Skip to content

[Feature] Add qwen2.5 chat templates (#1066) #331

[Feature] Add qwen2.5 chat templates (#1066)

[Feature] Add qwen2.5 chat templates (#1066) #331

# Notebook Tests
# These should only be run on main, because they access secrets
# Not part of the regular CI run, since notebook tests seem
# particularly flaky
name: Notebook Tests
on:
workflow_dispatch:
push:
branches: [main]
schedule:
# * is a special character in YAML so we quote this string
# Run at 0830 UTC every day
- cron: '30 08 * * *'
permissions:
id-token: write
contents: read
jobs:
build:
runs-on: gpu-runner
strategy:
fail-fast: false # Don't cancel all on first failure
matrix:
python-version: ["3.9", "3.10", "3.11", "3.12"]
steps:
- uses: actions/checkout@v4
- name: Install Rust
shell: bash
run: |
curl https://sh.rustup.rs -sSf | sh -s -- -y --default-toolchain 1.75.0
echo "$HOME/.cargo/bin" >> $GITHUB_PATH
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Show GPUs
run: |
nvidia-smi
- name: Update Ubuntu
run: |
sudo apt-get update
sudo apt-get -y upgrade
- name: Ensure NVIDIA SDK available
run: |
sudo apt-get -y install cuda-toolkit
echo "/usr/local/cuda-12.6/bin" >> $GITHUB_PATH
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install pytest
pip install -e .[all,test]
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
- name: GPU pip installs
run: |
pip install accelerate
CMAKE_ARGS="-DGGML_CUDA=on" pip install "llama-cpp-python!=0.2.58,!=0.2.75,!=0.2.84"
- name: Check GPU available
run: |
python -c "import torch; assert torch.cuda.is_available()"
- name: 'Az CLI login'
uses: azure/login@v2
with:
client-id: ${{ secrets.AZURE_CLIENT_ID }}
tenant-id: ${{ secrets.AZURE_TENANT_ID }}
subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
- name: 'Run Azure CLI commands'
run: |
az account show
az group list
- name: Test with pytest
env:
HF_TOKEN: ${{ secrets.HF_TOKEN }}
# Configure endpoints for Azure OpenAI
AZUREAI_CHAT_ENDPOINT: ${{ vars.AZUREAI_CHAT_ENDPOINT }}
AZUREAI_CHAT_MODEL: ${{ vars.AZUREAI_CHAT_MODEL }}
AZUREAI_COMPLETION_ENDPOINT: ${{ vars.AZUREAI_COMPLETION_ENDPOINT }}
AZUREAI_COMPLETION_MODEL: ${{ vars.AZUREAI_COMPLETION_MODEL }}
# Configure endpoints for Azure AI Studio
AZURE_AI_STUDIO_PHI3_ENDPOINT: ${{ vars.AZURE_AI_STUDIO_PHI3_ENDPOINT }}
AZURE_AI_STUDIO_PHI3_DEPLOYMENT: ${{ vars.AZURE_AI_STUDIO_PHI3_DEPLOYMENT }}
AZURE_AI_STUDIO_PHI3_KEY: ${{ secrets.AZURE_AI_STUDIO_PHI3_KEY }}
AZURE_AI_STUDIO_MISTRAL_CHAT_ENDPOINT: ${{ vars.AZURE_AI_STUDIO_MISTRAL_CHAT_ENDPOINT }}
AZURE_AI_STUDIO_MISTRAL_CHAT_DEPLOYMENT: ${{ vars.AZURE_AI_STUDIO_MISTRAL_CHAT_DEPLOYMENT }}
AZURE_AI_STUDIO_MISTRAL_CHAT_KEY: ${{ secrets.AZURE_AI_STUDIO_MISTRAL_CHAT_KEY }}
AZURE_AI_STUDIO_LLAMA3_CHAT_ENDPOINT: ${{ vars.AZURE_AI_STUDIO_LLAMA3_CHAT_ENDPOINT }}
AZURE_AI_STUDIO_LLAMA3_CHAT_DEPLOYMENT: ${{ vars.AZURE_AI_STUDIO_LLAMA3_CHAT_DEPLOYMENT }}
AZURE_AI_STUDIO_LLAMA3_CHAT_KEY: ${{ secrets.AZURE_AI_STUDIO_LLAMA3_CHAT_KEY }}
run: |
pytest --cov=guidance --cov-report=xml --cov-report=term-missing \
-vv \
./tests/notebooks
- name: Upload coverage reports to Codecov
uses: codecov/codecov-action@v4
with:
token: ${{ secrets.CODECOV_TOKEN }}