EvoTransformer-Demo / README.md
HemanM's picture
Update README.md
303646a verified
---
title: EvoTransformer Demo
emoji: 🧬
colorFrom: pink
colorTo: green
sdk: gradio
app_file: app.py
pinned: false
license: mit
sdk_version: 5.36.2
---
# 🧬 EvoTransformer Demo
Welcome to the official demo of **EvoTransformer** β€” an evolving Transformer architecture built to adapt itself *during training* using principles inspired by evolutionary algorithms.
This project showcases a lightweight, in-training neural architecture search (NAS) system that mutates key traits such as:
- Number of layers
- Attention heads
- Feed-forward dimension
- Dropout
- Memory module toggle
> πŸ“ Developed by **Dr. Heman Mohabeer**, Intelligent Africa Ltd
> πŸ“€ Submitted to JMLR 2025 | 🌍 Built from **Mauritius**
---
## πŸš€ Try It Live
Use the Gradio interface to simulate architectural evolution across generations.
Visualize how traits adapt β€” and get a simulated accuracy + parameter estimate.
---
## πŸ“Š Behind the Scenes
EvoTransformer includes:
- Genetic operators: mutation, crossover (demo limited to mutation)
- Structural traits representation
- Online evolution loop
- Lightweight scoring and parameter estimation
This demo is a simplified, live-running version of the full EvoTransformer system submitted for peer review.
---
## πŸ“š Citation
```bibtex
@misc{mohabeer2024evotransformer,
title={EvoTransformer: In-Training Evolution of Transformer Architectures for Adaptive and Efficient NLP},
author={Heman Mohabeer},
year={2024},
note={Hugging Face Demo},
url={https://huggingface.co/spaces/HemanM/EvoTransformer-Demo}
}
---
## πŸ”— Links
- πŸ“„ [JMLR Submission PDF (coming soon)]()
- 🧠 [Colab Notebook (in progress)]()
- πŸ“˜ [More from Dr. Heman Mohabeer](https://linkedin.com/in/hemanmohabeer)
---
## πŸ“œ License
MIT License β€” feel free to use, fork, and build upon this demo.