borjanG / 2023-transformers-rotfLinks
Codes for the paper "A mathematical perspective on Transformers".
☆39Updated last year
Alternatives and similar repositories for 2023-transformers-rotf
Users that are interested in 2023-transformers-rotf are comparing it to the libraries listed below
Sorting:
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆174Updated 2 years ago
- Code for Discovering Preference Optimization Algorithms with and for Large Language Models☆64Updated last year
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆92Updated last year
- Meta-Learning for Compositionality (MLC) for modeling human behavior☆145Updated 3 weeks ago
- Codes for the paper The emergence of clusters in self-attention dynamics.☆17Updated last year
- A State-Space Model with Rational Transfer Function Representation.☆83Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆80Updated 3 years ago
- Omnigrok: Grokking Beyond Algorithmic Data☆62Updated 2 years ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆196Updated last year
- ☆41Updated 3 years ago
- ☆231Updated 2 weeks ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆38Updated 3 years ago
- ☆53Updated last year
- Learning Universal Predictors☆81Updated last year
- About A collection of AWESOME things about information geometry Topics☆172Updated last year
- ☆167Updated 2 years ago
- The Energy Transformer block, in JAX☆62Updated 2 years ago
- Repository for code used in the xVal paper☆145Updated last year
- Open source code for EigenGame.☆33Updated 2 years ago
- Evaluation of neuro-symbolic engines☆40Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆135Updated 11 months ago
- ☆62Updated last year
- JAX implementation of the Mistral 7b v0.2 model☆35Updated last year
- ☆53Updated last year
- ☆164Updated last year
- Jax like function transformation engine but micro, microjax☆33Updated last year
- ☆35Updated last year
- Code associated to papers on superposition (in ML interpretability)☆33Updated 3 years ago
- ☆33Updated last year
- A Mechanistic Interpretability Analysis of Grokking☆23Updated 3 years ago