vincent-163 / transformer-arithmeticLinks
☆13Updated 3 years ago
Alternatives and similar repositories for transformer-arithmetic
Users that are interested in transformer-arithmetic are comparing it to the libraries listed below
Sorting:
- Materials for ConceptARC paper☆114Updated this week
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆190Updated 3 years ago
- Language-annotated Abstraction and Reasoning Corpus☆99Updated 2 years ago
- Neural Networks and the Chomsky Hierarchy☆214Updated last year
- A dataset of alignment research and code to reproduce it☆78Updated 2 years ago
- ☆259Updated 8 months ago
- An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"☆323Updated last year
- Tools for working with the Abstraction & Reasoning Corpus☆215Updated 5 months ago
- Train very large language models in Jax.☆210Updated 2 years ago
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆163Updated 7 months ago
- JAX implementation of the Llama 2 model☆216Updated 2 years ago
- Pytorch implementation of the paper 'Compositional language emerge in a neural iterated learning' (ICLR 2020).☆16Updated 4 years ago
- Code for the paper "Predictive Coding Approximates Backprop along Arbitrary Computation Graphs"☆168Updated 5 years ago
- Code for NEMO, and Assembly Calculus☆110Updated last year
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆216Updated 3 weeks ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆83Updated 3 years ago
- A hard gym for programming☆165Updated last year
- Reimplementation of Geoffrey Hinton's Forward-Forward Algorithm☆162Updated 2 years ago
- A domain-specific probabilistic programming language for modeling and inference with language models☆141Updated 9 months ago
- ☆49Updated 4 years ago
- A programming language for formal/informal computation.☆43Updated last month
- ☆67Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆201Updated 2 years ago
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆175Updated 2 years ago
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆224Updated last year
- ☆14Updated 3 years ago
- Simple Annotated implementation of GPT-NeoX in PyTorch☆110Updated 3 years ago
- Probabilistic LLM evaluations. [CogSci2023; ACL2023]☆73Updated last year
- Fast Discounted Cumulative Sums in PyTorch☆97Updated 4 years ago
- PapersWithCode RSS feeds (unofficial)☆43Updated 8 months ago