synoema-iot-lite-1.5b-v2
Language 0.1.0-beta.1
Code generator, not a chatbot. Give it an IoT automation task — it outputs Synoema code. Example:
Turn on fan when temperature exceeds 30
Trained on Synoema — a formally verified functional language (GBNF + Hindley-Milner + contracts, prompt to native/WASM/IoT with no human review).
Evaluation
| Metric | Value |
|---|---|
| compile_pass | 97.1% |
| run_pass | 57.7% |
| Eval set | 104 examples |
| Method | greedy (do_sample=False) |
| Language version | 0.1.0-beta.1 |
Quickstart
wget https://huggingface.co/delimitter/synoema-iot-lite-1.5b-v2/resolve/main/synoema-iot-lite-1.5b-v2-q4km.gguf
wget https://huggingface.co/delimitter/synoema-iot-lite-1.5b-v2/resolve/main/Makefile
make pull
make run
make pullsets the system prompt automatically — required for correct behavior.
| Target | Action |
|---|---|
make pull |
Create Ollama model + system prompt |
make run |
Interactive chat |
make clean |
Remove from Ollama |
Example prompts
Turn on fan when temperature exceeds 30
humidity > 80 -> turn on pump on GPIO 22
Turn off lights when no motion for 10 minutes
Open valve when pressure exceeds 150
Model details
| Field | Value |
|---|---|
| Base model | Qwen/Qwen2.5-Coder-1.5B-Instruct |
| Fine-tuning | QLoRA SFT (LoRA r=16) |
| Size | 941 MB Q4_K_M |
| Language version | 0.1.0-beta.1 |
Links
- synoema.tech · docs · iot · all models
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for delimitter/synoema-iot-lite-1.5b-v2
Base model
Qwen/Qwen2.5-1.5B Finetuned
Qwen/Qwen2.5-Coder-1.5B Finetuned
Qwen/Qwen2.5-Coder-1.5B-Instruct