LLM inference in C/C++

Unify Efficient Fine-Tuning of 100+ LLMs

Effortless data labeling with AI support from Segment Anything and other awesome models.

Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

Llama中文社区，最好的中文Llama大模型，完全开源可商用

DeepSeek Coder: Let the Code Write Itself

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

Protocol Buffers - Google's data interchange format

The devkit of the nuScenes dataset.

RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision. (Former version: UniOcc)

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

Official code base of the BEVDet series .

Transformer related optimization, including BERT, GPT

Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

算法竞赛模板库 by 灵茶山艾府 💭💡🎈

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

Spatial Sparse Convolution Library

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

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

Stable Diffusion web UI

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

A latent text-to-image diffusion model

LoRA training scripts use kohya-ss's trainer, for diffusion model.