Suggest to use `litgpt chat` after finetuning

[awaelchli]

Our finetuning tutorials end with suggesting to run litgpt generate but no mention of litgpt chat. I believe chatting is a more intuitive suggestion to immediately use and test the model. So I propose to incluce this as the first step after finetuning in our tutorials.

(this would apply to full and lora only at the moment)

Thoughts @rasbt?

We could even print the commands to the terminal after finetuning ends, so the user can copy paste it.

[rasbt]

I agree. I think generate.py is more useful when you want to execute the end-to-end example in a bash script, but for the general tutorials let's use chat.py

[carmocca]

At some point I would like that we merge them. It was originally separate to keep the code complexity low