neverix

candle

Minimalist ML framework for Rust

transformer-debugger

weak-to-strong

penzai

A JAX research toolkit for building, editing, and visualizing neural networks.

intel-extension-for-pytorch

A Python package for extending the official PyTorch that can easily obtain performance on Intel platform

megablocks

diffuser

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

ema-pytorch

A simple way to keep track of an Exponential Moving Average (EMA) version of your pytorch model

nnsight

The nnsight package enables interpreting and manipulating the internals of deep learned models.

signatory

Differentiable computations of the signature and logsignature transforms, on both CPU and GPU. (ICLR 2021)

GP4A

Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes"

Score-Entropy-Discrete-Diffusion

[ICML 2024 Oral] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

causal-conv1d

Causal depthwise conv1d in CUDA, with a PyTorch interface

pymlir

Python interface for MLIR - the Multi-Level Intermediate Representation

geometric-algebra-transformer

sae_vis

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

writeup_factorio

Writeup of a remote code execution in Factorio by supplying a modified save file.

MindEyeV2

ReinMax

Beyond Straight-Through

deep-thinking

A centralized place for deep thinking code and experiments

LLM-LieDetector

Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"

sparkvis

Visualize tensors in a plain Python REPL using Sparklines

improved-diffusion

Text-writing denoising diffusion (and much more)

dice-mc

DiCE: The Infinitely Differentiable Monte-Carlo Estimator

SparseMixer

Sparse Backpropagation for Mixture-of-Expert Training

PySvelte

A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations

pygguf

GGUF parser in Python

Celeste-Bot

Genetic algorithm learns to play a recreation of Celeste Classic

radeline

Small collection of brute-force tools to help with Celeste TASing

vis

Working title. PySvelte reimplementation. Jupyter notebook visualisations for language model interpretability