Aaron Lou's starred repositories
audiocraft
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
flash-attention
Fast and memory-efficient exact attention
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
consistencydecoder
Consistency Distilled Diff VAE
gpt-2-output-dataset
Dataset of GPT-2 outputs for research in detection, biases, and more
score_sde_pytorch
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
CUDALibrarySamples
CUDA Library Samples
gpt-2-Pytorch
Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation
VQ-Diffusion
Official implementation of VQ-Diffusion
openwebtext
Open clone of OpenAI's unreleased WebText dataset scraper. This version uses pushshift.io files instead of the API for speed.
ringattention
Transformers with Arbitrarily Large Context
magvit2-pytorch
Implementation of MagViT2 Tokenizer in Pytorch
DNA-Diffusion
🧬 Generative modeling of regulatory DNA sequences with diffusion probabilistic models 💨
riemannian-score-sde
Score-based generative models for compact manifolds
reparam-discrete-diffusion
Reparameterized Discrete Diffusion Models for Text Generation
Riemannian-Residual-Neural-Networks
[NeurIPS 2023] Riemannian Residual Neural Networks (https://arxiv.org/abs/2006.10254)