DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

A collection of AWESOME things about mixture-of-experts

Visual Grounding for Object-Level Generalization in Reinforcement Learning (ECCV 2024)

More than 98% accuracy on CIFAR10 with Pytorch and small GPU

A UI-Focused Agent for Windows OS Interaction.

A natural language interface for computers

a state-of-the-art-level open visual language model | 多模态预训练模型

Code/Data for the paper: "LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding"

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…

Simple image captioning model