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
| .PHONY: help build test push deploy-local clean k8s-install k8s-uninstall | |
| # Default target | |
| help: | |
| @echo "Stack 2.9 Deployment Makefile" | |
| @echo "" | |
| @echo "Usage: make [target]" | |
| @echo "" | |
| @echo "Targets:" | |
| @echo " build Build Docker image" | |
| @echo " test Test local deployment" | |
| @echo " push Push image to registry (set REGISTRY)" | |
| @echo " deploy-local Deploy with docker-compose" | |
| @echo " clean Clean up containers and images" | |
| @echo " k8s-install Install to Kubernetes" | |
| @echo " k8s-uninstall Remove from Kubernetes" | |
| @echo " k8s-logs Show Kubernetes pod logs" | |
| @echo " k8s-status Show Kubernetes resources status" | |
| # Build Docker image | |
| build: | |
| docker build \ | |
| --build-arg PYTHON_VERSION=3.10 \ | |
| --build-arg VLLM_VERSION=0.6.3 \ | |
| --build-arg CUDA_VERSION=12.1.0 \ | |
| -t stack-2.9:latest . | |
| # Test with docker-compose | |
| test: | |
| docker-compose up -d | |
| @echo "Waiting for health check..." | |
| @sleep 60 | |
| @curl -f http://localhost:8000/health && echo "β Server healthy" || echo "β Health check failed" | |
| docker-compose logs stack-2.9 | |
| # Push to registry | |
| push: | |
| ifndef REGISTRY | |
| $(error REGISTRY is not set. Usage: make push REGISTRY=your-registry) | |
| endif | |
| docker tag stack-2.9:latest $(REGISTRY)/stack-2.9:latest | |
| docker tag stack-2.9:latest $(REGISTRY)/stack-2.9:2.9.0 | |
| docker push $(REGISTRY)/stack-2.9:latest | |
| docker push $(REGISTRY)/stack-2.9:2.9.0 | |
| # Deploy locally | |
| deploy-local: build | |
| @echo "Modifying docker-compose.yaml for local deployment..." | |
| @docker-compose up -d | |
| @echo "" | |
| @echo "β Stack 2.9 is starting..." | |
| @echo " API: http://localhost:8000" | |
| @echo " Docs: http://localhost:8000/docs" | |
| @echo "" | |
| @echo "View logs: docker-compose logs -f" | |
| @echo "Stop: docker-compose down" | |
| # Clean up | |
| clean: | |
| docker-compose down -v | |
| docker rmi stack-2.9:latest 2>/dev/null || true | |
| docker system prune -f --volumes | |
| # Kubernetes - Install | |
| k8s-install: | |
| @echo "Creating namespace..." | |
| -kubectl create namespace stack-2-9 | |
| @echo "Creating secrets..." | |
| @if [ -f secrets.yaml ]; then \ | |
| kubectl apply -f secrets.yaml; \ | |
| else \ | |
| echo "Warning: secrets.yaml not found. Create it with your Hugging Face token."; \ | |
| fi | |
| @echo "Applying manifests..." | |
| kubectl apply -f kubernetes/ | |
| @echo "Waiting for deployment..." | |
| @sleep 10 | |
| kubectl wait --for=condition=available --timeout=300s deployment/stack-2.9 -n stack-2-9 | |
| @echo "" | |
| @echo "β Stack 2.9 deployed to Kubernetes" | |
| @echo "Status: kubectl get all -n stack-2-9" | |
| # Kubernetes - Uninstall | |
| k8s-uninstall: | |
| -kubectl delete -f kubernetes/ | |
| -kubectl delete namespace stack-2-9 | |
| @echo "β Stack 2.9 removed from Kubernetes" | |
| # Kubernetes - Status | |
| k8s-status: | |
| kubectl get all,pvc,hpa -n stack-2-9 | |
| # Kubernetes - Logs | |
| k8s-logs: | |
| kubectl logs -f deployment/stack-2.9 -n stack-2-9 | |
| # Quick start | |
| quick-start: build deploy-local | |
| @./deploy.sh local | |