google-deepmind / neural_networks_chomsky_hierarchy
Neural Networks and the Chomsky Hierarchy
☆205Updated last year
Alternatives and similar repositories for neural_networks_chomsky_hierarchy:
Users that are interested in neural_networks_chomsky_hierarchy are comparing it to the libraries listed below
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 2 years ago
- An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"☆307Updated 7 months ago
- ☆166Updated last year
- Mechanistic Interpretability for Transformer Models☆50Updated 2 years ago
- Train very large language models in Jax.☆204Updated last year
- ☆255Updated 2 years ago
- Resources from the EleutherAI Math Reading Group☆53Updated last month
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆187Updated 2 years ago
- Named Tensors for Legible Deep Learning in JAX☆172Updated last week
- ☆349Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- ☆215Updated 9 months ago
- Inference code for LLaMA models in JAX☆118Updated 11 months ago
- ☆62Updated 2 years ago
- Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale, TACL (2022)☆125Updated 5 months ago
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆207Updated 3 months ago
- An interactive exploration of Transformer programming.☆262Updated last year
- A domain-specific probabilistic programming language for modeling and inference with language models☆126Updated last year
- Materials for ConceptARC paper☆92Updated 5 months ago
- [NeurIPS 2023] Learning Transformer Programs☆159Updated 11 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆180Updated last year
- ☆531Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆120Updated 2 years ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆568Updated this week
- A library to create and manage configuration files, especially for machine learning projects.☆77Updated 3 years ago
- LoRA for arbitrary JAX models and functions☆136Updated last year
- Language-annotated Abstraction and Reasoning Corpus☆86Updated last year
- Tools for studying developmental interpretability in neural networks.☆88Updated 3 months ago
- Named tensors with first-class dimensions for PyTorch☆320Updated last year
- ☆175Updated last year