teddykoker/grokking
PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
This project helps machine learning researchers explore and understand the phenomenon of "Grokking" using small algorithmic datasets. It takes as input training parameters and outputs models that demonstrate generalization beyond overfitting, helping you reproduce the behaviors described in the original "Grokking" paper. Machine learning researchers and academics studying model generalization would find this useful.
No commits in the last 6 months.
Use this if you are a machine learning researcher interested in replicating and studying the 'Grokking' phenomenon, particularly with modular arithmetic datasets.
Not ideal if you are looking for a pre-trained model or a tool for applying machine learning to real-world, large-scale problems.
Stars
39
Forks
6
Language
Python
License
—
Category
Last pushed
Dec 07, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/teddykoker/grokking"
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