Fix HFTransformers recipe for kv-cache

[KaelanDt]

Before submitting

• Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure to update the docs?
• Did you write any new necessary tests?

What does this PR do?

This fixes an issue when trying to use the HFTransformers recipe when using HF kv-caching option (use_cache=True). The use of partial freezes the model, so history is still set to none when the cache is passed on the next iteration, so the test added in this PR was failing.

PR review

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙃

[t-vi]

Thank you @KaelanDt @k223kim
If it works. Of course, with each iteration, we should probably look at adding a comment (I'm guilty of it, too) describing the magic...