zye1996

meilisearch

A lightning-fast search API that fits effortlessly into your apps, websites, and workflow

YT-Spammer-Purge

Allows you easily scan for and delete scam comments using several methods.

EfficientTrain

1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.

marker

Convert PDF to markdown quickly with high accuracy

awesome-generative-information-retrieval

in-context-ralm

slidev

Presentation Slides for Developers

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

GroundingDINO

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

gorilla

Gorilla: An API store for LLMs

gpt-crawler

Crawl a site to generate knowledge files to create your own custom GPT from a URL

VAR

[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

surya

OCR, layout analysis, reading order, line detection in 90+ languages

LPMDataset

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

DocumentLayoutAnalysis

Document Layout Analysis resources repos for development with PdfPig.

CnSTD

CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula Detection, MFD）、篇章分析（Layout Analysis）的Python3 包

PaddleOCR2Pytorch

PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

ai

Build AI-powered applications with React, Svelte, Vue, and Solid

BitNet

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

AutoPrompt

A framework for prompt tuning using Intent-based Prompt Calibration

Chinese-medical-dialogue-data

Chinese medical dialogue data 中文医疗对话数据集

vearch

Distributed vector search for AI-native applications

LESS

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

magika

Detect file content types with deep learning

jieba

结巴中文分词

speechbrain

A PyTorch-based Speech Toolkit

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)