| --- |
| title: EXD — Self-Directed PhD in AI |
| emoji: 🧠 |
| colorFrom: indigo |
| colorTo: purple |
| sdk: static |
| pinned: true |
| --- |
| |
| # 🧠 EXD — Self-Directed PhD in AI |
|
|
| **Engineering mastery through first principles, from the top down.** |
|
|
| A deep dive into AI engineering — fine-tuning, architectures, inference optimization, and systems thinking. Work backwards from high-level concepts to fundamentals. |
|
|
| --- |
|
|
| ## 🗺️ Episodes |
|
|
| | # | Title | Video | Interactive | Article | |
| |---|-------|-------|-------------|---------| |
| | 01 | Intro to EXD | [📺 Watch](https://youtu.be/mUFNk2yOblc) | — | — | |
| | 02 | Setup & First Inference | [📺 Watch](https://youtu.be/pPboQK6hXBw) | — | [📖 GitHub](https://github.com/Ramshreyas/EXD/blob/main/episodes/Ep02/ep2-setup-and-first-inference.md) | |
| | 03 | Inference Benchmarking | [📺 Watch](https://youtu.be/BwMJo25iK9A) | [🚀 Simulator](https://huggingface.co/spaces/EXD-AI/inference-simulator) | [📖 GitHub](https://github.com/Ramshreyas/EXD/blob/main/episodes/Ep03/ep3-inference-benchmarking.md) | |
| | 04 | Performance Tuning | [📺 Watch](https://youtu.be/jUDci02mTOM) | [🚀 Sim v2](https://huggingface.co/spaces/EXD-AI/inference-simulator-v2) | [📖 GitHub](https://github.com/Ramshreyas/EXD/blob/main/episodes/Ep04/ep4-inference-benchmarking-continued.md) | |
| | 05 | Speculative Decoding | [📺 Watch](https://youtu.be/ip8G_ukhI7E) | [⚡ Spec Decode](https://huggingface.co/spaces/EXD-AI/speculative-decoding-simulator) | [📖 GitHub](https://github.com/Ramshreyas/EXD/blob/main/episodes/Ep05/shownotes.md) | |
| | 06 | Taking Stock | [📺 Watch](https://youtu.be/bFWP2QDxAAU) | — | — | |
| | 07 | Tokenization & Embeddings | [📺 Watch](https://youtu.be/E03MyfzUsJI) | [🔤 Notebook](https://huggingface.co/datasets/EXD-AI/episode-07-tokenization) | [📖 GitHub](https://github.com/Ramshreyas/EXD/blob/main/episodes/Ep07/tokenization_and_embeddings.ipynb) | |
|
|
| --- |
|
|
| ## 📦 Artifacts |
|
|
| | Type | Name | Description | |
| |------|------|-------------| |
| | 📊 Dataset | [benchmark-results](https://huggingface.co/datasets/EXD-AI/benchmark-results) | Performance data from inference sweeps | |
| | ⚙️ Dataset | [vllm-configs](https://huggingface.co/datasets/EXD-AI/vllm-configs) | Production vLLM configuration profiles | |
| | 📝 Article | [GitHub episodes](https://github.com/Ramshreyas/EXD/tree/main/episodes) | Full write-ups for each episode | |
| | 📓 Notebook | [episode-07-tokenization](https://huggingface.co/datasets/EXD-AI/episode-07-tokenization) | Tokenization & embeddings deep-dive | |
|
|
| --- |
|
|
| ## 🌐 Links |
|
|
| 📺 [YouTube Channel](https://youtube.com/@EXD-ai) · 💻 [GitHub](https://github.com/Ramshreyas/EXD) · 🏗️ [@EXDai](https://huggingface.co/EXDai) · 📚 [Collection](https://huggingface.co/collections/EXD-AI/EXD-AI/exd-self-directed-phd-in-ai-6a3bbd3cbac6d838d3c749e2) |
|
|
| --- |
|
|
| ## 🛠️ Focus Areas |
|
|
| - Model fine-tuning (LoRA, QLoRA, RLHF/DPO) |
| - Transformer architectures (attention variants, MoE) |
| - Inference optimization (quantization, KV cache, speculative decoding, compilation) |
|
|
| --- |
|
|
| *Work backwards. Understand everything.* |
|
|
