Can you please point me to good resources on fine tuning? Thanks.

Check out https://github.com/OpenAccess-AI-Collective/axolotl

Search for articles showing you code for fine-tuning Llama 2, ideally including a colab notebook that you can run and modify yourself so that you have real code to work with. You can try to modify their working example to suit your own toy project as a first step.

This has not been very useful as everyone is trying to market their tool in a way.

Assuming you are using Transformers, the official notebooks are a logical place to start: https://huggingface.co/docs/transformers/notebooks