Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,47 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# **nanochat students**
|
| 11 |
+
|
| 12 |
+
Welcome to the **nanochat students** organization\! This is a community organization for students following Andrej Karpathy's [nanochat course](https://github.com/karpathy/nanochat). We are learning to build a full-stack LLM implementation from tokenization to web serving, all for under $100.
|
| 13 |
+
|
| 14 |
+
## **What is nanochat?**
|
| 15 |
+
|
| 16 |
+
nanochat is a complete implementation of an LLM like ChatGPT in a minimal, hackable codebase. It's designed as the capstone project for the LLM101n course by Eureka Labs, teaching you to build and train your own ChatGPT clone end-to-end.
|
| 17 |
+
|
| 18 |
+
## **What You'll Find Here**
|
| 19 |
+
|
| 20 |
+
This organization hosts community-contributed resources to help you learn and succeed with nanochat. You'll find:
|
| 21 |
+
\- notebooks that break down the implementation.
|
| 22 |
+
\- spaces that demo or illustrate the concepts we’re learning.
|
| 23 |
+
\- trained models and checkpoints from the community
|
| 24 |
+
\- relevant curated datasets.
|
| 25 |
+
|
| 26 |
+
## Getting Help and Sharing Ideas
|
| 27 |
+
|
| 28 |
+
The [Discussions](https://huggingface.co/spaces/nanochat-students/README/discussions) section is where you can ask questions, share your training results and report cards, discuss optimization techniques, and collaborate on experiments.
|
| 29 |
+
|
| 30 |
+
<!-- ## **Getting Started**
|
| 31 |
+
|
| 32 |
+
1. **Start with the main repo**: Clone and explore [karpathy/nanochat](https://github.com/karpathy/nanochat)
|
| 33 |
+
2. **Run the speedrun**: Follow the quick start guide to train your first $100 model
|
| 34 |
+
3. **Explore resources here**: Check out community notebooks and spaces
|
| 35 |
+
4. **Join discussions**: Share your results and learn from others
|
| 36 |
+
5. **Contribute back**: Share your own notebooks, models, or datasets\! -->
|
| 37 |
+
|
| 38 |
+
## **Contributing**
|
| 39 |
+
|
| 40 |
+
We welcome contributions from all students or experts. Here's how you can help:
|
| 41 |
+
|
| 42 |
+
- Notebooks: make tutorials or experiments that explain concepts from the code.
|
| 43 |
+
- Demos: make interactive demos or tools as Spaces
|
| 44 |
+
- Models Share your trained checkpoints with training details
|
| 45 |
+
- Help: Answer questions in [discussions](https://huggingface.co/spaces/nanochat-students/README/discussions)
|
| 46 |
+
- Articles: Write guides based on your experience and share them.
|
| 47 |
+
|
| 48 |
+
If you make anything, share it in this discussion [thread](https://huggingface.co/spaces/nanochat-students/README/discussions/1)
|
| 49 |
+
|
| 50 |
+
## **Resources**
|
| 51 |
+
|
| 52 |
+
- nanochat repo - [karpathy/nanochat](https://github.com/karpathy/nanochat)
|
| 53 |
+
- Introduction post: ["Introducing nanochat: The best ChatGPT that $100 can buy"](https://github.com/karpathy/nanochat/discussions/1)
|