This repository documents my journey of building deep learning projects from 0 to 1. The goal is to gain a deeper, hands-on understanding of the core principles behind foundational models in deep learning and large language models (LLMs). Each project is my attempt to take a deep dive into the implementation details, trying to understand the core mechanics and potential pitfalls.
- NMT - Neural Machine Translation
- A complete workflow for an English-to-Chinese translation model based on the Transformer architecture. See
nmt/README.mdfor details.
- A complete workflow for an English-to-Chinese translation model based on the Transformer architecture. See