fxmarty

I meant dtype!

@isaac-chung According to https://github.com/microsoft/onnxruntime/blob/main/docs/OperatorKernels.md you could try to add a cast to `torch.int32` before the operation.

Hi @Yuang-Deng happy to have a look, could you provide a full reproduction? I think your code snippet is truncated.

@bry00 thank you, fixed by https://github.com/huggingface/optimum/pull/1666

Thank you, related to https://github.com/huggingface/optimum/issues/1044 & https://github.com/microsoft/Olive/blob/697948c2a1f7fe938609e1c97060d17f255c322e/olive/passes/onnx/optimum_merging.py#L44-L49 This is a bug in ModelProto.ByteSize() on Windows only. As a workaround, can you try: `python -m optimum.exporters.onnx -m microsoft/phi-2 --library-name transformers ....

@xenova Is bicubic/linear not a config option? If it is not, I am afraid we need to patch indeed. What is the issue exactly? The model not loadable in ORT?

@xenova can you push to this branch so that the CI is rerun?

Thanks! Not sure why we have ``` =========================== short test summary info ============================ FAILED exporters/onnx/test_onnx_export.py::OnnxExportTestCase::test_all_models_tested - AssertionError: Not testing all models. Missing models: {'siglip-text-with-projection', 'siglip-text-model'} ```

Thank you @coolyashas, feel free if you need any help.

@xenova Can you fix ``` FAILED exporters/onnx/test_onnx_export.py::OnnxExportTestCase::test_all_models_tested - AssertionError: Not testing all models. Missing models: {'dit'} 2023-12-24T18:41:32.3343756Z FAILED onnxruntime/test_modeling.py::ORTModelForImageClassificationIntegrationTest::test_pipeline_ort_model_01_dit - KeyError: 'dit' 2023-12-24T18:41:32.3344416Z FAILED onnxruntime/test_modeling.py::ORTModelForImageClassificationIntegrationTest::test_compare_to_transformers_01_dit - KeyError: 'dit' ```