docs: feat: add llama2 notebook resources from OSSCA community

[junejae]

What does this PR do?

Adds a notebook resource of LLaMA2 on how to fine-tune LLaMA2 as a Korean text classifier.
The notebook is created by our OSSCA community.
Part of #20055

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue or the forum? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

May you please review this PR?
@bolizabeth, @nuatmochoi, @heuristicwave, @mjk0618, @keonju2, @harheem, @HongB1, @junejae, @54data, @seank021, @augustinLib, @sronger, @TaeYupNoh, @kj021, @eenzeenee

[stevhliu]

Nice, thanks for creating a notebook! 🤗

I wasn't able to get the code in it to run successfully though. I get the following error because I think in your implementation of the TrainingArgument class you have batch_size instead of per_device_train_batch_size?

TypeError: TrainingArguments.__init__() got an unexpected keyword argument 'per_device_train_batch_size'

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint.

[junejae]

Nice, thanks for creating a notebook! 🤗

I wasn't able to get the code in it to run successfully though. I get the following error because I think in your implementation of the TrainingArgument class you have batch_size instead of per_device_train_batch_size?

TypeError: TrainingArguments.__init__() got an unexpected keyword argument 'per_device_train_batch_size'

@stevhliu
It's fixed! Could you try it again?

I messed up my code while polishing some variable names.
I rolled back the change and tested. It works fine now!

[stevhliu]

Cool, it works now; feel free to mark this as ready, and then we can merge!

[stevhliu]

Great work! 🎉