18.06 course at MIT

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

MLX: An array framework for Apple silicon

The simplest, fastest repository for training/finetuning medium-sized GPTs.

llama3 implementation one matrix multiplication at a time

tiny vision language model

An advanced guide to learn English which might benefit you a lot 🎉 . 离谱的英语学习指南/英语学习教程。

基于深度学习高性能中文车牌识别 High Performance Chinese License Plate Recognition Framework.

Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

更纯粹、更高压缩率的Tokenizer

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

An implementation of "CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model".

Generative Models by Stability AI

一个基于 electron 的音乐软件

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[CVPR 2023] Code release for PConv and FasterNet

A latent text-to-image diffusion model

Code release for ConvNeXt V2 model

transformers ocr for chinese

TACTiS: Transformer-Attentional Copulas for Time Series from ServiceNow Research

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

About Code release for "Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy" (ICLR 2022 Spotlight), https://openreview.net/forum?id=LzQQ89U1qm_

A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Code for "MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER"

Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)