Cantonese Grapheme-to-Phoneme Converter based on GitYCC/g2pW

Code for our paper "Graph Language Models"

A library written in rust with functions for Han character (in particular Cantonese) processing.

Code for "Heterogeneous Graph Transformer" (WWW'20), which is based on pytorch_geometric

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages -- ACL 2023

FuzzPEG: A Context-Free Random Program Generator

Companion code for the "When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations" paper.

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Wavelet Convolutions for Large Receptive Fields. ECCV 2024.

Normalizing flows in PyTorch

[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

An official pytorch implementation of EACL2024 short paper "Flow Matching for Conditional Text Generation in a Few Sampling Steps"

Generative Flow based Sequence-to-Sequence Toolkit written in Python.

DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Simple go utility to download HuggingFace Models and Datasets

《粵音資料集叢》粵音音節錄音檔

Official pytorch implement of paper InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization

Mutual Information in Pytorch

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

official code of WaLa paper

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

PyTorch code and models for the DINOv2 self-supervised learning method.

PyWavelets - Wavelet Transforms in Python

Lossy compression; Variable rate compresson; Lossless compression;