backpropper

academicpages.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

babelcode

distrax

dm_robotics

Libraries, tools and tasks created and used at DeepMind Robotics.

ede

Code for the paper "Uncertainty-Driven Exploration for Generalization in Reinforcement Learning".

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

llama

Inference code for LLaMA models

llama-recipes

Examples and recipes for Llama model

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

math

The MATH Dataset (NeurIPS 2021)

METER

METER: A Multimodal End-to-end TransformER Framework

mlx

MLX: An array framework for Apple silicon

mlx-examples

Examples in the MLX framework

mujoco_menagerie

A collection of high-quality models for the MuJoCo physics engine, curated by DeepMind.

openai-cookbook

Examples and guides for using the OpenAI API

openai-quickstart-python

Python example app from the OpenAI API quickstart tutorial

optax

Optax is a gradient processing and optimization library for JAX.

procgen

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

PromptPG

Data and code for the ICLR 2023 paper "Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning".

retro

Retro Games in Gym

rliable

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

Stable-Alignment

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

summarize-from-feedback

Code for "Learning to summarize from human feedback"

tiktoken

trax

Trax — Deep Learning with Clear Code and Speed

trl

Train transformer language models with reinforcement learning.

website