl", hash = "sha256:f3835c5be51de8c0a092058a4d4380cb9244fb34681fd0a295fbf0a52a5fdf33"},
     {file = "tokenizers-0.13.3-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:4ef4c3e821730f2692489e926b184321e887f34fb8a6b80b8096b966ba663d07"},
     {file = "tokenizers-0.13.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c5fd1a6a25353e9aa762e2aae5a1e63883cad9f4e997c447ec39d071020459bc"},
@@ -1354,11 +1288,30 @@ tokenizers = [
     {file = "tokenizers-0.13.3-cp39-cp39-win_amd64.whl", hash = "sha256:bc0a6f1ba036e482db6453571c9e3e60ecd5489980ffd95d11dc9f960483d783"},
     {file = "tokenizers-0.13.3.tar.gz", hash = "sha256:2e546dbb68b623008a5442353137fbb0123d311a6d7ba52f2667c8862a75af2e"},
 ]
-tomli = [
+
+[package.extras]
+dev = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
+docs = ["setuptools-rust", "sphinx", "sphinx-rtd-theme"]
+testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
+
+[[package]]
+name = "tomli"
+version = "2.0.1"
+description = "A lil' TOML parser"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
 ]
-torch = [
+
+[[package]]
+name = "torch"
+version = "2.0.1"
+description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+optional = true
+python-versions = ">=3.8.0"
+files = [
     {file = "torch-2.0.1-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:8ced00b3ba471856b993822508f77c98f48a458623596a4c43136158781e306a"},
     {file = "torch-2.0.1-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:359bfaad94d1cda02ab775dc1cc386d585712329bb47b8741607ef6ef4950747"},
     {file = "torch-2.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:7c84e44d9002182edd859f3400deaa7410f5ec948a519cc7ef512c2f9b34d2c4"},
@@ -1380,27 +1333,175 @@ torch = [
     {file = "torch-2.0.1-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:c62df99352bd6ee5a5a8d1832452110435d178b5164de450831a3a8cc14dc680"},
     {file = "torch-2.0.1-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:671a2565e3f63b8fe8e42ae3e36ad249fe5e567435ea27b94edaa672a7d0c416"},
 ]
-tqdm = [
+
+[package.dependencies]
+filelock = "*"
+jinja2 = "*"
+networkx = "*"
+sympy = "*"
+typing-extensions = "*"
+
+[package.extras]
+opt-einsum = ["opt-einsum (>=3.3)"]
+
+[[package]]
+name = "tqdm"
+version = "4.65.0"
+description = "Fast, Extensible Progress Meter"
+optional = false
+python-versions = ">=3.7"
+files = [
     {file = "tqdm-4.65.0-py3-none-any.whl", hash = "sha256:c4f53a17fe37e132815abceec022631be8ffe1b9381c2e6e30aa70edc99e9671"},
     {file = "tqdm-4.65.0.tar.gz", hash = "sha256:1871fb68a86b8fb3b59ca4cdd3dcccbc7e6d613eeed31f4c332531977b89beb5"},
 ]
-typer = [
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+dev = ["py-make (>=0.1.0)", "twine", "wheel"]
+notebook = ["ipywidgets (>=6)"]
+slack = ["slack-sdk"]
+telegram = ["requests"]
+
+[[package]]
+name = "transformers"
+version = "4.30.2"
+description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
+optional = false
+python-versions = ">=3.7.0"
+files = [
+    {file = "transformers-4.30.2-py3-none-any.whl", hash = "sha256:c332e3a3097f9ed89ce556b403251235931c00237b8bc2d7adaa19d226c13f1d"},
+    {file = "transformers-4.30.2.tar.gz", hash = "sha256:f4a8aac4e1baffab4033f4a345b0d7dc7957d12a4f1ba969afea08205a513045"},
+]
+
+[package.dependencies]
+filelock = "*"
+huggingface-hub = ">=0.14.1,<1.0"
+numpy = ">=1.17"
+packaging = ">=20.0"
+pyyaml = ">=5.1"
+regex = "!=2019.12.17"
+requests = "*"
+safetensors = ">=0.3.1"
+tokenizers = ">=0.11.1,<0.11.3 || >0.11.3,<0.14"
+tqdm = ">=4.27"
+
+[package.extras]
+accelerate = ["accelerate (>=0.20.2)"]
+agents = ["Pillow", "accelerate (>=0.20.2)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch (>=1.9,!=1.12.0)"]
+all = ["Pillow", "accelerate (>=0.20.2)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.6.9)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf (<=3.20.3)", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"]
+audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+codecarbon = ["codecarbon (==1.2.0)"]
+deepspeed = ["accelerate (>=0.20.2)", "deepspeed (>=0.8.3)"]
+deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.20.2)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.8.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf (<=3.20.3)", "psutil", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "timeout-decorator"]
+dev = ["GitPython (<3.1.19)", "Pillow", "accelerate (>=0.20.2)", "av (==9.2.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "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,<=0.6.9)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf (<=3.20.3)", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "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)", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+dev-tensorflow = ["GitPython (<3.1.19)", "Pillow", "beautifulsoup4", "black (>=23.1,<24.0)", "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 (<=3.20.3)", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "urllib3 (<2.0.0)"]
+dev-torch = ["GitPython (<3.1.19)", "Pillow", "accelerate (>=0.20.2)", "beautifulsoup4", "black (>=23.1,<24.0)", "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 (<=3.20.3)", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "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)", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+docs = ["Pillow", "accelerate (>=0.20.2)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.6.9)", "hf-doc-builder", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf (<=3.20.3)", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"]
+docs-specific = ["hf-doc-builder"]
+fairscale = ["fairscale (>0.3)"]
+flax = ["flax (>=0.4.1,<=0.6.9)", "jax (>=0.2.8,!=0.3.2,<=0.3.6)", "jaxlib (>=0.1.65,<=0.3.6)", "optax (>=0.0.8,<=0.1.4)"]
+flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+ftfy = ["ftfy"]
+integrations = ["optuna", "ray[tune]", "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)"]
+modelcreation = ["cookiecutter (==1.7.3)"]
+natten = ["natten (>=0.14.6)"]
+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)", "black (>=23.1,<24.0)", "datasets (!=2.5.0)", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "ruff (>=0.0.241,<=0.0.259)", "urllib3 (<2.0.0)"]
+ray = ["ray[tune]"]
+retrieval = ["datasets (!=2.5.0)", "faiss-cpu"]
+sagemaker = ["sagemaker (>=2.31.0)"]
+sentencepiece = ["protobuf (<=3.20.3)", "sentencepiece (>=0.1.91,!=0.1.92)"]
+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", "black (>=23.1,<24.0)", "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 (<=3.20.3)", "psutil", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "timeout-decorator"]
+tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx"]
+tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.4,<2.13)", "tensorflow-text (<2.13)", "tf2onnx"]
+tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+timm = ["timm"]
+tokenizers = ["tokenizers (>=0.11.1,!=0.11.3,<0.14)"]
+torch = ["accelerate (>=0.20.2)", "torch (>=1.9,!=1.12.0)"]
+torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
+torch-vision = ["Pillow", "torchvision"]
+torchhub = ["filelock", "huggingface-hub (>=0.14.1,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf (<=3.20.3)", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "tqdm (>=4.27)"]
+video = ["av (==9.2.0)", "decord (==0.6.0)"]
+vision = ["Pillow"]
+
+[[package]]
+name = "typer"
+version = "0.6.1"
+description = "Typer, build great CLIs. Easy to code. Based on Python type hints."
+optional = false
+python-versions = ">=3.6"
+files = [
     {file = "typer-0.6.1-py3-none-any.whl", hash = "sha256:54b19e5df18654070a82f8c2aa1da456a4ac16a2a83e6dcd9f170e291c56338e"},
     {file = "typer-0.6.1.tar.gz", hash = "sha256:2d5720a5e63f73eaf31edaa15f6ab87f35f0690f8ca233017d7d23d743a91d73"},
 ]
-typing-extensions = [
-    {file = "typing_extensions-4.6.0-py3-none-any.whl", hash = "sha256:6ad00b63f849b7dcc313b70b6b304ed67b2b2963b3098a33efe18056b1a9a223"},
-    {file = "typing_extensions-4.6.0.tar.gz", hash = "sha256:ff6b238610c747e44c268aa4bb23c8c735d665a63726df3f9431ce707f2aa768"},
+
+[package.dependencies]
+click = ">=7.1.1,<9.0.0"
+
+[package.extras]
+all = ["colorama (>=0.4.3,<0.5.0)", "rich (>=10.11.0,<13.0.0)", "shellingham (>=1.3.0,<2.0.0)"]
+dev = ["autoflake (>=1.3.1,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)", "pre-commit (>=2.17.0,<3.0.0)"]
+doc = ["mdx-include (>=1.4.1,<2.0.0)", "mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)"]
+test = ["black (>=22.3.0,<23.0.0)", "coverage (>=5.2,<6.0)", "isort (>=5.0.6,<6.0.0)", "mypy (==0.910)", "pytest (>=4.4.0,<5.4.0)", "pytest-cov (>=2.10.0,<3.0.0)", "pytest-sugar (>=0.9.4,<0.10.0)", "pytest-xdist (>=1.32.0,<2.0.0)", "rich (>=10.11.0,<13.0.0)", "shellingham (>=1.3.0,<2.0.0)"]
+
+[[package]]
+name = "typing-extensions"
+version = "4.6.3"
+description = "Backported and Experimental Type Hints for Python 3.7+"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "typing_extensions-4.6.3-py3-none-any.whl", hash = "sha256:88a4153d8505aabbb4e13aacb7c486c2b4a33ca3b3f807914a9b4c844c471c26"},
+    {file = "typing_extensions-4.6.3.tar.gz", hash = "sha256:d91d5919357fe7f681a9f2b5b4cb2a5f1ef0a1e9f59c4d8ff0d3491e05c0ffd5"},
 ]
-urllib3 = [
-    {file = "urllib3-2.0.2-py3-none-any.whl", hash = "sha256:d055c2f9d38dc53c808f6fdc8eab7360b6fdbbde02340ed25cfbcd817c62469e"},
-    {file = "urllib3-2.0.2.tar.gz", hash = "sha256:61717a1095d7e155cdb737ac7bb2f4324a858a1e2e6466f6d03ff630ca68d3cc"},
+
+[[package]]
+name = "urllib3"
+version = "2.0.3"
+description = "HTTP library with thread-safe connection pooling, file post, and more."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "urllib3-2.0.3-py3-none-any.whl", hash = "sha256:48e7fafa40319d358848e1bc6809b208340fafe2096f1725d05d67443d0483d1"},
+    {file = "urllib3-2.0.3.tar.gz", hash = "sha256:bee28b5e56addb8226c96f7f13ac28cb4c301dd5ea8a6ca179c0b9835e032825"},
 ]
-win32-setctime = [
+
+[package.extras]
+brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
+secure = ["certifi", "cryptography (>=1.9)", "idna (>=2.0.0)", "pyopenssl (>=17.1.0)", "urllib3-secure-extra"]
+socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
+zstd = ["zstandard (>=0.18.0)"]
+
+[[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"},
 ]
-wrapt = [
+
+[package.extras]
+dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"]
+
+[[package]]
+name = "wrapt"
+version = "1.15.0"
+description = "Module for decorators, wrappers and monkey patching."
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
+files = [
     {file = "wrapt-1.15.0-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:ca1cccf838cd28d5a0883b342474c630ac48cac5df0ee6eacc9c7290f76b11c1"},
     {file = "wrapt-1.15.0-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:e826aadda3cae59295b95343db8f3d965fb31059da7de01ee8d1c40a60398b29"},
     {file = "wrapt-1.15.0-cp27-cp27m-manylinux1_x86_64.whl", hash = "sha256:5fc8e02f5984a55d2c653f5fea93531e9836abbd84342c1d1e17abc4a15084c2"},
@@ -1477,3 +1578,12 @@ wrapt = [
     {file = "wrapt-1.15.0-py3-none-any.whl", hash = "sha256:64b1df0f83706b4ef4cfb4fb0e4c2669100fd7ecacfb59e091fad300d4e04640"},
     {file = "wrapt-1.15.0.tar.gz", hash = "sha256:d06730c6aed78cee4126234cf2d071e01b44b915e725a6cb439a879ec9754a3a"},
 ]
+
+[extras]
+accelerate = ["accelerate"]
+bnb = ["bitsandbytes"]
+
+[metadata]
+lock-version = "2.0"
+python-versions = "^3.9"
+content-hash = "54ecacb32d699cb1298c237c4661c1b707f119cf2c27bd54bad7a1ea2ffb8b10"
diff --git a/server/requirements.txt b/server/requirements.txt
index e8cee52b..a9bd441c 100644
--- a/server/requirements.txt
+++ b/server/requirements.txt
@@ -1,21 +1,21 @@
 backoff==2.2.1 ; python_version >= "3.9" and python_version < "4.0"
-bitsandbytes==0.38.1 ; python_version >= "3.9" and python_version < "4.0"
 certifi==2023.5.7 ; python_version >= "3.9" and python_version < "4.0"
 charset-normalizer==3.1.0 ; python_version >= "3.9" and python_version < "4.0"
 click==8.1.3 ; python_version >= "3.9" and python_version < "4.0"
-colorama==0.4.6 ; python_version >= "3.9" and python_version < "4.0" and sys_platform == "win32" or python_version >= "3.9" and python_version < "4.0" and platform_system == "Windows"
-deprecated==1.2.13 ; python_version >= "3.9" and python_version < "4.0"
-filelock==3.12.0 ; python_version >= "3.9" and python_version < "4.0"
-fsspec==2023.5.0 ; python_version >= "3.9" and python_version < "4.0"
-googleapis-common-protos==1.59.0 ; python_version >= "3.9" and python_version < "4.0"
+colorama==0.4.6 ; python_version >= "3.9" and python_version < "4.0" and (sys_platform == "win32" or platform_system == "Windows")
+deprecated==1.2.14 ; python_version >= "3.9" and python_version < "4.0"
+filelock==3.12.2 ; python_version >= "3.9" and python_version < "4.0"
+fsspec==2023.6.0 ; python_version >= "3.9" and python_version < "4.0"
+googleapis-common-protos==1.59.1 ; python_version >= "3.9" and python_version < "4.0"
 grpc-interceptor==0.15.2 ; python_version >= "3.9" and python_version < "4.0"
-grpcio-reflection==1.55.0 ; python_version >= "3.9" and python_version < "4.0"
-grpcio-status==1.55.0 ; python_version >= "3.9" and python_version < "4.0"
-grpcio==1.55.0 ; python_version >= "3.9" and python_version < "4.0"
+grpcio-reflection==1.54.2 ; python_version >= "3.9" and python_version < "4.0"
+grpcio-status==1.54.2 ; python_version >= "3.9" and python_version < "4.0"
+grpcio==1.54.2 ; python_version >= "3.9" and python_version < "4.0"
 hf-transfer==0.1.3 ; python_version >= "3.9" and python_version < "4.0"
 huggingface-hub==0.14.1 ; python_version >= "3.9" and python_version < "4.0"
-idna==3.4 ; python_version >= "3.9" and python_version < "4"
+idna==3.4 ; python_version >= "3.9" and python_version < "4.0"
 loguru==0.6.0 ; python_version >= "3.9" and python_version < "4.0"
+numpy==1.24.3 ; python_version >= "3.9" and python_version < "4.0"
 opentelemetry-api==1.15.0 ; python_version >= "3.9" and python_version < "4.0"
 opentelemetry-exporter-otlp-proto-grpc==1.15.0 ; python_version >= "3.9" and python_version < "4.0"
 opentelemetry-exporter-otlp-proto-http==1.15.0 ; python_version >= "3.9" and python_version < "4.0"
@@ -26,17 +26,18 @@ opentelemetry-proto==1.15.0 ; python_version >= "3.9" and python_version < "4.0"
 opentelemetry-sdk==1.15.0 ; python_version >= "3.9" and python_version < "4.0"
 opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "4.0"
 packaging==23.1 ; python_version >= "3.9" and python_version < "4.0"
-protobuf==4.23.1 ; python_version >= "3.9" and python_version < "4.0"
+protobuf==4.23.2 ; python_version >= "3.9" and python_version < "4.0"
 pyyaml==6.0 ; python_version >= "3.9" and python_version < "4.0"
+regex==2023.6.3 ; python_version >= "3.9" and python_version < "4.0"
 requests==2.31.0 ; python_version >= "3.9" and python_version < "4.0"
 safetensors==0.3.1 ; python_version >= "3.9" and python_version < "4.0"
 sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "4.0"
 setuptools==67.8.0 ; python_version >= "3.9" and python_version < "4.0"
 tokenizers==0.13.3 ; python_version >= "3.9" and python_version < "4.0"
-transformers==4.29.2 ; python_version >= "3.9" and python_version < "4.0"
 tqdm==4.65.0 ; python_version >= "3.9" and python_version < "4.0"
+transformers==4.30.2 ; python_version >= "3.9" and python_version < "4.0"
 typer==0.6.1 ; python_version >= "3.9" and python_version < "4.0"
-typing-extensions==4.6.0 ; python_version >= "3.9" and python_version < "4.0"
-urllib3==2.0.2 ; python_version >= "3.9" and python_version < "4.0"
+typing-extensions==4.6.3 ; python_version >= "3.9" and python_version < "4.0"
+urllib3==2.0.3 ; python_version >= "3.9" and python_version < "4.0"
 win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "4.0" and sys_platform == "win32"
 wrapt==1.15.0 ; python_version >= "3.9" and python_version < "4.0"
diff --git a/server/text_generation_server/cli.py b/server/text_generation_server/cli.py
index c0e6c2dc..aeb1f13b 100644
--- a/server/text_generation_server/cli.py
+++ b/server/text_generation_server/cli.py
@@ -151,5 +151,37 @@ def download_weights(
         utils.convert_files(local_pt_files, local_st_files)
 
 
+@app.command()
+def quantize(
+    model_id: str,
+    output_dir: str,
+    revision: Optional[str] = None,
+    logger_level: str = "INFO",
+    json_output: bool = False,
+    trust_remote_code: bool = False,
+    upload_to_model_id: Optional[str] = None,
+    percdamp: float = 0.01,
+    act_order: bool = False,
+):
+    download_weights(
+        model_id=model_id,
+        revision=revision,
+        logger_level=logger_level,
+        json_output=json_output,
+    )
+    from text_generation_server.utils.gptq.quantize import quantize
+
+    quantize(
+        model_id=model_id,
+        bits=4,
+        groupsize=128,
+        output_dir=output_dir,
+        trust_remote_code=trust_remote_code,
+        upload_to_model_id=upload_to_model_id,
+        percdamp=percdamp,
+        act_order=act_order,
+    )
+
+
 if __name__ == "__main__":
     app()
diff --git a/server/text_generation_server/models/__init__.py b/server/text_generation_server/models/__init__.py
index 3fdc23b2..2abde685 100644
--- a/server/text_generation_server/models/__init__.py
+++ b/server/text_generation_server/models/__init__.py
@@ -246,6 +246,10 @@ def get_model(
 
     if sharded:
         raise ValueError("sharded is not supported for AutoModel")
+    if quantize == "gptq":
+        raise ValueError(
+            "gptq quantization is not supported for AutoModel, you can try to quantize it with `text-generation-server quantize ORIGINAL_MODEL_ID NEW_MODEL_ID`"
+        )
 
     if model_type in modeling_auto.MODEL_FOR_CAUSAL_LM_MAPPING_NAMES:
         return CausalLM(
diff --git a/server/text_generation_server/models/custom_modeling/flash_neox_modeling.py b/server/text_generation_server/models/custom_modeling/flash_neox_modeling.py
index 3586b85a..9c1020a5 100644
--- a/server/text_generation_server/models/custom_modeling/flash_neox_modeling.py
+++ b/server/text_generation_server/models/custom_modeling/flash_neox_modeling.py
@@ -42,7 +42,8 @@ from text_generation_server.utils.layers import (
 
 
 def load_row(config, prefix: str, weights, bias: bool):
-    weight = weights.get_sharded(f"{prefix}.weight", dim=1)
+    weight = weights.get_multi_weights_row(prefix, quantize=config.quantize)
+
     if bias and weights.process_group.rank() == 0:
         # Rank is only on the first rank process
         bias = weights.get_tensor(f"{prefix}.bias")
@@ -57,19 +58,21 @@ def load_row(config, prefix: str, weights, bias: bool):
 
 
 def load_qkv(config, prefix: str, weights, num_heads, head_size, hidden_size):
-    weight = weights.get_sharded(f"{prefix}.weight", dim=0)
-    bias = weights.get_sharded(f"{prefix}.bias", dim=0)
-
-    weight = (
-        weight.view(
-            num_heads,
-            3,
-            head_size,
-            hidden_size,
+    weight = weights.get_multi_weights_col([prefix], quantize=config.quantize, dim=0)
+    if isinstance(weight, torch.Tensor):
+        # Only on non quantized versions
+        weight = (
+            weight.view(
+                num_heads,
+                3,
+                head_size,
+                hidden_size,
+            )
+            .permute(1, 0, 2, 3)
+            .reshape(-1, hidden_size)
         )
-        .permute(1, 0, 2, 3)
-        .reshape(-1, hidden_size)
-    )
+
+    bias = weights.get_sharded(f"{prefix}.bias", dim=0)
     bias = bias.view(num_heads, 3, head_size).permute(1, 0, 2).reshape(-1)
 
     linear = get_linear(weight, bias, config.quantize)
diff --git a/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py b/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py
index 4a9063eb..fa35c359 100644
--- a/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py
+++ b/server/text_generation_server/models/custom_modeling/flash_rw_modeling.py
@@ -21,7 +21,8 @@ from text_generation_server.utils.layers import (
 
 
 def load_row(config, prefix: str, weights, bias: bool):
-    weight = weights.get_sharded(f"{prefix}.weight", dim=1)
+    weight = weights.get_multi_weights_row(prefix, quantize=config.quantize)
+
     if bias and weights.process_group.rank() == 0:
         # Rank is only on the first rank process
         bias = weights.get_tensor(f"{prefix}.bias")
diff --git a/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py b/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py
index b01d752a..4eb0034d 100644
--- a/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py
+++ b/server/text_generation_server/models/custom_modeling/flash_santacoder_modeling.py
@@ -21,6 +21,81 @@ from text_generation_server.utils.layers import (
 def load_multi_mqa(
     config, prefix: str, weights, bias: bool, head_size, num_heads, hidden_size
 ):
+
+    if config.quantize == "gptq":
+        return _load_multi_mqa_gptq(
+            config, prefix, weights, bias, head_size, num_heads, hidden_size
+        )
+    else:
+        return _load_multi_mqa(
+            config, prefix, weights, bias, head_size, num_heads, hidden_size
+        )
+
+
+def _load_multi_mqa_gptq(
+    config, prefix: str, weights, bias: bool, head_size, num_heads, hidden_size
+):
+    if any("c_attn" in k for k in weights.routing.keys()) and not config.transpose:
+        world_size = weights.process_group.size()
+        rank = weights.process_group.rank()
+
+        slice_ = weights._get_slice(f"{prefix}.c_attn.qweight")
+        shape = slice_.get_shape()
+        block_size = (shape[1] - 2 * head_size) // world_size
+        start = rank * block_size
+        stop = (rank + 1) * block_size
+        assert (shape[1] - 2 * head_size) % world_size == 0
+        q_tensor = slice_[:, start:stop]
+        kv_tensor = slice_[:, -2 * head_size :]
+        qweight = torch.cat([q_tensor, kv_tensor], dim=1)
+
+        slice_ = weights._get_slice(f"{prefix}.c_attn.scales")
+        shape = slice_.get_shape()
+        block_size = (shape[1] - 2 * head_size) // world_size
+        start = rank * block_size
+        stop = (rank + 1) * block_size
+        assert (shape[1] - 2 * head_size) % world_size == 0
+        q_tensor = slice_[:, start:stop]
+        kv_tensor = slice_[:, -2 * head_size :]
+        scales = torch.cat([q_tensor, kv_tensor], dim=1)
+
+        slice_ = weights._get_slice(f"{prefix}.c_attn.qzeros")
+        shape = slice_.get_shape()
+        block_size = (shape[1] - (2 * head_size) * 4 // 32) // world_size
+        start = rank * block_size
+        stop = (rank + 1) * block_size
+        assert 2 * head_size % (32 // 4) == 0
+        q_tensor = slice_[:, start:stop]
+        kv_tensor = slice_[:, -2 * head_size * 4 // 32 :]
+        qzeros = torch.cat([q_tensor, kv_tensor], dim=1)
+
+        g_idx = weights.get_tensor(f"{prefix}.c_attn.g_idx")
+        bits = weights.get_tensor("gptq_bits").item()
+        groupsize = weights.get_tensor("gptq_groupsize").item()
+
+        weight = (qweight, qzeros, scales, g_idx, bits, groupsize)
+
+        if bias:
+            slice_ = weights._get_slice(f"{prefix}.c_attn.bias")
+            shape = slice_.get_shape()
+            block_size = (shape[0] - 2 * head_size) // world_size
+            assert (shape[0] - 2 * head_size) % world_size == 0
+            q_tensor = slice_[start:stop]
+            start = rank * block_size
+            stop = (rank + 1) * block_size
+            q_tensor = slice_[start:stop]
+            kv_tensor = slice_[-2 * head_size :]
+            bias = torch.cat([q_tensor, kv_tensor], dim=0)
+
+        return TensorParallelColumnLinear(get_linear(weight, bias, config.quantize))
+    else:
+        raise NotImplementedError("Gptq loading with santacoder is not implemented")
+
+
+def _load_multi_mqa(
+    config, prefix: str, weights, bias: bool, head_size, num_heads, hidden_size
+):
+
     if any("c_attn" in k for k in weights.routing.keys()):
         slice_ = weights._get_slice(f"{prefix}.c_attn.weight")
         shape = slice_.get_shape()
@@ -92,7 +167,9 @@ def load_col(config, prefix: str, weights, bias: bool):
     if config.transpose:
         weight = weights.get_sharded(f"{prefix}.weight", dim=1).T
     else:
-        weight = weights.get_sharded(f"{prefix}.weight", dim=0)
+        weight = weights.get_multi_weights_col(
+            [prefix], quantize=config.quantize, dim=0
+        )
 
     if bias:
         bias = weights.get_sharded(f"{prefix}.bias", dim=0)
@@ -105,7 +182,7 @@ def load_row(config, prefix: str, weights, bias: bool):
     if config.transpose:
         weight = weights.get_sharded(f"{prefix}.weight", dim=0).T
     else:
-        weight = weights.get_sharded(f"{prefix}.weight", dim=1)
+        weight = weights.get_multi_weights_row(prefix, quantize=config.quantize)
 
     if bias and weights.process_group.rank() == 0:
         # Rank is only on the first rank process
diff --git a/server/text_generation_server/models/flash_llama.py b/server/text_generation_server/models/flash_llama.py
index eb216a20..a80d58cb 100644
--- a/server/text_generation_server/models/flash_llama.py
+++ b/server/text_generation_server/models/flash_llama.py
@@ -3,7 +3,7 @@ import torch.distributed
 
 from opentelemetry import trace
 from transformers import AutoConfig
-from transformers.models.llama import LlamaTokenizer
+from transformers.models.llama import LlamaTokenizer, LlamaTokenizerFast
 from typing import Optional
 
 from text_generation_server.models import FlashCausalLM
@@ -34,13 +34,22 @@ class FlashLlama(FlashCausalLM):
         else:
             raise NotImplementedError("FlashLlama is only available on GPU")
 
-        tokenizer = LlamaTokenizer.from_pretrained(
-            model_id,
-            revision=revision,
-            padding_side="left",
-            truncation_side="left",
-            trust_remote_code=trust_remote_code,
-        )
+        try:
+            tokenizer = LlamaTokenizer.from_pretrained(
+                model_id,
+                revision=revision,
+                padding_side="left",
+                truncation_side="left",
+                trust_remote_code=trust_remote_code,
+            )
+        except Exception:
+            tokenizer = LlamaTokenizerFast.from_pretrained(
+                model_id,
+                revision=revision,
+                padding_side="left",
+                truncation_side="left",
+                trust_remote_code=trust_remote_code,
+            )
 
         config = AutoConfig.from_pretrained(
             model_id, revision=revision, trust_remote_code=trust_remote_code
diff --git a/server/text_generation_server/utils/gptq/custom_autotune.py b/server/text_generation_server/utils/gptq/custom_autotune.py
new file mode 100644
index 00000000..17dff02e
--- /dev/null
+++ b/server/text_generation_server/utils/gptq/custom_autotune.py
@@ -0,0 +1,261 @@
+# https://github.com/fpgaminer/GPTQ-triton
+"""
+Mostly the same as the autotuner in Triton, but with a few changes like using 40 runs instead of 100.
+"""
+
+import builtins
+import math
+import time
+from typing import Dict
+
+import triton
+
+
+class Autotuner(triton.KernelInterface):
+    def __init__(
+        self,
+        fn,
+        arg_names,
+        configs,
+        key,
+        reset_to_zero,
+        prune_configs_by: Dict = None,
+        nearest_power_of_two: bool = False,
+    ):
+        """
+        :param prune_configs_by: a dict of functions that are used to prune configs, fields:
+                'perf_model': performance model used to predicate running time with different configs, returns running time
+                'top_k': number of configs to bench
+                'prune_num_stages_by'(optional): a function used to prune num_stages. It take configs:List[Config] as its input, and returns pruned configs.
+                'nearest_power_of_two'(optional): whether to round key arguments to the nearest power of two when caching tuning results
+        """
+        if not configs:
+            self.configs = [triton.Config({}, num_warps=4, num_stages=2)]
+        else:
+            self.configs = configs
+        self.key_idx = [arg_names.index(k) for k in key]
+        self.nearest_power_of_two = nearest_power_of_two
+        self.cache = {}
+        # hook to reset all required tensor to zeros before relaunching a kernel
+        self.hook = lambda args: 0
+        if reset_to_zero is not None:
+            self.reset_idx = [arg_names.index(k) for k in reset_to_zero]
+
+            def _hook(args):
+                for i in self.reset_idx:
+                    args[i].zero_()
+
+            self.hook = _hook
+        self.arg_names = arg_names
+        # prune configs
+        if prune_configs_by:
+            perf_model, top_k = (
+                prune_configs_by["perf_model"],
+                prune_configs_by["top_k"],
+            )
+            if "early_config_prune" in prune_configs_by:
+                early_config_prune = prune_configs_by["early_config_prune"]
+        else:
+            perf_model, top_k, early_config_prune = None, None, None
+        self.perf_model, self.configs_top_k = perf_model, top_k
+        self.early_config_prune = early_config_prune
+        self.fn = fn
+
+    def _bench(self, *args, config, **meta):
+        # check for conflicts, i.e. meta-parameters both provided
+        # as kwargs and by the autotuner
+        conflicts = meta.keys() & config.kwargs.keys()
+        if conflicts:
+            raise ValueError(
+                f"Conflicting meta-parameters: {', '.join(conflicts)}."
+                " Make sure that you don't re-define auto-tuned symbols."
+            )
+        # augment meta-parameters with tunable ones
+        current = dict(meta, **config.kwargs)
+
+        def kernel_call():
+            if config.pre_hook:
+                config.pre_hook(self.nargs)
+            self.hook(args)
+            self.fn.run(
+                *args,
+                num_warps=config.num_warps,
+                num_stages=config.num_stages,
+                **current,
+            )
+
+        try:
+            # In testings using only 40 reps seems to be close enough and it appears to be what PyTorch uses
+            # PyTorch also sets fast_flush to True, but I didn't see any speedup so I'll leave the default
+            return triton.testing.do_bench(
+                kernel_call, percentiles=(0.5, 0.2, 0.8), rep=40
+            )
+        except triton.compiler.OutOfResources:
+            return (float("inf"), float("inf"), float("inf"))
+
+    def run(self, *args, **kwargs):
+        self.nargs = dict(zip(self.arg_names, args))
+        if len(self.configs) > 1:
+            key = tuple(args[i] for i in self.key_idx)
+
+            # This reduces the amount of autotuning by rounding the keys to the nearest power of two
+            # In my testing this gives decent results, and greatly reduces the amount of tuning required
+            if self.nearest_power_of_two:
+                key = tuple([2 ** int(math.log2(x) + 0.5) for x in key])
+
+            if key not in self.cache:
+                # prune configs
+                pruned_configs = self.prune_configs(kwargs)
+                bench_start = time.time()
+                timings = {
+                    config: self._bench(*args, config=config, **kwargs)
+                    for config in pruned_configs
+                }
+                bench_end = time.time()
+                self.bench_time = bench_end - bench_start
+                self.cache[key] = builtins.min(timings, key=timings.get)
+                self.hook(args)
+                self.configs_timings = timings
+            config = self.cache[key]
+        else:
+            config = self.configs[0]
+        self.best_config = config
+        if config.pre_hook is not None:
+            config.pre_hook(self.nargs)
+        return self.fn.run(
+            *args,
+            num_warps=config.num_warps,
+            num_stages=config.num_stages,
+            **kwargs,
+            **config.kwargs,
+        )
+
+    def prune_configs(self, kwargs):
+        pruned_configs = self.configs
+        if self.early_config_prune:
+            pruned_configs = self.early_config_prune(self.configs, self.nargs)
+        if self.perf_model:
+            top_k = self.configs_top_k
+            if isinstance(top_k, float) and top_k <= 1.0:
+                top_k = int(len(self.configs) * top_k)
+            if len(pruned_configs) > top_k:
+                est_timing = {
+                    config: self.perf_model(
+                        **self.nargs,
+                        **kwargs,
+                        **config.kwargs,
+                        num_stages=config.num_stages,
+                        num_warps=config.num_warps,
+                    )
+                    for config in pruned_configs
+                }
+                pruned_configs = sorted(est_timing.keys(), key=lambda x: est_timing[x])[
+                    :top_k
+                ]
+        return pruned_configs
+
+    def warmup(self, *args, **kwargs):
+        self.nargs = dict(zip(self.arg_names, args))
+        for config in self.prune_configs(kwargs):
+            self.fn.warmup(
+                *args,
+                num_warps=config.num_warps,
+                num_stages=config.num_stages,
+                **kwargs,
+                **config.kwargs,
+            )
+        self.nargs = None
+
+
+def autotune(
+    configs, key, prune_configs_by=None, reset_to_zero=None, nearest_power_of_two=False
+):
+    """
+    Decorator for auto-tuning a :code:`triton.jit`'d function.
+    .. highlight:: python
+    .. code-block:: python
+            @triton.autotune(configs=[
+                    triton.Config(meta={'BLOCK_SIZE': 128}, num_warps=4),
+                    triton.Config(meta={'BLOCK_SIZE': 1024}, num_warps=8),
+                    ],
+                    key=['x_size'] # the two above configs will be evaluated anytime
+                                                    # the value of x_size changes
+            )
+            @triton.jit
+            def kernel(x_ptr, x_size, **META):
+                    BLOCK_SIZE = META['BLOCK_SIZE']
+    :note: When all the configurations are evaluated, the kernel will run multiple time.
+                    This means that whatever value the kernel updates will be updated multiple times.
+                    To avoid this undesired behavior, you can use the `reset_to_zero` argument, which
+                    reset the value of the provided tensor to `zero` before running any configuration.
+    :param configs: a list of :code:`triton.Config` objects
+    :type configs: list[triton.Config]
+    :param key: a list of argument names whose change in value will trigger the evaluation of all provided configs.
+    :type key: list[str]
+    :param prune_configs_by: a dict of functions that are used to prune configs, fields:
+            'perf_model': performance model used to predicate running time with different configs, returns running time
+            'top_k': number of configs to bench
+            'early_config_prune'(optional): a function used to do early prune (eg, num_stages). It take configs:List[Config] as its input, and returns pruned configs.
+    :param reset_to_zero: a list of argument names whose value will be reset to zero before evaluating any configs.
+    :type reset_to_zero: list[str]
+    """
+
+    def decorator(fn):
+        return Autotuner(
+            fn,
+            fn.arg_names,
+            configs,
+            key,
+            reset_to_zero,
+            prune_configs_by,
+            nearest_power_of_two,
+        )
+
+    return decorator
+
+
+def matmul248_kernel_config_pruner(configs, nargs):
+    """
+    The main purpose of this function is to shrink BLOCK_SIZE_* when the corresponding dimension is smaller.
+    """
+    m = max(2 ** int(math.ceil(math.log2(nargs["M"]))), 16)
+    n = max(2 ** int(math.ceil(math.log2(nargs["N"]))), 16)
+    k = max(2 ** int(math.ceil(math.log2(nargs["K"]))), 16)
+
+    used = set()
+    for config in configs:
+        block_size_m = min(m, config.kwargs["BLOCK_SIZE_M"])
+        block_size_n = min(n, config.kwargs["BLOCK_SIZE_N"])
+        block_size_k = min(k, config.kwargs["BLOCK_SIZE_K"])
+        group_size_m = config.kwargs["GROUP_SIZE_M"]
+
+        if (
+            block_size_m,
+            block_size_n,
+            block_size_k,
+            group_size_m,
+            config.num_stages,
+            config.num_warps,
+        ) in used:
+            continue
+
+        used.add(
+            (
+                block_size_m,
+                block_size_n,
+                block_size_k,
+                group_size_m,
+                config.num_stages,
+                config.num_warps,
+            )
+        )
+        yield triton.Config(
+            {
+                "BLOCK_SIZE_M": block_size_m,
+                "BLOCK_SIZE_N": block_size_n,
+                "BLOCK_SIZE_K": block_size_k,
+                "GROUP_SIZE_M": group_size_m,
+            },
+            num_stages=config.num_stages,
+            num_warps=config.num_warps,
+        )
diff --git a/server/text_generation_server/utils/gptq/quant_linear.py b/server/text_generation_server/utils/gptq/quant_linear.py
new file mode 100644
index 00000000..54fa2014
--- /dev/null
+++ b/server/text_generation_server/utils/gptq/quant_linear.py
@@ -0,0 +1,359 @@
+import math
+import numpy as np
+import torch
+import torch.nn as nn
+from torch.cuda.amp import custom_bwd, custom_fwd
+
+try:
+    import triton
+    import triton.language as tl
+    from . import custom_autotune
+
+    # code based https://github.com/fpgaminer/GPTQ-triton
+    @custom_autotune.autotune(
+        configs=[
+            triton.Config(
+                {
+                    "BLOCK_SIZE_M": 64,
+                    "BLOCK_SIZE_N": 256,
+                    "BLOCK_SIZE_K": 32,
+                    "GROUP_SIZE_M": 8,
+                },
+                num_stages=4,
+                num_warps=4,
+            ),
+            triton.Config(
+                {
+                    "BLOCK_SIZE_M": 128,
+                    "BLOCK_SIZE_N": 128,
+                    "BLOCK_SIZE_K": 32,
+                    "GROUP_SIZE_M": 8,
+                },
+                num_stages=4,
+                num_warps=4,
+            ),
+            triton.Config(
+                {
+                    "BLOCK_SIZE_M": 64,
+                    "BLOCK_SIZE_N": 128,
+                    "BLOCK_SIZE_K": 32,
+                    "GROUP_SIZE_M": 8,
+                },
+                num_stages=4,
+                num_warps=4,
+            ),
+            triton.Config(
+                {
+                    "BLOCK_SIZE_M": 128,
+                    "BLOCK_SIZE_N": 32,
+                    "BLOCK_SIZE_K": 32,
+                    "GROUP_SIZE_M": 8,
+                },
+                num_stages=4,
+                num_warps=4,
+            ),
+            triton.Config(
+                {
+                    "BLOCK_SIZE_M": 64,
+                    "BLOCK_SIZE_N": 64,
+                    "BLOCK_SIZE_K": 32,
+                    "GROUP_SIZE_M": 8,
+                },
+                num_stages=4,
+                num_warps=4,
+            ),
+            triton.Config(
+                {
+                    "BLOCK_SIZE_M": 64,
+                    "BLOCK_SIZE_N": 128,
+                    "BLOCK_SIZE_K": 32,
+                    "GROUP_SIZE_M": 8,
+                },
+                num_stages=2,
+                num_warps=8,
+            ),
+            triton.Config(
+                {
+                    "BLOCK_SIZE_M": 64,
+                    "BLOCK_SIZE_N": 64,
+                    "BLOCK_SIZE_K": 64,
+                    "GROUP_SIZE_M": 8,
+                },
+                num_stages=3,
+                num_warps=8,
+            ),
+            triton.Config(
+                {
+                    "BLOCK_SIZE_M": 32,
+                    "BLOCK_SIZE_N": 32,
+                    "BLOCK_SIZE_K": 128,
+                    "GROUP_SIZE_M": 8,
+                },
+                num_stages=2,
+                num_warps=4,
+            ),
+        ],
+        key=["M", "N", "K"],
+        nearest_power_of_two=True,
+        prune_configs_by={
+            "early_config_prune": custom_autotune.matmul248_kernel_config_pruner,
+            "perf_model": None,
+            "top_k": None,
+        },
+    )
+    @triton.jit
+    def matmul_248_kernel(
+        a_ptr,
+        b_ptr,
+        c_ptr,
+        scales_ptr,
+        zeros_ptr,
+        g_ptr,
+        M,
+        N,
+        K,
+        bits,
+        maxq,
+        stride_am,
+        stride_ak,
+        stride_bk,
+        stride_bn,
+        stride_cm,
+        stride_cn,
+        stride_scales,
+        stride_zeros,
+        BLOCK_SIZE_M: tl.constexpr,
+        BLOCK_SIZE_N: tl.constexpr,
+        BLOCK_SIZE_K: tl.constexpr,
+        GROUP_SIZE_M: tl.constexpr,
+    ):
+        """
+        Compute the matrix multiplication C = A x B.
+        A is of shape (M, K) float16
+        B is of shape (K//8, N) int32
+        C is of shape (M, N) float16
+        scales is of shape (G, N) float16
+        zeros is of shape (G, N) float16
+        g_ptr is of shape (K) int32
+        """
+        infearure_per_bits = 32 // bits
+
+        pid = tl.program_id(axis=0)
+        num_pid_m = tl.cdiv(M, BLOCK_SIZE_M)
+        num_pid_n = tl.cdiv(N, BLOCK_SIZE_N)
+        num_pid_k = tl.cdiv(K, BLOCK_SIZE_K)
+        num_pid_in_group = GROUP_SIZE_M * num_pid_n
+        group_id = pid // num_pid_in_group
+        first_pid_m = group_id * GROUP_SIZE_M
+        group_size_m = min(num_pid_m - first_pid_m, GROUP_SIZE_M)
+        pid_m = first_pid_m + (pid % group_size_m)
+        pid_n = (pid % num_pid_in_group) // group_size_m
+
+        offs_am = pid_m * BLOCK_SIZE_M + tl.arange(0, BLOCK_SIZE_M)
+        offs_bn = pid_n * BLOCK_SIZE_N + tl.arange(0, BLOCK_SIZE_N)
+        offs_k = tl.arange(0, BLOCK_SIZE_K)
+        a_ptrs = a_ptr + (
+            offs_am[:, None] * stride_am + offs_k[None, :] * stride_ak
+        )  # (BLOCK_SIZE_M, BLOCK_SIZE_K)
+        a_mask = offs_am[:, None] < M
+        # b_ptrs is set up such that it repeats elements along the K axis 8 times
+        b_ptrs = b_ptr + (
+            (offs_k[:, None] // infearure_per_bits) * stride_bk
+            + offs_bn[None, :] * stride_bn
+        )  # (BLOCK_SIZE_K, BLOCK_SIZE_N)
+        g_ptrs = g_ptr + offs_k
+        # shifter is used to extract the N bits of each element in the 32-bit word from B
+        scales_ptrs = scales_ptr + offs_bn[None, :]
+        zeros_ptrs = zeros_ptr + (offs_bn[None, :] // infearure_per_bits)
+
+        shifter = (offs_k % infearure_per_bits) * bits
+        zeros_shifter = (offs_bn % infearure_per_bits) * bits
+        accumulator = tl.zeros((BLOCK_SIZE_M, BLOCK_SIZE_N), dtype=tl.float32)
+
+        for k in range(0, num_pid_k):
+            g_idx = tl.load(g_ptrs)
+
+            # Fetch scales and zeros; these are per-outfeature and thus reused in the inner loop
+            scales = tl.load(
+                scales_ptrs + g_idx[:, None] * stride_scales
+            )  # (BLOCK_SIZE_K, BLOCK_SIZE_N,)
+            zeros = tl.load(
+                zeros_ptrs + g_idx[:, None] * stride_zeros
+            )  # (BLOCK_SIZE_K, BLOCK_SIZE_N,)
+
+            zeros = (zeros >> zeros_shifter[None, :]) & maxq
+            zeros = zeros + 1
+
+            a = tl.load(a_ptrs, mask=a_mask, other=0.0)  # (BLOCK_SIZE_M, BLOCK_SIZE_K)
+            b = tl.load(b_ptrs)  # (BLOCK_SIZE_K, BLOCK_SIZE_N), but repeated
+
+            # Now we need to unpack b (which is N-bit values) into 32-bit values
+            b = (b >> shifter[:, None]) & maxq  # Extract the N-bit values
+            b = (b - zeros) * scales  # Scale and shift
+
+            accumulator += tl.dot(a, b)
+            a_ptrs += BLOCK_SIZE_K
+            b_ptrs += (BLOCK_SIZE_K // infearure_per_bits) * stride_bk
+            g_ptrs += BLOCK_SIZE_K
+
+        c_ptrs = c_ptr + stride_cm * offs_am[:, None] + stride_cn * offs_bn[None, :]
+        c_mask = (offs_am[:, None] < M) & (offs_bn[None, :] < N)
+        tl.store(c_ptrs, accumulator, mask=c_mask)
+
+except:
+    print("triton not installed.")
+
+
+def matmul248(input, qweight, scales, qzeros, g_idx, bits, maxq):
+    with torch.cuda.device(input.device):
+        output = torch.empty(
+            (input.shape[0], qweight.shape[1]), device=input.device, dtype=torch.float16
+        )
+        grid = lambda META: (
+            triton.cdiv(input.shape[0], META["BLOCK_SIZE_M"])
+            * triton.cdiv(qweight.shape[1], META["BLOCK_SIZE_N"]),
+        )
+        matmul_248_kernel[grid](
+            input,
+            qweight,
+            output,
+            scales,
+            qzeros,
+            g_idx,
+            input.shape[0],
+            qweight.shape[1],
+            input.shape[1],
+            bits,
+            maxq,
+            input.stride(0),
+            input.stride(1),
+            qweight.stride(0),
+            qweight.stride(1),
+            output.stride(0),
+            output.stride(1),
+            scales.stride(0),
+            qzeros.stride(0),
+        )
+        return output
+
+
+class QuantLinearFunction(torch.autograd.Function):
+    @staticmethod
+    @custom_fwd(cast_inputs=torch.float16)
+    def forward(ctx, input, qweight, scales, qzeros, g_idx, bits, maxq):
+        output = matmul248(input, qweight, scales, qzeros, g_idx, bits, maxq)
+        return output
+
+
+class QuantLinear(nn.Module):
+    def __init__(self, qweight, qzeros, scales, g_idx, bias, bits, groupsize):
+        super().__init__()
+        self.register_buffer("qweight", qweight)
+        self.register_buffer("qzeros", qzeros)
+        self.register_buffer("scales", scales)
+        self.register_buffer("g_idx", g_idx)
+        if bias is not None:
+            self.register_buffer("bias", bias)
+        else:
+            self.bias = None
+        if bits not in [2, 4, 8]:
+            raise NotImplementedError("Only 2,4,8 bits are supported.")
+        self.bits = bits
+        self.maxq = 2**self.bits - 1
+        self.groupsize = groupsize
+
+        self.outfeatures = qweight.shape[1]
+        self.infeatures = qweight.shape[0] * 32 // 4
+
+    @classmethod
+    def new(cls, bits, groupsize, infeatures, outfeatures, bias):
+        if bits not in [2, 4, 8]:
+            raise NotImplementedError("Only 2,4,8 bits are supported.")
+
+        qweight = torch.zeros((infeatures // 32 * bits, outfeatures), dtype=torch.int32)
+        qzeros = torch.zeros(
+            (math.ceil(infeatures / groupsize), outfeatures // 32 * bits),
+            dtype=torch.int32,
+        )
+        scales = torch.zeros(
+            (math.ceil(infeatures / groupsize), outfeatures), dtype=torch.float16
+        )
+        g_idx = torch.tensor(
+            [i // groupsize for i in range(infeatures)], dtype=torch.int32
+        )
+        if bias:
+            bias = torch.zeros((outfeatures), dtype=torch.float16)
+        else:
+            bias = None
+        return cls(qweight, qzeros, scales, g_idx, bias, bits, groupsize)
+
+    def pack(self, linear, scales, zeros, g_idx=None):
+        self.g_idx = g_idx.clone() if g_idx is not None else self.g_idx
+
+        scales = scales.t().contiguous()
+        zeros = zeros.t().contiguous()
+        scale_zeros = zeros * scales
+        self.scales = scales.clone().half()
+        if linear.bias is not None:
+            self.bias = linear.bias.clone().half()
+
+        intweight = []
+        for idx in range(self.infeatures):
+            intweight.append(
+                torch.round(
+                    (linear.weight.data[:, idx] + scale_zeros[self.g_idx[idx]])
+                    / self.scales[self.g_idx[idx]]
+                ).to(torch.int)[:, None]
+            )
+        intweight = torch.cat(intweight, dim=1)
+        intweight = intweight.t().contiguous()
+        intweight = intweight.numpy().astype(np.uint32)
+        qweight = np.zeros(
+            (intweight.shape[0] // 32 * self.bits, intweight.shape[1]), dtype=np.uint32
+        )
+        i = 0
+        row = 0
+        while row < qweight.shape[0]:
+            if self.bits in [2, 4, 8]:
+                for j in range(i, i + (32 // self.bits)):
+                    qweight[row] |= intweight[j] << (self.bits * (j - i))
+                i += 32 // self.bits
+                row += 1
+            else:
+                raise NotImplementedError("Only 2,4,8 bits are supported.")
+
+        qweight = qweight.astype(np.int32)
+        self.qweight = torch.from_numpy(qweight)
+
+        zeros -= 1
+        zeros = zeros.numpy().astype(np.uint32)
+        qzeros = np.zeros(
+            (zeros.shape[0], zeros.shape[1] // 32 * self.bits), dtype=np.uint32
+        )
+        i = 0
+        col = 0
+        while col < qzeros.shape[1]:
+            if self.bits in [2, 4, 8]:
+                for j in range(i, i + (32 // self.bits)):
+                    qzeros[:, col] |= zeros[:, j] << (self.bits * (j - i))
+                i += 32 // self.bits
+                col += 1
+            else:
+                raise NotImplementedError("Only 2,4,8 bits are supported.")
+
+        qzeros = qzeros.astype(np.int32)
+        self.qzeros = torch.from_numpy(qzeros)
+
+    def forward(self, x):
+        out_shape = x.shape[:-1] + (self.outfeatures,)
+        out = QuantLinearFunction.apply(
+            x.reshape(-1, x.shape[-1]),
+            self.qweight,
+            self.scales,
+            self.qzeros,
+            self.g_idx,
+            self.bits,
+            self.maxq,
+        )
+        out = out + self.bias if self.bias is not None else out
+        return out.reshape(out_shape)
diff --git a/server/text_generation_server/utils/gptq/quantize.py b/server/text_generation_server/utils/gptq/quantize.py
new file mode 100644
index 00000000..5a4ed8da
--- /dev/null
+++ b/server/text_generation_server/utils/gptq/quantize.py
@@ -0,0 +1,866 @@
+import argparse
+import time
+import numpy as np
+import torch
+import torch.nn as nn
+import math
+import json
+import os
+
+from texttable import Texttable
+from transformers import AutoModelForCausalLM, AutoConfig, AutoTokenizer
+import transformers
+from huggingface_hub import HfApi
+import numpy as np
+import torch
+from text_generation_server.utils.gptq.quant_linear import QuantLinear
+from loguru import logger
+from typing import Optional
+
+DEV = torch.device("cuda:0")
+
+
+class Quantizer(nn.Module):
+    def __init__(self, shape=1):
+        super(Quantizer, self).__init__()
+        self.register_buffer("maxq", torch.tensor(0))
+        self.register_buffer("scale", torch.zeros(shape))
+        self.register_buffer("zero", torch.zeros(shape))
+
+    def configure(
+        self,
+        bits,
+        perchannel=False,
+        sym=True,
+        mse=False,
+        norm=2.4,
+        grid=100,
+        maxshrink=0.8,
+        trits=False,
+    ):
+
+        self.maxq = torch.tensor(2**bits - 1)
+        self.perchannel = perchannel
+        self.sym = sym
+        self.mse = mse
+        self.norm = norm
+        self.grid = grid
+        self.maxshrink = maxshrink
+        if trits:
+            self.maxq = torch.tensor(-1)
+        self.scale = torch.zeros_like(self.scale)
+
+    def _quantize(self, x, scale, zero, maxq):
+        if maxq < 0:
+            return (x > scale / 2).float() * scale + (x < zero / 2).float() * zero
+        q = torch.clamp(torch.round(x / scale) + zero, 0, maxq)
+        return scale * (q - zero)
+
+    def find_params(self, x, weight=False):
+        dev = x.device
+        self.maxq = self.maxq.to(dev)
+
+        shape = x.shape
+        if self.perchannel:
+            if weight:
+                x = x.flatten(1)
+            else:
+                if len(shape) == 4:
+                    x = x.permute([1, 0, 2, 3])
+                    x = x.flatten(1)
+                if len(shape) == 3:
+                    x = x.reshape((-1, shape[-1])).t()
+                if len(shape) == 2:
+                    x = x.t()
+        else:
+            x = x.flatten().unsqueeze(0)
+
+        tmp = torch.zeros(x.shape[0], device=dev)
+        xmin = torch.minimum(x.min(1)[0], tmp)
+        xmax = torch.maximum(x.max(1)[0], tmp)
+
+        if self.sym:
+            xmax = torch.maximum(torch.abs(xmin), xmax)
+            tmp = xmin < 0
+            if torch.any(tmp):
+                xmin[tmp] = -xmax[tmp]
+        tmp = (xmin == 0) & (xmax == 0)
+        xmin[tmp] = -1
+        xmax[tmp] = +1
+
+        if self.maxq < 0:
+            self.scale = xmax
+            self.zero = xmin
+        else:
+            self.scale = (xmax - xmin) / self.maxq
+            if self.sym:
+                self.zero = torch.full_like(self.scale, (self.maxq + 1) / 2)
+            else:
+                self.zero = torch.round(-xmin / self.scale)
+
+        if self.mse:
+            best = torch.full([x.shape[0]], float("inf"), device=dev)
+            for i in range(int(self.maxshrink * self.grid)):
+                p = 1 - i / self.grid
+                xmin1 = p * xmin
+                xmax1 = p * xmax
+                scale1 = (xmax1 - xmin1) / self.maxq
+                zero1 = torch.round(-xmin1 / scale1) if not self.sym else self.zero
+                q = self._quantize(
+                    x, scale1.unsqueeze(1), zero1.unsqueeze(1), self.maxq
+                )
+                q -= x
+                q.abs_()
+                q.pow_(self.norm)
+                err = torch.sum(q, 1)
+                tmp = err < best
+                if torch.any(tmp):
+                    best[tmp] = err[tmp]
+                    self.scale[tmp] = scale1[tmp]
+                    self.zero[tmp] = zero1[tmp]
+        if not self.perchannel:
+            if weight:
+                tmp = shape[0]
+            else:
+                tmp = shape[1] if len(shape) != 3 else shape[2]
+            self.scale = self.scale.repeat(tmp)
+            self.zero = self.zero.repeat(tmp)
+
+        if weight:
+            shape = [-1] + [1] * (len(shape) - 1)
+            self.scale = self.scale.reshape(shape)
+            self.zero = self.zero.reshape(shape)
+            return
+        if len(shape) == 4:
+            self.scale = self.scale.reshape((1, -1, 1, 1))
+            self.zero = self.zero.reshape((1, -1, 1, 1))
+        if len(shape) == 3:
+            self.scale = self.scale.reshape((1, 1, -1))
+            self.zero = self.zero.reshape((1, 1, -1))
+        if len(shape) == 2:
+            self.scale = self.scale.unsqueeze(0)
+            self.zero = self.zero.unsqueeze(0)
+
+    def quantize(self, x):
+        if self.ready():
+            return self._quantize(x, self.scale, self.zero, self.maxq)
+
+        return x
+
+    def enabled(self):
+        return self.maxq > 0
+
+    def ready(self):
+        return torch.all(self.scale != 0)
+
+
+class GPTQ:
+    def __init__(self, layer, observe=False):
+        self.layer = layer
+        self.dev = self.layer.weight.device
+        W = layer.weight.data.clone()
+        if isinstance(self.layer, nn.Conv2d):
+            W = W.flatten(1)
+        if isinstance(self.layer, transformers.Conv1D):
+            W = W.t()
+        self.rows = W.shape[0]
+        self.columns = W.shape[1]
+        self.H = torch.zeros((self.columns, self.columns), device=self.dev)
+        self.nsamples = 0
+        self.quantizer = Quantizer()
+        self.observe = observe
+
+    def add_batch(self, inp, out):
+        # Hessian H = 2 X XT + λ I
+        if self.observe:
+            self.inp1 = inp
+            self.out1 = out
+        else:
+            self.inp1 = None
+            self.out1 = None
+
+        if len(inp.shape) == 2:
+            inp = inp.unsqueeze(0)
+        tmp = inp.shape[0]
+        if isinstance(self.layer, nn.Linear) or isinstance(
+            self.layer, transformers.Conv1D
+        ):
+            if len(inp.shape) == 3:
+                inp = inp.reshape((-1, inp.shape[-1]))
+            inp = inp.t()
+        if isinstance(self.layer, nn.Conv2d):
+            unfold = nn.Unfold(
+                self.layer.kernel_size,
+                dilation=self.layer.dilation,
+                padding=self.layer.padding,
+                stride=self.layer.stride,
+            )
+            inp = unfold(inp)
+            inp = inp.permute([1, 0, 2])
+            inp = inp.flatten(1)
+        self.H *= self.nsamples / (self.nsamples + tmp)
+        self.nsamples += tmp
+        # inp = inp.float()
+        inp = math.sqrt(2 / self.nsamples) * inp.float()
+        # self.H += 2 / self.nsamples * inp.matmul(inp.t())
+        self.H += inp.matmul(inp.t())
+
+    def print_loss(self, name, q_weight, weight_error, timecost):
+        table = Texttable()
+        length = 28
+        name = (
+            (name + " " * (length - len(name)))
+            if len(name) <= length
+            else name[:length]
+        )
+
+        table.header(["name", "weight_error", "fp_inp_SNR", "q_inp_SNR", "time"])
+
+        # assign weight
+        self.layer.weight.data = q_weight.reshape(self.layer.weight.shape).to(
+            self.layer.weight.data.dtype
+        )
+
+        if self.inp1 is not None:
+            # quantize input to int8
+            quantizer = Quantizer()
+            quantizer.configure(8, perchannel=False, sym=True, mse=False)
+            quantizer.find_params(self.inp1)
+            q_in = quantizer.quantize(self.inp1).type(torch.float16)
+            q_out = self.layer(q_in)
+
+            # get kinds of SNR
+            q_SNR = torch_snr_error(q_out, self.out1).item()
+            fp_SNR = torch_snr_error(self.layer(self.inp1), self.out1).item()
+        else:
+            q_SNR = "-"
+            fp_SNR = "-"
+
+        table.add_row([name, weight_error, fp_SNR, q_SNR, timecost])
+        print(table.draw().split("\n")[-2])
+
+    def fasterquant(
+        self, blocksize=128, percdamp=0.01, groupsize=-1, act_order=False, name=""
+    ):
+        self.layer.to(self.dev)
+
+        W = self.layer.weight.data.clone()
+        if isinstance(self.layer, nn.Conv2d):
+            W = W.flatten(1)
+        if isinstance(self.layer, transformers.Conv1D):
+            W = W.t()
+        W = W.float()
+
+        tick = time.time()
+
+        if not self.quantizer.ready():
+            self.quantizer.find_params(W, weight=True)
+
+        H = self.H
+        if not self.observe:
+            del self.H
+        dead = torch.diag(H) == 0
+        H[dead, dead] = 1
+        W[:, dead] = 0
+
+        if act_order:
+            perm = torch.argsort(torch.diag(H), descending=True)
+            W = W[:, perm]
+            H = H[perm][:, perm]
+
+        Losses = torch.zeros_like(W)
+        Q = torch.zeros_like(W)
+
+        damp = percdamp * torch.mean(torch.diag(H))
+        diag = torch.arange(self.columns, device=self.dev)
+        H[diag, diag] += damp
+        H = torch.linalg.cholesky(H)
+        H = torch.cholesky_inverse(H)
+        try:
+            H = torch.linalg.cholesky(H, upper=True)
+        except Exception:
+            # Addition because Falcon fails on h_to_4h
+            H = torch.linalg.cholesky(
+                H + 1e-5 * torch.eye(H.shape[0]).to(H.device), upper=True
+            )
+        Hinv = H
+
+        g_idx = []
+        scale = []
+        zero = []
+        now_idx = 1
+
+        for i1 in range(0, self.columns, blocksize):
+            i2 = min(i1 + blocksize, self.columns)
+            count = i2 - i1
+
+            W1 = W[:, i1:i2].clone()
+            Q1 = torch.zeros_like(W1)
+            Err1 = torch.zeros_like(W1)
+            Losses1 = torch.zeros_like(W1)
+            Hinv1 = Hinv[i1:i2, i1:i2]
+
+            for i in range(count):
+                w = W1[:, i]
+                d = Hinv1[i, i]
+
+                if groupsize != -1:
+                    if (i1 + i) % groupsize == 0:
+                        self.quantizer.find_params(
+                            W[:, (i1 + i) : (i1 + i + groupsize)], weight=True
+                        )
+
+                    if ((i1 + i) // groupsize) - now_idx == -1:
+                        scale.append(self.quantizer.scale)
+                        zero.append(self.quantizer.zero)
+                        now_idx += 1
+
+                q = self.quantizer.quantize(w.unsqueeze(1)).flatten()
+                Q1[:, i] = q
+                Losses1[:, i] = (w - q) ** 2 / d**2
+
+                err1 = (w - q) / d
+                W1[:, i:] -= err1.unsqueeze(1).matmul(Hinv1[i, i:].unsqueeze(0))
+                Err1[:, i] = err1
+
+            Q[:, i1:i2] = Q1
+            Losses[:, i1:i2] = Losses1 / 2
+
+            W[:, i2:] -= Err1.matmul(Hinv[i1:i2, i2:])
+
+        torch.cuda.synchronize()
+        error = torch.sum(Losses).item()
+
+        groupsize = groupsize if groupsize != -1 else self.columns
+        g_idx = [i // groupsize for i in range(self.columns)]
+        g_idx = torch.tensor(g_idx, dtype=torch.int32, device=Q.device)
+        if act_order:
+            invperm = torch.argsort(perm)
+            Q = Q[:, invperm]
+            g_idx = g_idx[invperm]
+
+        if isinstance(self.layer, transformers.Conv1D):
+            Q = Q.t()
+
+        self.print_loss(
+            name=name, q_weight=Q, weight_error=error, timecost=(time.time() - tick)
+        )
+
+        if scale == []:
+            scale.append(self.quantizer.scale)
+            zero.append(self.quantizer.zero)
+        scale = torch.cat(scale, dim=1)
+        zero = torch.cat(zero, dim=1)
+        return scale, zero, g_idx, error
+
+    def free(self):
+        self.inp1 = None
+        self.out1 = None
+        self.H = None
+        self.Losses = None
+        self.Trace = None
+        torch.cuda.empty_cache()
+
+
+def get_wikitext2(nsamples, seed, seqlen, model_id):
+    from datasets import load_dataset
+
+    traindata = load_dataset("wikitext", "wikitext-2-raw-v1", split="train")
+    testdata = load_dataset("wikitext", "wikitext-2-raw-v1", split="test")
+
+    from transformers import AutoTokenizer
+
+    tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)
+    trainenc = tokenizer("\n\n".join(traindata["text"]), return_tensors="pt")
+    testenc = tokenizer("\n\n".join(testdata["text"]), return_tensors="pt")
+
+    import random
+
+    random.seed(seed)
+    trainloader = []
+    for _ in range(nsamples):
+        i = random.randint(0, trainenc.input_ids.shape[1] - seqlen - 1)
+        j = i + seqlen
+        inp = trainenc.input_ids[:, i:j]
+        tar = inp.clone()
+        tar[:, :-1] = -100
+        trainloader.append((inp, tar))
+    return trainloader, testenc
+
+
+def get_ptb(nsamples, seed, seqlen, model_id):
+    from datasets import load_dataset
+
+    traindata = load_dataset("ptb_text_only", "penn_treebank", split="train")
+    valdata = load_dataset("ptb_text_only", "penn_treebank", split="validation")
+
+    from transformers import AutoTokenizer
+
+    try:
+        tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)
+    except:
+        tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
+    trainenc = tokenizer("\n\n".join(traindata["sentence"]), return_tensors="pt")
+    testenc = tokenizer("\n\n".join(valdata["sentence"]), return_tensors="pt")
+
+    import random
+
+    random.seed(seed)
+    trainloader = []
+    for _ in range(nsamples):
+        i = random.randint(0, trainenc.input_ids.shape[1] - seqlen - 1)
+        j = i + seqlen
+        inp = trainenc.input_ids[:, i:j]
+        tar = inp.clone()
+        tar[:, :-1] = -100
+        trainloader.append((inp, tar))
+    return trainloader, testenc
+
+
+def get_c4(nsamples, seed, seqlen, model_id):
+    from datasets import load_dataset
+
+    traindata = load_dataset(
+        "allenai/c4",
+        "allenai--c4",
+        data_files={"train": "en/c4-train.00000-of-01024.json.gz"},
+        split="train",
+        use_auth_token=False,
+    )
+    valdata = load_dataset(
+        "allenai/c4",
+        "allenai--c4",
+        data_files={"validation": "en/c4-validation.00000-of-00008.json.gz"},
+        split="validation",
+        use_auth_token=False,
+    )
+
+    from transformers import AutoTokenizer
+
+    try:
+        tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)
+    except:
+        tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
+
+    import random
+
+    random.seed(seed)
+    trainloader = []
+    for _ in range(nsamples):
+        while True:
+            i = random.randint(0, len(traindata) - 1)
+            trainenc = tokenizer(traindata[i]["text"], return_tensors="pt")
+            if trainenc.input_ids.shape[1] >= seqlen:
+                break
+        i = random.randint(0, trainenc.input_ids.shape[1] - seqlen - 1)
+        j = i + seqlen
+        inp = trainenc.input_ids[:, i:j]
+        tar = inp.clone()
+        tar[:, :-1] = -100
+        trainloader.append((inp, tar))
+
+    import random
+
+    random.seed(0)
+    valenc = []
+    for _ in range(256):
+        while True:
+            i = random.randint(0, len(valdata) - 1)
+            tmp = tokenizer(valdata[i]["text"], return_tensors="pt")
+            if tmp.input_ids.shape[1] >= seqlen:
+                break
+        i = random.randint(0, tmp.input_ids.shape[1] - seqlen - 1)
+        j = i + seqlen
+        valenc.append(tmp.input_ids[:, i:j])
+    valenc = torch.hstack(valenc)
+
+    class TokenizerWrapper:
+        def __init__(self, input_ids):
+            self.input_ids = input_ids
+
+    valenc = TokenizerWrapper(valenc)
+
+    return trainloader, valenc
+
+
+def get_ptb_new(nsamples, seed, seqlen, model_id):
+    from datasets import load_dataset
+
+    traindata = load_dataset("ptb_text_only", "penn_treebank", split="train")
+    testdata = load_dataset("ptb_text_only", "penn_treebank", split="test")
+
+    from transformers import AutoTokenizer
+
+    try:
+        tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)
+    except:
+        tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
+    trainenc = tokenizer(" ".join(traindata["sentence"]), return_tensors="pt")
+    testenc = tokenizer(" ".join(testdata["sentence"]), return_tensors="pt")
+
+    import random
+
+    random.seed(seed)
+    trainloader = []
+    for _ in range(nsamples):
+        i = random.randint(0, trainenc.input_ids.shape[1] - seqlen - 1)
+        j = i + seqlen
+        inp = trainenc.input_ids[:, i:j]
+        tar = inp.clone()
+        tar[:, :-1] = -100
+        trainloader.append((inp, tar))
+    return trainloader, testenc
+
+
+def get_c4_new(nsamples, seed, seqlen, model_id):
+    from datasets import load_dataset
+
+    traindata = load_dataset(
+        "allenai/c4",
+        "allenai--c4",
+        data_files={"train": "en/c4-train.00000-of-01024.json.gz"},
+        split="train",
+    )
+    valdata = load_dataset(
+        "allenai/c4",
+        "allenai--c4",
+        data_files={"validation": "en/c4-validation.00000-of-00008.json.gz"},
+        split="validation",
+    )
+
+    from transformers import AutoTokenizer
+
+    try:
+        tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)
+    except:
+        tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
+
+    import random
+
+    random.seed(seed)
+    trainloader = []
+    for _ in range(nsamples):
+        while True:
+            i = random.randint(0, len(traindata) - 1)
+            trainenc = tokenizer(traindata[i]["text"], return_tensors="pt")
+            if trainenc.input_ids.shape[1] >= seqlen:
+                break
+        i = random.randint(0, trainenc.input_ids.shape[1] - seqlen - 1)
+        j = i + seqlen
+        inp = trainenc.input_ids[:, i:j]
+        tar = inp.clone()
+        tar[:, :-1] = -100
+        trainloader.append((inp, tar))
+
+    valenc = tokenizer(" ".join(valdata[:1100]["text"]), return_tensors="pt")
+    valenc = valenc.input_ids[:, : (256 * seqlen)]
+
+    class TokenizerWrapper:
+        def __init__(self, input_ids):
+            self.input_ids = input_ids
+
+    valenc = TokenizerWrapper(valenc)
+
+    return trainloader, valenc
+
+
+def get_loaders(name, nsamples=128, seed=0, seqlen=2048, model_id=""):
+    if "wikitext2" in name:
+        return get_wikitext2(nsamples, seed, seqlen, model_id)
+    if "ptb" in name:
+        if "new" in name:
+            return get_ptb_new(nsamples, seed, seqlen, model_id)
+        return get_ptb(nsamples, seed, seqlen, model_id)
+    if "c4" in name:
+        if "new" in name:
+            return get_c4_new(nsamples, seed, seqlen, model_id)
+        return get_c4(nsamples, seed, seqlen, model_id)
+
+
+def find_layers(module, layers=(nn.Conv2d, nn.Linear), name=""):
+    # Skip last lm_head linear
+    # Need isintance Falcon is inheriting Linear.
+    if isinstance(module, layers) and "lm_head" not in name:
+        return {name: module}
+    res = {}
+    for name1, child in module.named_children():
+        res.update(
+            find_layers(
+                child, layers=layers, name=name + "." + name1 if name != "" else name1
+            )
+        )
+    return res
+
+
+@torch.no_grad()
+def sequential(
+    model,
+    dataloader,
+    dev,
+    nsamples,
+    bits,
+    groupsize,
+    percdamp=0.01,
+    sym: bool = False,
+    act_order: bool = False,
+):
+    print("Starting ...")
+
+    use_cache = model.config.use_cache
+    model.config.use_cache = False
+    try:
+        layers = model.model.layers
+        prefix = "model.layers"
+    except Exception:
+        layers = model.transformer.h
+        prefix = "transformer.h"
+
+    dtype = next(iter(model.parameters())).dtype
+    inps = torch.zeros(
+        (nsamples, model.seqlen, model.config.hidden_size), dtype=dtype, device=dev
+    )
+
+    cache = {"i": 0}
+    extra = {}
+
+    class Catcher(nn.Module):
+        def __init__(self, module):
+            super().__init__()
+            self.module = module
+
+        def forward(self, inp, **kwargs):
+            inps[cache["i"]] = inp
+            cache["i"] += 1
+            extra.update(kwargs.copy())
+            raise ValueError
+
+    layers[0] = Catcher(layers[0])
+    for batch in dataloader:
+        try:
+            model(batch[0])
+        except ValueError:
+            pass
+    layers[0] = layers[0].module
+
+    # layers[0] = layers[0].cpu()
+    # model.model.embed_tokens = model.model.embed_tokens.cpu()
+    # model.model.norm = model.model.norm.cpu()
+    torch.cuda.empty_cache()
+
+    outs = torch.zeros_like(inps)
+
+    extra = {
+        k: v.to(dev) if isinstance(v, torch.Tensor) else v for k, v in extra.items()
+    }
+
+    print("Ready.")
+
+    quantizers = {}
+    for i in range(len(layers)):
+        print(f"Quantizing layer {i+1}/{len(layers)}..")
+        print("+------------------+--------------+------------+-----------+-------+")
+        print("|       name       | weight_error | fp_inp_SNR | q_inp_SNR | time  |")
+        print("+==================+==============+============+===========+=======+")
+
+        from accelerate.hooks import remove_hook_from_submodules
+
+        layer = layers[i].to(dev)
+        remove_hook_from_submodules(layer)
+        full = find_layers(layer)
+        sequential = [list(full.keys())]
+
+        for names in sequential:
+            subset = {n: full[n] for n in names}
+            gptq = {}
+            for name in subset:
+                gptq[name] = GPTQ(subset[name])
+                gptq[name].quantizer.configure(
+                    bits, perchannel=True, sym=sym, mse=False
+                )
+
+            def add_batch(name):
+                def tmp(_, inp, out):
+                    gptq[name].add_batch(inp[0].data, out.data)
+
+                return tmp
+
+            handles = []
+            for name in subset:
+                handles.append(subset[name].register_forward_hook(add_batch(name)))
+            for j in range(nsamples):
+
+                outs[j] = layer(inps[j].unsqueeze(0), **extra)[0]
+            for h in handles:
+                h.remove()
+
+            for name in subset:
+                scale, zero, g_idx, error = gptq[name].fasterquant(
+                    percdamp=percdamp,
+                    groupsize=groupsize,
+                    act_order=act_order,
+                    name=name,
+                )
+                quantizers[f"{prefix}.{i}.{name}"] = (
+                    gptq[name].quantizer.cpu(),
+                    scale.cpu(),
+                    zero.cpu(),
+                    g_idx.cpu(),
+                    bits,
+                    groupsize,
+                )
+
+                gptq[name].free()
+
+        for j in range(nsamples):
+            outs[j] = layer(inps[j].unsqueeze(0), **extra)[0]
+
+        layers[i] = layer.cpu()
+        del layer
+        del gptq
+        torch.cuda.empty_cache()
+
+        inps, outs = outs, inps
+        print("+------------------+--------------+------------+-----------+-------+")
+        print("\n")
+
+    model.config.use_cache = use_cache
+
+    return quantizers
+
+
+def make_quant_linear(module, names, bits, groupsize, name=""):
+    if isinstance(module, QuantLinear):
+        return
+    for attr in dir(module):
+        tmp = getattr(module, attr)
+        name1 = name + "." + attr if name != "" else attr
+        if name1 in names:
+            delattr(module, attr)
+            setattr(
+                module,
+                attr,
+                QuantLinear.new(
+                    bits,
+                    groupsize,
+                    tmp.in_features,
+                    tmp.out_features,
+                    tmp.bias is not None,
+                ),
+            )
+    for name1, child in module.named_children():
+        make_quant_linear(
+            child, names, bits, groupsize, name + "." + name1 if name != "" else name1
+        )
+
+
+# TODO: perform packing on GPU
+def pack(model, quantizers, bits, groupsize):
+    layers = find_layers(model)
+    layers = {n: layers[n] for n in quantizers}
+    make_quant_linear(model, quantizers, bits, groupsize)
+    qlayers = find_layers(model, (QuantLinear,))
+    print("Packing ...")
+    for name in qlayers:
+        print(name)
+        quantizers[name], scale, zero, g_idx, _, _ = quantizers[name]
+        qlayers[name].pack(layers[name], scale, zero, g_idx)
+    print("Done.")
+    return model
+
+
+def quantize(
+    model_id: str,
+    bits: int,
+    groupsize: int,
+    output_dir: str,
+    trust_remote_code: bool,
+    upload_to_model_id: Optional[str],
+    percdamp: float,
+    act_order: bool,
+):
+    print("loading model")
+    model = AutoModelForCausalLM.from_pretrained(
+        model_id,
+        torch_dtype=torch.float16,
+        device_map="balanced_low_0",
+        trust_remote_code=trust_remote_code,
+    )
+    print("LOADED model")
+    model.seqlen = 2048
+
+    dataset = "wikitext2"
+    nsamples = 128
+    seed = None
+
+    dataloader, testloader = get_loaders(
+        dataset, nsamples=nsamples, seed=seed, model_id=model_id, seqlen=model.seqlen
+    )
+
+    tick = time.time()
+    quantizers = sequential(
+        model,
+        dataloader,
+        DEV,
+        nsamples,
+        bits,
+        groupsize,
+        percdamp=percdamp,
+        act_order=act_order,
+    )
+    print(time.time() - tick)
+
+    pack(model, quantizers, bits, groupsize)
+    from safetensors.torch import save_file
+    from transformers.modeling_utils import shard_checkpoint
+
+    state_dict = model.state_dict()
+    state_dict = {k: v.cpu().contiguous() for k, v in state_dict.items()}
+    state_dict["gptq_bits"] = torch.LongTensor([bits])
+    state_dict["gptq_groupsize"] = torch.LongTensor([groupsize])
+
+    max_shard_size = "10GB"
+    shards, index = shard_checkpoint(
+        state_dict, max_shard_size=max_shard_size, weights_name="model.safetensors"
+    )
+    os.makedirs(output_dir, exist_ok=True)
+    for shard_file, shard in shards.items():
+        save_file(
+            shard,
+            os.path.join(output_dir, shard_file),
+            metadata={
+                "format": "pt",
+                "quantized": "gptq",
+                "origin": "text-generation-inference",
+            },
+        )
+    if index is None:
+        path_to_weights = os.path.join(output_dir, "model.safetensors")
+        logger.info(f"Model weights saved in {path_to_weights}")
+    else:
+        save_index_file = "model.safetensors.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+        logger.info(
+            f"The model is bigger than the maximum size per checkpoint ({max_shard_size}) and is going to be "
+            f"split in {len(shards)} checkpoint shards. You can find where each parameters has been saved in the "
+            f"index located at {save_index_file}."
+        )
+    config = AutoConfig.from_pretrained(model_id, trust_remote_code=trust_remote_code)
+    config.save_pretrained(output_dir)
+    logger.info("Saved config")
+    logger.info("Saving tokenizer")
+    tokenizer = AutoTokenizer.from_pretrained(
+        model_id, trust_remote_code=trust_remote_code
+    )
+    tokenizer.save_pretrained(output_dir)
+    logger.info("Saved tokenizer")
+
+    if upload_to_model_id:
+
+        api = HfApi()
+
+        api.upload_folder(
+            folder_path=output_dir, repo_id=upload_to_model_id, repo_type="model"
+        )
diff --git a/server/text_generation_server/utils/layers.py b/server/text_generation_server/utils/layers.py
index 93865d52..a2b0c739 100644
--- a/server/text_generation_server/utils/layers.py
+++ b/server/text_generation_server/utils/layers.py
@@ -15,6 +15,8 @@ except ImportError:
 
 from accelerate import init_empty_weights
 
+from text_generation_server.utils.gptq.quant_linear import QuantLinear
+
 
 # Monkey patching
 @classmethod
@@ -129,7 +131,22 @@ def get_linear(weight, bias, quantize):
         if bias is not None:
             linear.bias = nn.Parameter(bias)
     elif quantize == "gptq":
-        raise NotImplementedError("Soon")
+        try:
+            qweight, qzeros, scales, g_idx, bits, groupsize = weight
+        except Exception:
+            raise NotImplementedError(
+                f"The passed weight is not `gptq` compatible, loader needs to be updated."
+            )
+
+        linear = QuantLinear(
+            qweight,
+            qzeros,
+            scales,
+            g_idx,
+            bias,
+            bits,
+            groupsize,
+        )
     else:
         raise NotImplementedError(f"Quantization `{quantize}` is not implemented yet.")
     return linear
@@ -152,8 +169,14 @@ class TensorParallelHead(SuperLayer):
     @staticmethod
     def load(config, prefix: str, weights):
         weight = weights.get_sharded(f"{prefix}.weight", dim=0)
+
+        # GPTQ doesn't quantize heads (nor embeddings)
+        if config.quantize == "gptq":
+            quantize = None
+        else:
+            quantize = config.quantize
         return TensorParallelHead(
-            get_linear(weight, bias=None, quantize=config.quantize),
+            get_linear(weight, bias=None, quantize=quantize),
             process_group=weights.process_group,
         )
 
@@ -196,24 +219,21 @@ class TensorParallelHead(SuperLayer):
 class TensorParallelColumnLinear(SuperLayer):
     @classmethod
     def load(cls, config, prefix: str, weights, bias: bool):
-        weight = weights.get_sharded(f"{prefix}.weight", dim=0)
-        if bias:
-            bias = weights.get_sharded(f"{prefix}.bias", dim=0)
-        else:
-            bias = None
-        return cls(get_linear(weight, bias, config.quantize))
+        return cls.load_multi(config, [prefix], weights, bias, dim=0)
 
     @classmethod
     def load_multi(cls, config, prefixes: List[str], weights, bias: bool, dim: int):
-        w = [weights.get_sharded(f"{p}.weight", dim=0) for p in prefixes]
-        weight = torch.cat(w, dim=dim)
+        weight = weights.get_multi_weights_col(
+            prefixes, quantize=config.quantize, dim=dim
+        )
 
         if bias:
             b = [weights.get_sharded(f"{p}.bias", dim=0) for p in prefixes]
-            bias = torch.cat(b, dim=0)
+            bias = torch.cat(b, dim=dim)
         else:
             bias = None
-        return cls(get_linear(weight, bias, config.quantize))
+        linear = get_linear(weight, bias, config.quantize)
+        return cls(linear)
 
 
 class TensorParallelRowLinear(SuperLayer):
@@ -223,7 +243,8 @@ class TensorParallelRowLinear(SuperLayer):
 
     @classmethod
     def load(cls, config, prefix: str, weights, bias: bool):
-        weight = weights.get_sharded(f"{prefix}.weight", dim=1)
+        weight = weights.get_multi_weights_row(prefix, quantize=config.quantize)
+
         if bias and weights.process_group.rank() == 0:
             # Rank is only on the first rank process
             bias = weights.get_tensor(f"{prefix}.bias")
diff --git a/server/text_generation_server/utils/weights.py b/server/text_generation_server/utils/weights.py
index 88347a6a..9d371834 100644
--- a/server/text_generation_server/utils/weights.py
+++ b/server/text_generation_server/utils/weights.py
@@ -1,6 +1,7 @@
 from pathlib import Path
 from typing import List, Dict, Optional
 from safetensors import safe_open
+import torch
 
 
 class Weights:
@@ -54,7 +55,10 @@ class Weights:
         filename, tensor_name = self.get_filename(tensor_name)
         f = self._get_handle(filename)
         tensor = f.get_tensor(tensor_name)
-        tensor = tensor.to(dtype=self.dtype)
+        # Special case for gptq which shouldn't convert
+        # u4 which are disguised as int32
+        if tensor.dtype not in [torch.int32, torch.int64]:
+            tensor = tensor.to(dtype=self.dtype)
         tensor = tensor.to(device=self.device)
         return tensor
 
@@ -80,6 +84,49 @@ class Weights:
             tensor = slice_[:, start:stop]
         else:
             raise NotImplementedError("Let's make that generic when needed")
-        tensor = tensor.to(dtype=self.dtype)
+        # Special case for gptq which shouldn't convert
+        # u4 which are disguised as int32
+        if tensor.dtype != torch.int32:
+            tensor = tensor.to(dtype=self.dtype)
         tensor = tensor.to(device=self.device)
         return tensor
+
+    def get_multi_weights_col(self, prefixes: List[str], quantize: str, dim: int):
+        if quantize == "gptq":
+            try:
+                qweight = torch.cat([self.get_sharded(f"{p}.qweight", dim=1) for p in prefixes], dim=1)
+            except RuntimeError:
+                raise RuntimeError("Cannot load `gptq` weight, make sure the model is already quantized, or quantize it with `text-generation-server quantize ORIGINAL_MODEL_ID NEW_MODEL_ID`")
+
+            qzeros = torch.cat([self.get_sharded(f"{p}.qzeros", dim=1) for p in prefixes], dim=1)
+            scales = torch.cat([self.get_sharded(f"{p}.scales", dim=1) for p in prefixes], dim=1)
+            w = [self.get_tensor(f"{p}.g_idx") for p in prefixes]
+            for w2 in w[1:]:
+                torch.testing.assert_close(w2, w[0])
+            g_idx = w[0]
+
+            bits = self.get_tensor("gptq_bits").item()
+            groupsize = self.get_tensor("gptq_groupsize").item()
+            weight = (qweight, qzeros, scales, g_idx, bits, groupsize)
+        else:
+            w = [self.get_sharded(f"{p}.weight", dim=0) for p in prefixes]
+            weight = torch.cat(w, dim=dim)
+        return weight
+
+    def get_multi_weights_row(self, prefix: str, quantize: str):
+        if quantize == "gptq":
+            try:
+                qweight = self.get_sharded(f"{prefix}.qweight", dim=0)
+            except RuntimeError:
+                raise RuntimeError("Cannot load `gptq` weight, make sure the model is already quantized, or quantize it with `text-generation-server quantize ORIGINAL_MODEL_ID NEW_MODEL_ID`")
+            qzeros = self.get_tensor(f"{prefix}.qzeros")
+            scales = self.get_tensor(f"{prefix}.scales")
+            g_idx = self.get_sharded(f"{prefix}.g_idx", dim=0)
+
+            bits = self.get_tensor("gptq_bits").item()
+            groupsize = self.get_tensor("gptq_groupsize").item()
+
+            weight = (qweight, qzeros, scales, g_idx, bits, groupsize)
+        else:
+            weight = self.get_sharded(f"{prefix}.weight", dim=1)
+        return weight