AI text detector trained on EditLens ICLR 2026 dataset

Remove ONNX files to reduce download size for Spaces

Replace with float32 ONNX (matches PyTorch exactly)

Remove duplicate fp16 file

Add fp16 ONNX (676MB, same accuracy as PyTorch, faster on CPU)

Remove int8 quantized ONNX

Add fp16 ONNX model (676MB, same accuracy as float32)

Remove unquantized ONNX (1.4GB), keep quantized only

AI text detector trained on EditLens ICLR 2026 dataset