https://github.com/cdpierse/transformers-interpret-streamlit

Streamlit demo app to demonstrate the features of transformers interpret with multiple models.
https://github.com/cdpierse/transformers-interpret-streamlit

Last synced: 14 days ago
JSON representation

Streamlit demo app to demonstrate the features of transformers interpret with multiple models.

• Host: GitHub
• URL: https://github.com/cdpierse/transformers-interpret-streamlit
• Owner: cdpierse
• Created: 2021-02-27T16:16:20.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2021-06-24T18:59:24.000Z (over 4 years ago)
• Last Synced: 2025-09-09T23:38:40.259Z (25 days ago)
• Language: Python
• Size: 82 KB
• Stars: 25
• Watchers: 2
• Forks: 4
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Transformer Interpret Streamlit App

![App GIF](https://i.gyazo.com/842a91085da2c6a9039f12276d00646a.gif)

- Simple streamlit app to demonstrate some of the features of [Transformers Interpret](https://github.com/cdpierse/transformers-interpret).

- View the word attributions of 7+ text classification HuggingFace Transformer models.

- View the attributions w.r.t to any class/label in a model.

- View attributions w.r.t to both word and position embeddings for a model

## Install

`pip install -r requirements.txt `

## Run 

`streamlit run app.py`