fix(server): fix hf_transfer issue with private repos (#203)

Dockerfile

@@ -142,6 +142,11 @@ COPY --from=transformers-builder /usr/src/transformers/build/lib.linux-x86_64-cp
 # Install transformers dependencies
 RUN cd /usr/src/transformers && pip install -e . --no-cache-dir && pip install einops --no-cache-dir
 
+# FIXME: remove when we get a release of huggingface-hub
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+        git \
+        && rm -rf /var/lib/apt/lists/*
+
 # Install server
 COPY proto proto
 COPY server server

server/poetry.lock

@@ -122,6 +122,38 @@ python-versions = ">=3.7"
 docs = ["furo (>=2023.3.27)", "sphinx (>=6.1.3)", "sphinx-autodoc-typehints (>=1.22,!=1.23.4)"]
 testing = ["covdefaults (>=2.3)", "coverage (>=7.2.2)", "diff-cover (>=7.5)", "pytest (>=7.2.2)", "pytest-cov (>=4)", "pytest-mock (>=3.10)", "pytest-timeout (>=2.1)"]
 
+[[package]]
+name = "fsspec"
+version = "2023.4.0"
+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"
@@ -207,6 +239,41 @@ category = "main"
 optional = false
 python-versions = ">=3.7"
 
+[[package]]
+name = "huggingface-hub"
+version = "0.14.0.dev0"
+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"
+develop = false
+
+[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.source]
+type = "git"
+url = "https://github.com/huggingface/huggingface_hub.git"
+reference = "4f27b44ee536cd654e171c7f37478eaf1996cc3f"
+resolved_reference = "4f27b44ee536cd654e171c7f37478eaf1996cc3f"
+
 [[package]]
 name = "idna"
 version = "3.4"
@@ -741,6 +808,23 @@ 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 = "triton"
 version = "2.0.0"
@@ -833,7 +917,7 @@ bnb = ["bitsandbytes"]
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.9"
-content-hash = "e05491a03938b79a71b498f2759169f5a41181084158fde5993e7dcb25292cb0"
+content-hash = "97539d3239ab1ab39036679e23af523deb6e28763028bb8331812b03de3a109d"
 
 [metadata.files]
 accelerate = [
@@ -968,6 +1052,10 @@ filelock = [
     {file = "filelock-3.11.0-py3-none-any.whl", hash = "sha256:f08a52314748335c6460fc8fe40cd5638b85001225db78c2aa01c8c0db83b318"},
     {file = "filelock-3.11.0.tar.gz", hash = "sha256:3618c0da67adcc0506b015fd11ef7faf1b493f0b40d87728e19986b536890c37"},
 ]
+fsspec = [
+    {file = "fsspec-2023.4.0-py3-none-any.whl", hash = "sha256:f398de9b49b14e9d84d2c2d11b7b67121bc072fe97b930c4e5668ac3917d8307"},
+    {file = "fsspec-2023.4.0.tar.gz", hash = "sha256:bf064186cd8808f0b2f6517273339ba0a0c8fb1b7048991c28bc67f58b8b67cd"},
+]
 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"},
@@ -1099,6 +1187,7 @@ 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 = []
 idna = [
     {file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
     {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
@@ -1547,6 +1636,10 @@ torch = [
     {file = "torch-2.0.0-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:6e0b97beb037a165669c312591f242382e9109a240e20054d5a5782d9236cad0"},
     {file = "torch-2.0.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:297a4919aff1c0f98a58ebe969200f71350a1d4d4f986dbfd60c02ffce780e99"},
 ]
+tqdm = [
+    {file = "tqdm-4.65.0-py3-none-any.whl", hash = "sha256:c4f53a17fe37e132815abceec022631be8ffe1b9381c2e6e30aa70edc99e9671"},
+    {file = "tqdm-4.65.0.tar.gz", hash = "sha256:1871fb68a86b8fb3b59ca4cdd3dcccbc7e6d613eeed31f4c332531977b89beb5"},
+]
 triton = [
     {file = "triton-2.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:38806ee9663f4b0f7cd64790e96c579374089e58f49aac4a6608121aa55e2505"},
     {file = "triton-2.0.0-1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:226941c7b8595219ddef59a1fdb821e8c744289a132415ddd584facedeb475b1"},

server/pyproject.toml

@@ -25,6 +25,7 @@ opentelemetry-instrumentation-grpc = "^0.36b0"
 hf-transfer = "^0.1.2"
 sentencepiece = "^0.1.97"
 tokenizers = "0.13.3"
+huggingface-hub = {git = "https://github.com/huggingface/huggingface_hub.git", rev = "4f27b44ee536cd654e171c7f37478eaf1996cc3f"}
 
 [tool.poetry.extras]
 bnb = ["bitsandbytes"]