mcbal/spin-model-transformers
Physics-inspired transformer modules based on mean-field dynamics of vector-spin models in JAX
This project provides specialized building blocks for AI models that are inspired by how particles interact in physics. It takes in numerical data, like patterns or features, and transforms it using these unique interaction rules to produce enhanced or re-represented data. Scientists and researchers working with complex data patterns, especially those in physics-related fields, might use this to develop more robust machine learning models.
No commits in the last 6 months.
Use this if you are a researcher building advanced machine learning models and want to experiment with novel, physics-inspired architectures for processing complex data.
Not ideal if you are looking for an off-the-shelf solution for common data analysis tasks or are unfamiliar with developing custom neural network architectures.
Stars
46
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 10, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mcbal/spin-model-transformers"
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