This project contains a notebook implementing a multi-task sentence transformer model, including layer-wise learning rates and custom optimizations.
-
Run without Docker:
- Install dependencies:
pip install -r requirements.txt
- Open the notebook:
jupyter notebook Take_Home.ipynb
- Install dependencies:
-
Run with Docker:
- Build the Docker image:
docker build -t sentence-transformer . - Run the Docker container:
docker run -p 8888:8888 sentence-transformer
- Open the notebook by navigating to
http://localhost:8888/in your browser.
- Build the Docker image:
Take_Home.ipynb: Contains the entire codebase, including the model implementation, multi-task setup, and layer-wise learning rate implementation.