Test head-wise compression

[alessiodevoto]

PR description

Some presses perform head-wise compression. To achieve that, we use a patch on the attention function (see attention_patch.py). This PR adds a test that ensures that the cumulative compression ratio corresponds to the expected one.

Side note: I also excluded some files from the .flake8 tests

Checklist

• Tests are working (make test)
• Code is formatted correctly (make style, on errors try fix with make format)
• Copyright header is included
• All commits are signed-off using git commit -s
• (new press) mypress_press.py is in the presses directory
• (new press) MyPress is in __init__.py
• (new press) README.md is updated with a 1 liner about the new press in the Available presses section
• (new press) New press is in the default_presses list in tests/default_presses.py
• (new press) A docstring is provided that follows the same structure as the existing ones

[maxjeblick]

Thanks a lot for the PR; adding this test is really helpful!

I left some comments; IMO adding a new test(file) for head-wise presses improves readability.

[maxjeblick]

Thanks a lot LGTM!