Ella Charlaix

> P.S. I'm still working on extending models coverage, but I think it makes sense to start looking on general API now Very nice, let's merge this PR and we...

Also seems there is an issue for Maskformer for the feature-extraction task ``` FAILED exporters/onnx/test_exporters_onnx_cli.py::OnnxCLIExportTestCase::test_exporters_cli_pytorch_cpu_357_maskformer_feature_extraction_default_hf_internal_testing_tiny_random_MaskFormerForInstanceSegmentation - RuntimeError: number of output names provided (1) exceeded number of outputs (0) ``` the...

Hi @purejomo, I was unfortunately not able to reproduce the error you're describing. Yes `_SENTENCE_TRANSFORMERS_TASKS_TO_MODEL_LOADERS` is defined in https://github.com/huggingface/optimum/blob/v1.21.4/optimum/exporters/tasks.py#L201-L204, could it be that in your case `is_torch_available` https://github.com/huggingface/optimum/blob/v1.21.4/optimum/exporters/tasks.py#L156 returns False?

Hi @michaelfeil, apologies for the delay! If I'm understanding it correctly you'd like to check whether optimum-intel was correctly installed before loading your model with a `OVModelXxx` class ? Something...

@michaelfeil any update on this ?

ITREX was deprecated in : https://github.com/huggingface/optimum-intel/pull/880

One test is failing still but not related to this PR directly, the failing test is for codegen2 coming from `codegen_wrapped_scaled_dot_product` after https://github.com/huggingface/optimum/pull/2023/commits/9fa9e9fc3ebd4ca719ac88aa06942cf6ae1da2d8 in optimum that was added to match...

cc @jiqing-feng who might have some insight on this

The generation parameters included in the model's config will be moved to the generation_config in https://github.com/huggingface/optimum-intel/pull/902 which should fix this issue

> @echarlaix thanks for confirmation and better solution! Could you please provide info when it is planned to be ready to merge? Couple of tests failing still requiring fixes, but...