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 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
walidsobhie-code
feat: Add remaining RTMP tools (FileRead, FileWrite, Sleep, AskQuestion, Brief, TaskGet, TeamDelete, MCPTool, Worktree, SyntheticOutput)
5dc5419 | """AskUserQuestionTool - Ask user questions interactively for Stack 2.9""" | |
| import json | |
| import uuid | |
| from datetime import datetime | |
| from pathlib import Path | |
| from typing import Any, Dict, List, Optional | |
| from .base import BaseTool, ToolResult | |
| from .registry import tool_registry | |
| QUESTIONS_FILE = Path.home() / ".stack-2.9" / "questions.json" | |
| def _load_questions() -> Dict[str, Any]: | |
| """Load pending questions.""" | |
| QUESTIONS_FILE.parent.mkdir(parents=True, exist_ok=True) | |
| if QUESTIONS_FILE.exists(): | |
| return json.loads(QUESTIONS_FILE.read_text()) | |
| return {"questions": []} | |
| def _save_questions(data: Dict[str, Any]) -> None: | |
| """Save pending questions.""" | |
| QUESTIONS_FILE.write_text(json.dumps(data, indent=2)) | |
| class AskQuestionTool(BaseTool): | |
| """Ask the user a question and wait for response.""" | |
| name = "ask_question" | |
| description = "Ask user a question with optional choices" | |
| input_schema = { | |
| "type": "object", | |
| "properties": { | |
| "question": {"type": "string", "description": "Question to ask"}, | |
| "options": {"type": "array", "items": {"type": "string"}, "description": "Optional choices"}, | |
| "timeout": {"type": "number", "default": 300, "description": "Timeout in seconds"} | |
| }, | |
| "required": ["question"] | |
| } | |
| async def execute(self, question: str, options: Optional[List[str]] = None, timeout: int = 300) -> ToolResult: | |
| """Ask question.""" | |
| data = _load_questions() | |
| q_id = str(uuid.uuid4())[:8] | |
| q_entry = { | |
| "id": q_id, | |
| "question": question, | |
| "options": options, | |
| "status": "pending", | |
| "created_at": datetime.now().isoformat(), | |
| "timeout": timeout | |
| } | |
| data["questions"].append(q_entry) | |
| _save_questions(data) | |
| return ToolResult(success=True, data={ | |
| "question_id": q_id, | |
| "question": question, | |
| "options": options, | |
| "status": "pending", | |
| "note": f"Question {q_id} is pending. Await user response." | |
| }) | |
| class GetPendingQuestionsTool(BaseTool): | |
| """Get all pending questions.""" | |
| name = "get_pending_questions" | |
| description = "List all pending questions" | |
| input_schema = { | |
| "type": "object", | |
| "properties": {}, | |
| "required": [] | |
| } | |
| async def execute(self) -> ToolResult: | |
| """Get pending questions.""" | |
| data = _load_questions() | |
| pending = [q for q in data.get("questions", []) if q.get("status") == "pending"] | |
| return ToolResult(success=True, data={ | |
| "pending_questions": pending, | |
| "count": len(pending) | |
| }) | |
| class AnswerQuestionTool(BaseTool): | |
| """Answer a pending question.""" | |
| name = "answer_question" | |
| description = "Submit an answer to a pending question" | |
| input_schema = { | |
| "type": "object", | |
| "properties": { | |
| "question_id": {"type": "string", "description": "Question ID"}, | |
| "answer": {"type": "string", "description": "Answer"} | |
| }, | |
| "required": ["question_id", "answer"] | |
| } | |
| async def execute(self, question_id: str, answer: str) -> ToolResult: | |
| """Answer question.""" | |
| data = _load_questions() | |
| for q in data.get("questions", []): | |
| if q.get("id") == question_id: | |
| q["status"] = "answered" | |
| q["answer"] = answer | |
| q["answered_at"] = datetime.now().isoformat() | |
| _save_questions(data) | |
| return ToolResult(success=True, data={ | |
| "question_id": question_id, | |
| "answer": answer, | |
| "status": "answered" | |
| }) | |
| return ToolResult(success=False, error=f"Question {question_id} not found") | |
| # Register tools | |
| tool_registry.register(AskQuestionTool()) | |
| tool_registry.register(GetPendingQuestionsTool()) | |
| tool_registry.register(AnswerQuestionTool()) | |