SimonOuellette35/CountingWithTransformers
Code for paper "Counting and Algorithmic Generalization with Transformers"
This project provides code for researchers studying how transformer models can learn to count. It takes various transformer architectures and training configurations as input, then outputs the results of their ability to count pixels in a grid or generalize identity functions. Machine learning researchers and AI scientists focused on model generalization and algorithmic learning would find this useful.
No commits in the last 6 months.
Use this if you are a machine learning researcher investigating the architectural properties of transformers that enable or hinder their ability to learn simple counting algorithms and generalize these skills.
Not ideal if you are looking for a pre-trained model or an application to count objects in real-world images, as this is a research tool for understanding model capabilities.
Stars
7
Forks
—
Language
Python
License
—
Category
Last pushed
Jan 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SimonOuellette35/CountingWithTransformers"
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