🚀
New: Try the improved
nanoforecast-v03 — 21% better MASE, 6.5M params, 512 context!
1from nanoforecast import NanoForecast
2model = NanoForecast.from_pretrained("eulogik/nanoforecast-500k")
1result = model.predict(context, horizon=48, return_state=True)
2state = result.pop("state")
3for new_val in incoming_data_stream:
4 result = model.predict_step(new_val, state, horizon=48)
5 print(result["forecast"][0, :5])
Perfect for IoT, real-time dashboards, and live financial data.
Upload a CSV → forecast + prediction intervals. No code. No GPU.
1# FastAPI
2pip install nanoforecast fastapi uvicorn python-multipart
3python3 deploy/fastapi_server.py
4
5# ONNX
6pip install "nanoforecast[onnx]"
7python3 -m nanoforecast.export.onnx_export --checkpoint <dir> --output nanoforecast.onnx