Skip to content

README.md

Latest commit

 

History

History
40 lines (25 loc) · 1.28 KB

README.md

File metadata and controls

40 lines (25 loc) · 1.28 KB

Binary Quantization OpenAI

This project aims to explore binary quantization techniques for OpenAI models.

Table of Contents

Introduction

Binary quantization is a technique used to reduce the memory footprint and computational requirements of deep learning models. This project focuses on applying binary quantization to OpenAI models to improve their efficiency.

Installation

To install the necessary dependencies, follow these steps:

  1. Clone the repository: git clone https://github.com/qdrant/examples.git
  2. Navigate to the project directory: cd binary-quantization-openai
  3. Install Poetry: pip install poetry
  4. Install the required packages: poetry install --no-root

Usage

To use the binary quantization techniques on an OpenAI embedding, follow these steps:

  1. Load the created embedding into Qdrant
  2. Apply binary quantization to the collection
  3. Evaluate the performance of the quantized model

Contributing

Contributions are welcome! If you have any ideas or suggestions, please open an issue or submit a pull request.

License

This project is licensed under the MIT License.