Add pretrained weights for MobileNet v2 and v3

[paulnovo]

This PR adds pretrained weights for MobileNet v2 and MobileNet v3 (both small and large) using the port_torchvision.jl script to generate the weights from torchvision. The PR also fixes MobileNet v3 in Metalhead to match the original paper and torchvision implementation.

Adding pretrained weights checklist

• Train your model or port the weights from another framework.
• Save the model state using BSON.jl with BSON.@save "modelname.bson" model_state=Flux.state(model). It is important that your model is saved under the key model_state.
• Compress the saved model as a tarball using tar -cvzf modelname.tar.gz modelname.bson.
• Obtain the SHAs (see the Pkg docs). Edit the Artifacts.toml file in the Metalhead.jl repository and add entry for your model. You can leave the URL empty for now.
• Open a PR on Metalhead.jl. Be sure to ping a maintainer (e.g. @darsnack or @theabhirath) to let us know that you are adding a pre-trained weight. We will create a model repository on HuggingFace if it does not already exist.
• Open a PR to the corresponding HuggingFace repo. Do this by going to the "Community" tab in the HuggingFace repository. PRs and discussions are shown as the same thing in the HuggingFace web app. You can use your local Git program to make clone the repo and make PRs if you wish. Check out the guide on PRs to HuggingFace for more information.
• Copy the download URL for the model file that you added to HuggingFace. Make sure to grab the URL for a specific commit and not for the main branch.
• Update your Metalhead.jl PR by adding the URL to the Artifacts.toml.
• If the tests pass for your weights, we will merge your PR! Your model should pass the acctest function in the Metalhead.jl test suite. If your model already exists in the repo, then these tests are already in place, and you can add your model configuration to the PRETRAINED_MODELS list in the runtests.jl file. Please refer to the ResNet tests as an example.

[CarloLucibello]

I create an huggingface repo where you can upload the weights
https://huggingface.co/FluxML/mobilenet

[paulnovo]

I create an huggingface repo where you can upload the weights https://huggingface.co/FluxML/mobilenet

Thank you @CarloLucibello, I have uploaded the weights and updated the PR. I think this is good to go, but let me know if anything else is needed.