XCJinggai

LIC_TCM

visqol

Perceptual Quality Estimator for speech and audio

trl

Train transformer language models with reinforcement learning.

FunCodec

FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.

USLM

Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)

1d-tokenizer

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

LLaVA

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

zero_nlp

中文nlp解决方案(大模型、数据、模型、训练、推理)

MaMMUT-pytorch

Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch

EMPatches

Extract and Merge image patches for easy, fast and self-contained digital image processing and deep learning model training.

patchify.py

A library that helps you split image into small, overlappable patches, and merge patches into original image.

LM4LV

🔥Official PyTorch implementation for "LM4LV: A Frozen Large Language Model for Low-level Vision Tasks".

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

libjxl

JPEG XL image format reference implementation

L3C-PyTorch

PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"

libbpg-py

a pure python binding for BPG (Better Portable Graphics)

imageio-flif

imageio plugin with FLIF wrapper for Python

pyFLIF

ctypes based python wrapper for FLIF library

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

CompressAI-Vision

CompressAI-Vision helps you design, test and compare Video Compression for Machines pipelines. Compression methods can be either pulled from custom AI-based modules from CompressAI or traditional codecs such as H.266/VVC.

CompressAI

A PyTorch library and evaluation platform for end-to-end compression research

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

vision_transformer

SpeechTokenizer

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on

magvit

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

magvit2-pytorch

Implementation of MagViT2 Tokenizer in Pytorch

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型