This repository provides hands-on tutorials and examples for getting started with deep learning using PyTorch and Hugging Face libraries. It covers fine-tuning various LLMs including FLAN-T5, Falcon, Llama 2, Gemma, and Llama 3 with techniques like LoRA, DeepSpeed ZeRO, FSDP, and quantization. The tutorials also include RLHF training with DPO, instruction tuning, embedding model fine-tuning for RAG, and distributed training on TPUs.