meta-llama/llama-cookbook ? reverse-engineered prompt

Build me a Llama learning repo that feels like a practical cookbook, with clear notebooks and examples for getting started with inference, fine tuning, and RAG.

I want it to be easy to follow for someone who just wants to try things out and see results, with a few end to end examples too, like a chatbot style use case and a document question answering workflow. Include examples for both text and vision where it makes sense, and make the code easy to run and adapt. If there are current best practices or updated docs online that would help, look them up and use them.

Please keep the project organized so a person can quickly find beginner examples, more advanced recipes, and any helpful notes for common fine tuning questions.