young-geng

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

koala_data_pipeline

The data processing pipeline for the Koala chatbot language model

CQL

Conservative Q Learning on top of SAC

scalax

A simple library for scaling up JAX programs

m3ae_public

Multimodal Masked Autoencoders (M3AE): A JAX/Flax Implementation

JaxCQL

Conservative Q learning in Jax

mlxu

Machine Learning eXperiment Utilities

gps_superball_public

GPS codebase for NASA Superball tensegrity robot

SimpleSAC

A simple and easy to use implementation of the soft actor-critic algorithm.

cs184_final

CS184 final project: a point cloud to mesh generator

parameterized_model

TensorFlow parameterized model library

brc_cql_example

mmlu_easylm

MMLU evaluation for language models served with EasyLM

acd_archive

Automatically archive to Amazon cloud drive

d4rl

A benchmark for offline reinforcement learning.

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

iColorTF

iColor implementation in TensorFlow

pytorch-maml-q-rl

auto-detect-indentation

Auto detect indentation of files in Atom

bairblog.github.io

design-baselines-icml

design-bench

Benchmarks for Model-Based Optimization

design-bench-icml

FastChat

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

jax-fid

FID computation in Jax/Flax.

leet_code

LeetCode online judge solutions in Python

ml_logger

A logger, server and visualization dashboard for ML projects

NTRTsim

The NASA Tensegrity Robotics Toolkit Simulator, a physics based simulator to research the design and control of tensegrity robots.

SUPERball-state-estimation

transformers

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