Dilshod Tadjibaev

@AdrianEddy #3673 is merged. It also addresses your concert regarding: `indices = Tensor::::from_data` In the PR fix (#3673), the indices are loaded from weights file now. Constant indices are preserved...

Yolov8n works https://github.com/tracel-ai/burn/pull/3750

YOLOv10 model requires scalar topK input and Mod op.

albert/albert-base-v2 model works with this PR fix: https://github.com/tracel-ai/burn/pull/3810 For tch backend on M3 Mac with params: 89,650,188: ``` ======================================== ALBERT Base v2 Burn Model Test ======================================== Initializing ALBERT Base v2...

There is a current limitation in burn-import implementation for large ONNX files (> 2GB). See https://github.com/tracel-ai/burn/issues/3812 That's why [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) can't be supported at the moment.

@a10736, thank you so much for you suggestion and great examples. `rstest_reuse` is a great pointer. I didn't know about it. Continuing with your example, let me clarify. Basically, I...

@la10736 Thank you. I will look into this. Here is the link that takes directly to the repo: https://github.com/la10736/contract_tests_example

> Maybe what you need are contract tests. There's a nice way to implement contract tests that's just work for integration tests. > > Look at [[email protected]](mailto:[email protected]):la10736/contract_tests_example.git and let me...