Download quickstart.py from sraivante/tiny-superfast-agentic-MLM-6.5m-v1: direct link, hf CLI and curl.
- Browser
- Download file 1.5 kB
-
https://huggingface.co/sraivante/tiny-superfast-agentic-MLM-6.5m-v1/resolve/main/quickstart.py
- Command line
-
hf download hf://sraivante/tiny-superfast-agentic-MLM-6.5m-v1/quickstart.py
-
curl -L -o quickstart.py https://huggingface.co/sraivante/tiny-superfast-agentic-MLM-6.5m-v1/resolve/main/quickstart.py
1.5 kB
| """Parse commands and show what the sample executor would run. Nothing is executed. | |
| python quickstart.py "volume 40 kar do" "connect to wifi Redmi Note 12 password hello@123" | |
| python quickstart.py # interactive | |
| """ | |
| import json, os, platform, sys | |
| # small matrices: a few BLAS threads are much faster than one per core (see eval/BENCHMARK.md). Must be set before numpy loads. | |
| _threads = "2" if platform.machine().lower() in ("aarch64", "arm64") else "4" | |
| os.environ.setdefault("OPENBLAS_NUM_THREADS", _threads); os.environ.setdefault("OMP_NUM_THREADS", _threads) | |
| HERE = os.path.dirname(os.path.abspath(__file__)) | |
| sys.path.insert(0, os.path.join(HERE, "model")); sys.path.insert(0, os.path.join(HERE, "executor")) | |
| from runtime import CommandModel # noqa: E402 | |
| import executor as EX # noqa: E402 | |
| model = CommandModel(os.path.join(HERE, "model")) | |
| def show(text): | |
| out = model.predict(text); meta = out.pop("_meta") | |
| plan = EX.plan(out, None, text) # None = this machine's platform; text lets it ask about bare GPIO pins | |
| print(json.dumps({"text": text, "command": out, "confidence": meta["confidence"], "latency_ms": meta["latency_ms"], | |
| "risk": plan.risk, "plan": plan.action, "would_run": plan.command or plan.note}, ensure_ascii=False, indent=1)) | |
| if len(sys.argv) > 1: | |
| for t in sys.argv[1:]: show(t) | |
| else: | |
| print("type a command (empty line to quit)") | |
| while True: | |
| t = input("> ").strip() | |
| if not t: break | |
| show(t) | |