C-J-Cundy

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

langchain

🦜🔗 Build context-aware reasoning applications

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

score_sde

Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

diffrax

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

OhMyREPL.jl

Syntax highlighting and other enhancements for the Julia REPL

zfp

Compressed numerical arrays that support high-speed random access

jaxrl

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

org-fragtog

Automatically toggle Org mode LaTeX fragment previews as the cursor enters and exits them

flaxmodels

Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.

blacken

Python Black for Emacs

adversarial-prompts

Curation of prompts that are known to be adversarial to large language models

bayeSDE

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

jax-smi

JAX Synergistic Memory Inspector

Reflected-Diffusion

[ICML 2023] Reflected Diffusion Models (https://arxiv.org/abs/2304.04740)

AdEMAMix-Optimizer-Pytorch

The AdEMAMix Optimizer: Better, Faster, Older.

UMNN

Implementation of Unconstrained Monotonic Neural Network and the related experiments. These architectures are particularly useful for modelling monotonic transformations in normalizing flows.

mathpix.el

Mathpix Emacs Plugin

LAP-solvers

Benchmarking Linear Assignment Problem Solvers

NuX

Normalizing Flows using JAX

commonsense-rl

Knowledge-Aware RL agents with Commonsense Reasoning

Crux.jl

Julia library for deep reinforcement learning

rcdqn

This repository contains the source code of the EMNLP 2020 paper Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning.

safe-grid-gym

A gym interface for AI safety gridworlds created in pycolab.

agent_debugger

Causal Analysis of Agent Behavior for AI Safety

bayes-net

Checking D-separations and I-equivalence in Bayesian Networks.

differentially-private-q-learning

bcd_nets

Code for `BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery`, Neurips 2021