https://github.com/yaacov/nitzanim-2024
Demo scripts from Nitzanim 2024 ai talk
https://github.com/yaacov/nitzanim-2024
Last synced: 7 months ago
JSON representation
Demo scripts from Nitzanim 2024 ai talk
- Host: GitHub
- URL: https://github.com/yaacov/nitzanim-2024
- Owner: yaacov
- License: gpl-3.0
- Created: 2024-07-25T06:17:55.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-10T07:48:56.000Z (12 months ago)
- Last Synced: 2025-01-23T09:43:11.531Z (9 months ago)
- Language: Python
- Size: 23.4 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Nitzanim 2024 AI Demo Scripts
This repository contains demo scripts used in the Nitzanim 2024 AI talk. The scripts demonstrate various AI model techniques, including embeddings, transformers, and neural network architectures.
## Repository Contents
### Large Models
- [embedings.py](embedings.py): Demonstrates large model embeddings and calculates cosine distances.
- [transformer.py](transformer.py): Showcases the functionality of a large model transformer.
**Large Models** are typically used for tasks requiring high capacity and complexity, such as natural language processing, image recognition, and other applications where understanding nuanced patterns and relationships in large datasets is crucial.
### Small Models
- [one-node-user-weights.py](one-node-user-weights.py): Demonstrates a simple one-node neural network (perceptron).
- [three-node-user-weights.py](three-node-user-weights.py): Illustrates a three-node neural network model.
- [three-node-train-weights.py](three-node-train-weights.py): Includes training logic for a three-node neural network.
**Small Models** are useful for simpler tasks or when computational resources are limited. They are often employed in scenarios where interpretability and efficiency are prioritized over the complexity and capacity of the model.
## How to Use
1. Clone the repository:
```
git clone https://github.com/yaacov/nitzanim-2024.git
```
2. Navigate to the project directory:
```
cd nitzanim-2024
```
3. Install required packages:
```
pip install -r requirements.txt
```
4. Run the scripts using Python:
```
python .py
```
## Prerequisites
Ensure you have Python installed along with necessary libraries like NumPy and PyTorch.
## License
This project is licensed under the GPL-3.0 License - see the LICENSE file for details.