Text Generation
Transformers
English
Spanish
iot
smart-home
home-assistant
tool-calling
agent
cybersecurity
devops
ollama
inference-pipeline
autonomous-agent
raspberry-pi
qwen3-coder
Instructions to use MrMoz33/tokioai-coder-iot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MrMoz33/tokioai-coder-iot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MrMoz33/tokioai-coder-iot")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MrMoz33/tokioai-coder-iot", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MrMoz33/tokioai-coder-iot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MrMoz33/tokioai-coder-iot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MrMoz33/tokioai-coder-iot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MrMoz33/tokioai-coder-iot
- SGLang
How to use MrMoz33/tokioai-coder-iot 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 "MrMoz33/tokioai-coder-iot" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MrMoz33/tokioai-coder-iot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "MrMoz33/tokioai-coder-iot" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MrMoz33/tokioai-coder-iot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MrMoz33/tokioai-coder-iot with Docker Model Runner:
docker model run hf.co/MrMoz33/tokioai-coder-iot
Download examples/custom_tools.py from MrMoz33/tokioai-coder-iot: direct link, hf CLI and curl.
- Browser
- Download file 1.04 kB
-
https://huggingface.co/MrMoz33/tokioai-coder-iot/resolve/main/examples/custom_tools.py
- Command line
-
hf download hf://MrMoz33/tokioai-coder-iot/examples/custom_tools.py
-
curl -L -o custom_tools.py https://huggingface.co/MrMoz33/tokioai-coder-iot/resolve/main/examples/custom_tools.py
1.04 kB
| #!/usr/bin/env python3 | |
| """ | |
| TokioAI Engine -- Custom Tools Example | |
| Shows how to add your own tools to the engine. | |
| Modify engine/schemas.py to add tool definitions, | |
| or pass them through the API. | |
| """ | |
| from engine.pipeline import Pipeline, EngineConfig | |
| from engine.schemas import TOOL_DEFINITIONS | |
| # You can inspect the built-in tools | |
| print("Built-in tools:") | |
| for tool in TOOL_DEFINITIONS: | |
| name = tool["function"]["name"] | |
| desc = tool["function"]["description"][:60] | |
| print(f" {name:20s} -- {desc}") | |
| print() | |
| # Use the engine normally -- it already knows all TokioAI tools | |
| config = EngineConfig( | |
| model_name="qwen3-coder", | |
| verbose=True, | |
| ) | |
| engine = Pipeline(config) | |
| # The engine's router will classify this as tool_call | |
| # and the guided generator will constrain output to valid tool names | |
| result = engine.process("search for TODO comments in all python files") | |
| print(f"\nResult: {result}") | |
| if result.tool_calls: | |
| print(f"Tool: {result.tool_calls[0]['name']}") | |
| print(f"Args: {result.tool_calls[0]['arguments']}") | |