MurtyShikhar/TreeProjections
Tool to measure tree-structuredness of the internal algorithm learnt by a transformer
This tool helps AI researchers understand how well transformer models learn tree-like structures, which are important for tasks like natural language processing. It takes a trained transformer model and a dataset, then outputs a 'tree projection score' that indicates how tree-structured the model's internal representations are. This is useful for researchers analyzing the internal workings and interpretability of neural networks.
No commits in the last 6 months.
Use this if you are an AI researcher studying transformer models and want to quantify how much their internal representations resemble hierarchical, tree-like structures.
Not ideal if you are looking for a tool to build or train new transformer models, or to improve model performance on a specific task.
Stars
12
Forks
2
Language
Python
License
MIT
Category
Last pushed
May 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/MurtyShikhar/TreeProjections"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action