sparse_attention

finetune-transformer-lm

Code and model for the paper "Improving Language Understanding by Generative Pre-Training"

blocksparse

Efficient GPU kernels for block-sparse matrix multiplication and convolution

transformer-debugger

iaf

Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autor...

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

ai-and-efficiency

Submissions for AI and Efficiency SOTA's

image-gpt

sparse_autoencoder

distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error...

grade-school-math

neural-gpu

Code for the Neural GPU model originally described in "Neural GPUs Learn Algorithms"

whisper-jax

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

faster-whisper

Faster Whisper transcription with CTranslate2

distribution_augmentation

Code for the paper, "Distribution Augmentation for Generative Modeling", ICML 2020.