From 6da4195282f55471ea136cf190821256f89b2a5a Mon Sep 17 00:00:00 2001
From: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Date: Fri, 31 Jan 2025 16:16:41 -0800
Subject: [PATCH] Add actual Hugging Face token to CIs (#1214)

### Description

This PR replaces the dummy Hugging Face authentication token with an
actual read-only token.

### Motivation and Context

This fixes the CI failures that are happening. This change is separated
from [this PR](https://github.com/microsoft/onnxruntime-genai/pull/1212)
for clarity in the repo's commit history.
---
 .github/workflows/linux-cpu-x64-build.yml         | 5 +----
 .github/workflows/linux-cpu-x64-nightly-build.yml | 5 +----
 .github/workflows/linux-gpu-x64-build.yml         | 5 +----
 .github/workflows/mac-cpu-arm64-build.yml         | 2 +-
 .github/workflows/win-cpu-x64-build.yml           | 5 +----
 .github/workflows/win-cuda-x64-build.yml          | 5 +----
 6 files changed, 6 insertions(+), 21 deletions(-)

diff --git a/.github/workflows/linux-cpu-x64-build.yml b/.github/workflows/linux-cpu-x64-build.yml
index 5fc97369d..9f0daef4e 100644
--- a/.github/workflows/linux-cpu-x64-build.yml
+++ b/.github/workflows/linux-cpu-x64-build.yml
@@ -10,6 +10,7 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 env:
+  HF_TOKEN: ${{ secrets.HF_TOKEN }}
   ORT_NIGHTLY_REST_API: "https://feeds.dev.azure.com/aiinfra/PublicPackages/_apis/packaging/Feeds/ORT-Nightly/packages?packageNameQuery=Microsoft.ML.OnnxRuntime&api-version=6.0-preview.1"
   ORT_PACKAGE_NAME: "Microsoft.ML.OnnxRuntime"
   ORT_NIGHTLY_SOURCE: "https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/nuget/v3/index.json"
@@ -84,10 +85,6 @@ jobs:
           python3 -m pip install -r test/python/cpu/ort/requirements.txt --user
           python3 -m pip install --user --no-index --no-deps --find-links build/cpu/wheel onnxruntime_genai
 
-      - name: Use Dummy HuggingFace Token
-        run: |
-          echo "HF_TOKEN=12345" >> $GITHUB_ENV
-
       - name: Verify Build Artifacts
         if: always()
         continue-on-error: true
diff --git a/.github/workflows/linux-cpu-x64-nightly-build.yml b/.github/workflows/linux-cpu-x64-nightly-build.yml
index 61be5eb6f..0020c0889 100644
--- a/.github/workflows/linux-cpu-x64-nightly-build.yml
+++ b/.github/workflows/linux-cpu-x64-nightly-build.yml
@@ -12,6 +12,7 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 env:
+  HF_TOKEN: ${{ secrets.HF_TOKEN }}
   ort_dir: "onnxruntime-linux-x64-1.18.0"
   ort_zip: "onnxruntime-linux-x64-1.18.0.tgz"
   ort_url: "https://github.com/microsoft/onnxruntime/releases/download/v1.18.0/onnxruntime-linux-x64-1.18.0.tgz"
@@ -55,10 +56,6 @@ jobs:
           python3 -m pip install -r test/python/cpu/ort/requirements.txt --user
           python3 -m pip install build/cpu/wheel/onnxruntime_genai*.whl --no-deps
 
-      - name: Use Dummy HuggingFace Token
-        run: |
-          echo "HF_TOKEN=12345" >> $GITHUB_ENV
-
       - name: Run the python tests
         run: |
           python3 test/python/test_onnxruntime_genai.py --cwd test/python --test_models test/test_models --e2e
diff --git a/.github/workflows/linux-gpu-x64-build.yml b/.github/workflows/linux-gpu-x64-build.yml
index e5a397a73..ccc93b0f8 100644
--- a/.github/workflows/linux-gpu-x64-build.yml
+++ b/.github/workflows/linux-gpu-x64-build.yml
@@ -12,6 +12,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
+  HF_TOKEN: ${{ secrets.HF_TOKEN }}
   ORT_NIGHTLY_REST_API: "https://feeds.dev.azure.com/aiinfra/PublicPackages/_apis/packaging/Feeds/ORT-Nightly/packages?packageNameQuery=Microsoft.ML.OnnxRuntime.Gpu.Linux&api-version=6.0-preview.1"
   ORT_PACKAGE_NAME: Microsoft.ML.OnnxRuntime.Gpu.Linux
   ORT_NIGHTLY_SOURCE: "https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/nuget/v3/index.json"
@@ -109,10 +110,6 @@ jobs:
             bash -c " \
               /usr/bin/cmake --build --preset linux_gcc_cuda_release"
 
-      - name: Use Dummy HuggingFace Token
-        run: |
-          echo "HF_TOKEN=12345" >> $GITHUB_ENV
-
       - name: Install the onnxruntime-genai Python wheel and run python test
         run: |
           echo "Installing the onnxruntime-genai Python wheel and running the Python tests"
diff --git a/.github/workflows/mac-cpu-arm64-build.yml b/.github/workflows/mac-cpu-arm64-build.yml
index 658f7a660..1adf64a98 100644
--- a/.github/workflows/mac-cpu-arm64-build.yml
+++ b/.github/workflows/mac-cpu-arm64-build.yml
@@ -10,6 +10,7 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 env:
+  HF_TOKEN: ${{ secrets.HF_TOKEN }}
   ORT_NIGHTLY_REST_API: "https://feeds.dev.azure.com/aiinfra/PublicPackages/_apis/packaging/Feeds/ORT-Nightly/packages?packageNameQuery=Microsoft.ML.OnnxRuntime&api-version=6.0-preview.1"
   ORT_PACKAGE_NAME: "Microsoft.ML.OnnxRuntime"
 jobs:
@@ -86,7 +87,6 @@ jobs:
       - name: Run the python tests
         run: |
           source genai-macos-venv/bin/activate
-          export HF_TOKEN="12345"
           export ORTGENAI_LOG_ORT_LIB=1
           python3 -m pip install requests
           python3 test/python/test_onnxruntime_genai.py --cwd test/python --test_models test/test_models
diff --git a/.github/workflows/win-cpu-x64-build.yml b/.github/workflows/win-cpu-x64-build.yml
index 3374a3b6d..3264a465e 100644
--- a/.github/workflows/win-cpu-x64-build.yml
+++ b/.github/workflows/win-cpu-x64-build.yml
@@ -11,6 +11,7 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
   cancel-in-progress: true
 env:
+  HF_TOKEN: ${{ secrets.HF_TOKEN }}
   binaryDir: 'build/cpu/win-x64'
   ORT_NIGHTLY_REST_API: "https://feeds.dev.azure.com/aiinfra/PublicPackages/_apis/packaging/Feeds/ORT-Nightly/packages?packageNameQuery=Microsoft.ML.OnnxRuntime&api-version=6.0-preview.1"
   ORT_PACKAGE_NAME: "Microsoft.ML.OnnxRuntime"
@@ -91,10 +92,6 @@ jobs:
         python3 -m pip install -r test\python\cpu\ort\requirements.txt --user
         python3 -m pip install (Get-ChildItem ("$env:binaryDir\wheel\*.whl")) --no-deps
 
-    - name: Use Dummy HuggingFace Token
-      run: |
-        Add-Content -Path $env:GITHUB_ENV -Value "HF_TOKEN=12345"
-
     - name: Run the Python Tests
       run: |
         python test/python/test_onnxruntime_genai.py --cwd "test\python" --test_models "test\test_models"
diff --git a/.github/workflows/win-cuda-x64-build.yml b/.github/workflows/win-cuda-x64-build.yml
index 5cda163d1..273560b9f 100644
--- a/.github/workflows/win-cuda-x64-build.yml
+++ b/.github/workflows/win-cuda-x64-build.yml
@@ -12,6 +12,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
+  HF_TOKEN: ${{ secrets.HF_TOKEN }}
   AZCOPY_AUTO_LOGIN_TYPE: MSI
   AZCOPY_MSI_CLIENT_ID: 63b63039-6328-442f-954b-5a64d124e5b4
   cuda_dir: "${{ github.workspace }}\\cuda_sdk"
@@ -80,10 +81,6 @@ jobs:
         python -m pip install -r test\python\cuda\ort\requirements.txt
         python -m pip install (Get-ChildItem ("$env:binaryDir\wheel\*.whl")) --no-deps
 
-    - name: Use Dummy HuggingFace Token
-      run: |
-        Add-Content -Path $env:GITHUB_ENV -Value "HF_TOKEN=12345"
-
     - name: Run the Python Tests
       run: |
         python test/python/test_onnxruntime_genai.py --cwd "test\python" --test_models "test\test_models" --e2e