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
walidsobhie-code
feat: Add remaining RTMP tools (FileRead, FileWrite, Sleep, AskQuestion, Brief, TaskGet, TeamDelete, MCPTool, Worktree, SyntheticOutput)
5dc5419 | """SleepTool - Simple delay tool for Stack 2.9""" | |
| import asyncio | |
| import time | |
| from datetime import datetime | |
| from .base import BaseTool, ToolResult | |
| from .registry import tool_registry | |
| class SleepTool(BaseTool): | |
| """Pause execution for a specified duration.""" | |
| name = "sleep" | |
| description = "Pause execution for a specified number of seconds" | |
| input_schema = { | |
| "type": "object", | |
| "properties": { | |
| "seconds": {"type": "number", "description": "Number of seconds to sleep"} | |
| }, | |
| "required": ["seconds"] | |
| } | |
| async def execute(self, seconds: float) -> ToolResult: | |
| """Sleep.""" | |
| if seconds <= 0: | |
| return ToolResult(success=False, error="Seconds must be positive") | |
| if seconds > 3600: | |
| return ToolResult(success=False, error="Maximum sleep is 3600 seconds (1 hour)") | |
| start = time.time() | |
| await asyncio.sleep(seconds) | |
| elapsed = time.time() - start | |
| return ToolResult(success=True, data={ | |
| "requested_seconds": seconds, | |
| "actual_elapsed": elapsed, | |
| "completed_at": datetime.now().isoformat() | |
| }) | |
| class WaitForTool(BaseTool): | |
| """Wait for a condition to become true.""" | |
| name = "wait_for" | |
| description = "Wait for a condition with timeout" | |
| input_schema = { | |
| "type": "object", | |
| "properties": { | |
| "seconds": {"type": "number", "description": "Maximum seconds to wait"}, | |
| "poll_interval": {"type": "number", "default": 1.0, "description": "Seconds between checks"} | |
| }, | |
| "required": ["seconds"] | |
| } | |
| async def execute(self, seconds: float, poll_interval: float = 1.0) -> ToolResult: | |
| """Wait with polling.""" | |
| if seconds <= 0 or poll_interval <= 0: | |
| return ToolResult(success=False, error="All values must be positive") | |
| start = time.time() | |
| elapsed = 0 | |
| while elapsed < seconds: | |
| await asyncio.sleep(min(poll_interval, seconds - elapsed)) | |
| elapsed = time.time() - start | |
| return ToolResult(success=True, data={ | |
| "waited_seconds": seconds, | |
| "actual_elapsed": elapsed, | |
| "timed_out": True | |
| }) | |
| # Register tools | |
| tool_registry.register(SleepTool()) | |
| tool_registry.register(WaitForTool()) | |