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
| #!/usr/bin/env python3 | |
| """ | |
| Stack 2.9 - Main Entry Point | |
| Launch the Stack 2.9 CLI and agent interface. | |
| """ | |
| import sys | |
| import argparse | |
| from pathlib import Path | |
| # Add directories to path | |
| stack_cli_dir = Path(__file__).parent / "stack_cli" | |
| stack_2_9_cli = Path(__file__).parent / "stack-2-9-cli" | |
| stack_2_9_eval = Path(__file__).parent / "stack-2-9-eval" | |
| stack_2_9_training = Path(__file__).parent / "stack-2-9-training" | |
| paths = [str(stack_cli_dir), str(stack_2_9_cli), str(stack_2_9_eval), str(stack_2_9_training)] | |
| for p in paths: | |
| if Path(p).exists(): | |
| sys.path.insert(0, p) | |
| def main(): | |
| parser = argparse.ArgumentParser(description="Stack 2.9 CLI") | |
| parser.add_argument("--provider", "-p", choices=["ollama", "openai", "anthropic", "together"], | |
| default="ollama", help="Model provider") | |
| parser.add_argument("--model", "-m", type=str, help="Model name") | |
| parser.add_argument("--chat", "-c", action="store_true", help="Start in chat mode") | |
| parser.add_argument("--eval", "-e", choices=["mbpp", "human_eval", "gsm8k", "all"], | |
| help="Run evaluation benchmark") | |
| parser.add_argument("--patterns", action="store_true", help="View pattern statistics") | |
| args = parser.parse_args() | |
| # Try new CLI first, fall back to old | |
| try: | |
| from stack_2_9_cli.main import main as new_main | |
| new_main() | |
| except ImportError: | |
| try: | |
| from stack_cli.cli import main as cli_main | |
| cli_main() | |
| except ImportError as e: | |
| print(f"Error: {e}") | |
| print("Install dependencies: pip install -r requirements.txt") | |
| sys.exit(1) | |
| if __name__ == "__main__": | |
| main() |