I’m trying a Transformers model (Tacoin/openpi-pi0.5-libero-onnx at main). mx_nc reports Model failed ONNX checker validation, while onnx.checker.check_model('/path/to/model.onnx') does not result in an error. How to fix the issue?
Hi, Thanks for sharing the model details. I looked into it, and this is a very large Transformer-based model, around 6.4 GB. Due to its size, it is not currently supported on the MX3 generation of chips. Sorry about that. Please let us know if you have any other questions. Thanks.