[Good First Issue][NNCF]: Remove compress_to_fp16=False from examples

[alexsu52]

Context

Using compress_to_fp16=False when saving a compressed/quantized OpenVINO model is no longer required following changes to OpenVINO openvinotoolkit/openvino#23609 that are included in the OpenVINO 2024.1.0 release.

This issue suggests removing compress_to_fp16=False from the examples to simplify the examples.

Example of using compress_to_fp16=False in example:

nncf/examples/post_training_quantization/openvino/mobilenet_v2/main.py

Line 145 in daec271

ov.save_model(ov_quantized_model, int8_ir_path, compress_to_fp16=False)

What needs to be done?

• Removing compress_to_fp16=False attribute when saving a compressed/quantized OpenVINO model in examples
• Check that these changes do not change metrics of the examples. Example tests should pass.

Example Pull Requests

No response

Resources

• Contribution guide - start here!
• Intel DevHub Discord channel - engage in discussions, ask questions and talk to OpenVINO developers
• How to link your Pull Request to an issue

Contact points

@alexsu52

Ticket

ref: 137146

[truhinnm]

Hello, I'm new to contributing, can i take this one? I'd be happy to work on this project!

[alexsu52]

Hello @truhinnm! Thank you for your interest in our project. I assigned to you this issue.

If you have any questions let me know.

[alexsu52]

Thanks for the contribution #2682!