Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,10 +1,52 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: static
|
| 7 |
-
pinned:
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: EXD — Self-Directed PhD in AI
|
| 3 |
+
emoji: 🧠
|
| 4 |
+
colorFrom: indigo
|
| 5 |
+
colorTo: purple
|
| 6 |
sdk: static
|
| 7 |
+
pinned: true
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# 🧠 EXD — Self-Directed PhD in AI
|
| 11 |
+
|
| 12 |
+
**Engineering mastery through first principles, from the top down.**
|
| 13 |
+
|
| 14 |
+
A deep dive into AI engineering — fine-tuning, architectures, inference optimization, and systems thinking. Work backwards from high-level concepts to fundamentals.
|
| 15 |
+
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
## 🌐 Where to find us
|
| 19 |
+
|
| 20 |
+
| Platform | Link |
|
| 21 |
+
|----------|------|
|
| 22 |
+
| **📺 YouTube** | [EXD YouTube Channel](https://youtube.com/@EXD-ai) |
|
| 23 |
+
| **💻 GitHub** | [github.com/Ramshreyas/EXD](https://github.com/Ramshreyas/EXD) |
|
| 24 |
+
| **🏗️ Creator** | [@EXDai on HF](https://huggingface.co/EXDai) |
|
| 25 |
+
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
## 🗺️ Episodes
|
| 29 |
+
|
| 30 |
+
| # | Title | Article | Interactive |
|
| 31 |
+
|---|-------|---------|-------------|
|
| 32 |
+
| 01 | Intro to EXD | — | — |
|
| 33 |
+
| 02 | Setup & First Inference | — | — |
|
| 34 |
+
| 03 | Inference Benchmarking | — | [Simulator](https://huggingface.co/spaces/EXD-AI/inference-simulator) |
|
| 35 |
+
| 04 | Performance Tuning | — | [Simulator v2](https://huggingface.co/spaces/EXD-AI/inference-simulator-v2) |
|
| 36 |
+
| 05 | Speculative Decoding | — | [Spec Decode Sim](https://huggingface.co/spaces/EXD-AI/speculative-decoding-simulator) |
|
| 37 |
+
| 06 | *coming soon* | — | — |
|
| 38 |
+
| 07 | *coming soon* | — | — |
|
| 39 |
+
|
| 40 |
+
---
|
| 41 |
+
|
| 42 |
+
## 🛠️ Focus Areas
|
| 43 |
+
|
| 44 |
+
- Model fine-tuning (LoRA, QLoRA, RLHF/DPO)
|
| 45 |
+
- Transformer architectures (attention variants, MoE)
|
| 46 |
+
- Inference optimization (quantization, KV cache, speculative decoding, compilation)
|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
⏳ *More artifacts (benchmark datasets, configs, article write-ups) coming as episodes progress.*
|
| 51 |
+
|
| 52 |
+
*Work backwards. Understand everything.*
|