poloclub/dodrio
Exploring attention weights in transformer-based models with linguistic knowledge.
This tool helps you visually analyze and compare how transformer-based language models process text. You input a pre-trained transformer model and sample text, and it outputs interactive visualizations showing the model's 'attention weights' alongside linguistic information like part-of-speech tags. It's designed for natural language processing (NLP) researchers and practitioners who want to understand why their models make certain predictions.
370 stars. No commits in the last 6 months.
Use this if you are an NLP researcher or practitioner who needs to interpret and debug the internal workings of transformer models.
Not ideal if you are looking for a tool to train new NLP models or if you need to perform large-scale, automated model evaluation without visual inspection.
Stars
370
Forks
36
Language
Svelte
License
MIT
Category
Last pushed
Oct 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/poloclub/dodrio"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
philipperemy/keras-attention
Keras Attention Layer (Luong and Bahdanau scores).
tatp22/linformer-pytorch
My take on a practical implementation of Linformer for Pytorch.
ematvey/hierarchical-attention-networks
Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is...
datalogue/keras-attention
Visualizing RNNs using the attention mechanism
thushv89/attention_keras
Keras Layer implementation of Attention for Sequential models