Moshe Ofer
Initial commit for Hugging Face Space
143bcfb
metadata
title: Multi Beam Text Streamer
emoji: πŸ†
colorFrom: green
colorTo: pink
sdk: docker
pinned: false
short_description: A generic text streamer that supports beam search and manage

Beam Search Generator with MultiBeamTextStreamer

This Hugging Face Space hosts a Beam Search Generator web application, powered by a Flask backend and integrated with Hugging Face Transformers. The application provides real-time visualization of beam search generation, offering insights into how language models explore multiple text completion possibilities simultaneously.

πŸš€ Features

  • Real-time visualization of active and completed beams.
  • Adjustable generation parameters:
    • Number of beams.
    • Maximum tokens.
    • Generation speed (using delay sliders).
  • Seamless interaction with Hugging Face Transformers.
  • Powered by the custom MultiBeamTextStreamer from the Transformers library.

πŸ“œ How It Works

  1. Input a prompt in the text box.
  2. Configure generation settings:
    • Number of beams.
    • Maximum token count.
    • Delay speed.
  3. Click Generate to visualize the beam search process in real-time.

πŸ› οΈ Setup Instructions

Running Locally

  1. Clone the repository:
    git clone https://huggingface.co/spaces/<your-username>/<your-space-name>
    cd <your-space-name>