🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.

An implacation of SignGraph: A Sign Sequence is Worth Graphs of Nodes (CVPR2024)

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

A high-throughput and memory-efficient inference and serving engine for LLMs

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

PyTorch package for the discrete VAE used for DALL·E.

High-Resolution Image Synthesis with Latent Diffusion Models

The official Meta Llama 3 GitHub site

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.

Latex code for making neural networks diagrams

Productive, portable, and performant GPU programming in Python.

Unofficial tensorflow implemention of "Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018) " model https://maybeshewill-cv.github.io/attentive-gan-derainnet/

Image Inpainting via Generative Multi-column Convolutional Neural Networks, NeurIPS2018

Attentive Generative Adversarial Network for Raindrop Removal from A Single Image (CVPR 2018)

运维之道

分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.