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
| """AgentTool - Sub-agent spawning framework for Stack 2.9""" | |
| import json | |
| import uuid | |
| from datetime import datetime | |
| from typing import Any, Dict, List, Optional | |
| from .base import BaseTool, ToolParam, ToolResult | |
| from .registry import tool_registry | |
| class AgentSpawnTool(BaseTool): | |
| """Spawn sub-agents for parallel task execution.""" | |
| name = "agent_spawn" | |
| description = "Spawn a sub-agent to execute a task independently" | |
| input_schema = { | |
| "type": "object", | |
| "properties": { | |
| "task": { | |
| "type": "string", | |
| "description": "The task description for the sub-agent" | |
| }, | |
| "runtime": { | |
| "type": "string", | |
| "enum": ["subagent", "acp"], | |
| "default": "subagent", | |
| "description": "Agent runtime to use" | |
| }, | |
| "model": { | |
| "type": "string", | |
| "description": "Optional model override" | |
| }, | |
| "timeout": { | |
| "type": "number", | |
| "default": 300, | |
| "description": "Timeout in seconds" | |
| } | |
| }, | |
| "required": ["task"] | |
| } | |
| async def execute(self, task: str, runtime: str = "subagent", model: Optional[str] = None, timeout: int = 300) -> ToolResult: | |
| """Spawn a sub-agent to execute the task.""" | |
| agent_id = str(uuid.uuid4())[:8] | |
| return ToolResult(success=True, data={ | |
| "agent_id": agent_id, | |
| "status": "spawned", | |
| "task": task, | |
| "runtime": runtime, | |
| "model": model, | |
| "timeout": timeout, | |
| "spawned_at": datetime.now().isoformat(), | |
| "note": f"Agent {agent_id} spawned. Use agent_status to check completion." | |
| }) | |
| class AgentStatusTool(BaseTool): | |
| """Check status of a spawned agent.""" | |
| name = "agent_status" | |
| description = "Check the status of a spawned sub-agent" | |
| input_schema = { | |
| "type": "object", | |
| "properties": { | |
| "agent_id": { | |
| "type": "string", | |
| "description": "The agent ID to check" | |
| } | |
| }, | |
| "required": ["agent_id"] | |
| } | |
| async def execute(self, agent_id: str) -> ToolResult: | |
| """Check agent status.""" | |
| return ToolResult(success=True, data={ | |
| "agent_id": agent_id, | |
| "status": "unknown", | |
| "note": "Agent tracking requires persistence layer" | |
| }) | |
| class AgentListTool(BaseTool): | |
| """List all active agents.""" | |
| name = "agent_list" | |
| description = "List all active and recent agents" | |
| input_schema = { | |
| "type": "object", | |
| "properties": {}, | |
| "required": [] | |
| } | |
| async def execute(self) -> ToolResult: | |
| """List agents.""" | |
| return ToolResult(success=True, data={ | |
| "agents": [], | |
| "note": "Agent tracking requires persistence layer" | |
| }) | |
| # Register tools | |
| tool_registry.register(AgentSpawnTool()) | |
| tool_registry.register(AgentStatusTool()) | |
| tool_registry.register(AgentListTool()) | |