Export from LightGBM

Save your trained LightGBM model as ONNX, as it is.

pip install onnxmltools onnxruntime

Export

from onnxmltools import convert_lightgbm
from onnxmltools.convert.common.data_types import FloatTensorType

onx = convert_lightgbm(model, initial_types=[("X", FloatTensorType([None, X.shape[1]]))], zipmap=False)
open("model.onnx", "wb").write(onx.SerializeToString())

model is your trained LGBMClassifier or LGBMRegressor, and X your training data. zipmap=False returns probabilities as plain numbers, so PeekML can show them as bars.

Then

Publish model.onnx. PeekML shows one box per feature. To name them and the classes, see Naming your features.