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", device_map="auto") 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 Settings
- 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
| """Tool registry for Stack 2.9 tools.""" | |
| from __future__ import annotations | |
| from typing import Any | |
| from .base import BaseTool | |
| class ToolRegistry: | |
| """Singleton registry mapping tool names to tool instances.""" | |
| _instance: ToolRegistry | None = None | |
| _tools: dict[str, BaseTool] = {} | |
| def __new__(cls) -> ToolRegistry: | |
| if cls._instance is None: | |
| cls._instance = super().__new__(cls) | |
| cls._tools = {} | |
| return cls._instance | |
| def register(self, tool: BaseTool) -> None: | |
| """Register a tool instance by name.""" | |
| if not tool.name: | |
| raise ValueError("Tool must have a non-empty name") | |
| self._tools[tool.name] = tool | |
| def get(self, name: str) -> BaseTool | None: | |
| """Retrieve a registered tool by name.""" | |
| return self._tools.get(name) | |
| def list(self) -> list[str]: | |
| """List all registered tool names.""" | |
| return list(self._tools.keys()) | |
| def list_tools(self) -> dict[str, dict[str, Any]]: | |
| """List all registered tools with their info. | |
| Returns a dict mapping tool name to info dict with keys: | |
| - name: str | |
| - description: str | |
| - input_schema: dict | |
| """ | |
| result = {} | |
| for name, tool in self._tools.items(): | |
| schema = tool.input_schema | |
| if callable(schema): | |
| schema = schema() | |
| result[name] = { | |
| "name": tool.name, | |
| "description": tool.description, | |
| "input_schema": schema, | |
| } | |
| return result | |
| def call(self, name: str, input_data: dict[str, Any]) -> Any: | |
| """Convenience: get tool and call it in one step.""" | |
| tool = self.get(name) | |
| if tool is None: | |
| raise KeyError(f"Tool not found: {name}") | |
| return tool.call(input_data) | |
| def unregister(self, name: str) -> bool: | |
| """Remove a tool from the registry. Returns True if it existed.""" | |
| if name in self._tools: | |
| del self._tools[name] | |
| return True | |
| return False | |
| def get_registry() -> ToolRegistry: | |
| """Get the global ToolRegistry instance.""" | |
| return ToolRegistry() | |
| # Global registry instance | |
| tool_registry = ToolRegistry() | |