Stricter loading of checkpoints

[carmocca]

Strict loading is useful as it enforces that your checkpoint gets loaded as you expect.

In the case of the fine-tuned checkpoints, we can merge them to the pre-trained one before loading so that strict=True can be used.

Additionally, we only set strict=False if quantization is used. This is because of https://github.com/Lightning-AI/lit-parrot/pull/72#issuecomment-1567317405