Text Generation
Transformers
English
qwen2
code-generation
python
fine-tuning
Qwen
tools
agent-framework
multi-agent
conversational
Eval Results (legacy)
Instructions to use my-ai-stack/Stack-2-9-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use my-ai-stack/Stack-2-9-finetuned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="my-ai-stack/Stack-2-9-finetuned") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("my-ai-stack/Stack-2-9-finetuned") model = AutoModelForCausalLM.from_pretrained("my-ai-stack/Stack-2-9-finetuned") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use my-ai-stack/Stack-2-9-finetuned with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "my-ai-stack/Stack-2-9-finetuned" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
- SGLang
How to use my-ai-stack/Stack-2-9-finetuned with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "my-ai-stack/Stack-2-9-finetuned" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "my-ai-stack/Stack-2-9-finetuned" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "my-ai-stack/Stack-2-9-finetuned", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use my-ai-stack/Stack-2-9-finetuned with Docker Model Runner:
docker model run hf.co/my-ai-stack/Stack-2-9-finetuned
| # Stack 2.9 - Quick Setup Script | |
| # This script sets up the development environment | |
| set -e | |
| echo "π Stack 2.9 Setup" | |
| echo "==================" | |
| echo "" | |
| # Check prerequisites | |
| echo "π¦ Checking prerequisites..." | |
| if ! command -v docker &> /dev/null; then | |
| echo "β Docker is not installed. Please install Docker first." | |
| exit 1 | |
| fi | |
| if ! command -v docker-compose &> /dev/null; then | |
| echo "β Docker Compose is not installed. Please install Docker Compose first." | |
| exit 1 | |
| fi | |
| if ! command -v python3 &> /dev/null; then | |
| echo "β Python 3 is not installed. Please install Python 3.9+." | |
| exit 1 | |
| fi | |
| if ! command -v npm &> /dev/null; then | |
| echo "β οΈ npm is not installed. Some features may not work." | |
| fi | |
| echo "β Prerequisites check passed!" | |
| echo "" | |
| # Install Python dependencies | |
| echo "π Installing Python dependencies..." | |
| pip3 install --upgrade pip | |
| pip3 install -r requirements.txt 2>/dev/null || echo "Note: Some packages may fail on older systems" | |
| # Install training dependencies separately (they're heavy) | |
| echo "" | |
| echo "π€ Installing training dependencies (this may take a while)..." | |
| cd stack-2.9-training | |
| pip3 install -r requirements.txt 2>/dev/null || echo "Note: Unsloth requires CUDA-compatible system" | |
| cd .. | |
| # Install voice dependencies | |
| echo "" | |
| echo "π€ Installing voice dependencies..." | |
| cd stack-2.9-voice | |
| if [ -f requirements.txt ]; then | |
| pip3 install -r requirements.txt 2>/dev/null || echo "Voice dependencies may require additional system libraries" | |
| fi | |
| cd .. | |
| # Create data directories | |
| echo "" | |
| echo "π Creating data directories..." | |
| mkdir -p training-data/code-pairs | |
| mkdir -p stack-2.9-training/data stack-2.9-training/output | |
| mkdir -p stack-2.9-deploy/models | |
| mkdir -p stack-2.9-voice/voice_models | |
| mkdir -p stack-2.9-eval/results | |
| # Verify training data exists | |
| if [ ! -f "training-data/synthetic/examples.jsonl" ]; then | |
| echo "β οΈ Training data not found. Run the data extractor?" | |
| fi | |
| echo "" | |
| echo "β Setup complete!" | |
| echo "" | |
| echo "Next steps:" | |
| echo " 1. Review README.md for architecture overview" | |
| echo " 2. Run 'make train' to start training (requires GPU)" | |
| echo " 3. Run 'make deploy-local' to start vLLM server" | |
| echo " 4. Run 'make voice-up' to start voice service" | |
| echo " 5. Run 'make eval' to evaluate the model" | |
| echo "" | |
| echo "For help: make help" |