handsOnLLM/Hands-On-Large-Language-Models — reverse-engineered prompt

Build me a clean companion code repo for a beginner friendly book about large language models. I want it to feel like an illustrated learning guide, with one runnable notebook per chapter and a simple README that helps people open everything in Google Colab.

The notebooks should walk through practical LLM topics in order, starting with what language models are, then tokens and embeddings, looking inside transformers, text classification, clustering and topic modeling, prompt engineering, text generation tools, semantic search and retrieval augmented generation, multimodal models, creating embedding models, and fine tuning models for classification and generation.

Please set it up so someone can either run the notebooks in Colab or install the project locally with a requirements file and an environment file. Add a short setup folder with beginner instructions. Keep the tone educational and visual, with clear explanations, comments, and placeholders for figures where helpful. Look up current docs online if you need to.