hatch-agent-qwen2.5-1.5b

HatchAgent — Qwen2.5-1.5B (GGUF)

A small language model fine-tuned to turn plain-English instructions into a structured control program for the Arduino UNO Q and its Modulino modules. It runs fully on-device through llama.cpp — no cloud, no API keys, works offline.

This is the model behind HatchAgent: you say "if the knob goes above 60, turn the lights red" and the board does it, with the model running locally on the UNO Q's Qualcomm MPU.

What it does

Given a natural-language instruction, it emits a compact JSON "program" — a small domain-specific language describing effects, conditions, and rules — which a rule engine on the board then executes.

{ "instruction": "blink the lights red really fast",
  "program": { "effect": "blink", "color": "red", "rate": "fast" } }

{ "instruction": "if the knob is between 40 and 60, glow yellow",
  "program": { "rule": { "src": "knob", "op": "between", "lo": 40, "hi": 60 },
               "effect": { "type": "solid", "color": "yellow" } } }

Training

• Base model: Qwen2.5-1.5B-Instruct
• Method: LoRA fine-tuning
• Data: a synthetic dataset of ~2,800 instruction → program pairs covering single commands, sensor-triggered rules, numeric ranges, AND/OR conditions, animations, and saved scenes
• Held-out evaluation: 19/19 correct on unseen paraphrases (never-seen wordings, ranges, boolean logic, scenes)

Usage (llama.cpp)

llama-server -m hatch-q25-1.5b-Q4_K_M.gguf --host 0.0.0.0 --port 8080 -c 2048

Then call the OpenAI-compatible endpoint at http://<host>:8080/v1/chat/completions.

Tip: include chat_template_kwargs: {"enable_thinking": false} in your request — the base model can otherwise spend its turn "thinking" and return empty content.

Files

• hatch-q25-1.5b-Q4_K_M.gguf — Q4_K_M quantization (~0.9 GB), CPU-friendly for edge devices

Intended use

On-device natural-language control of microcontroller hardware (lights, buzzers, sensors). Designed for the Arduino UNO Q + Modulino ecosystem, but the instruction→program pattern is reusable.

License & attribution

Released under Apache-2.0. This is a fine-tune of Qwen2.5-1.5B-Instruct (© Alibaba, Apache-2.0); please retain attribution to the base model.

---

Part of Hatch — making hardware approachable for everyone. 🐣