中国专利.skill，从项目文档到可交付的技术交底书，专利点挖掘、联网国知局查新、脱敏成文与自检闭环。

A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

🦜🔗 Build context-aware reasoning applications

总结Prompt&LLM论文，开源数据&模型，AIGC应用

✨✨Latest Advances on Multimodal Large Language Models

Awesome-Multilingual-LLMs-Papers

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

ModelScope: bring the notion of Model-as-a-Service to life.

Langchain-Chatchat（原Langchain-ChatGLM, Qwen 与 Llama 等）基于 Langchain 与 ChatGLM 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen a…

ms-swift: Use PEFT or Full-parameter to finetune 250+ LLMs or 35+ MLLMs. (Qwen2, GLM4, Internlm2, Yi, Llama3, Llava, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

YOLOv8 using TensorRT accelerate !

OpenMMLab Detection Toolbox and Benchmark

Grounded-SAM: Marrying Grounding-DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

A collection of various deep learning architectures, models, and tips

paper list of robotic grasping and some related works

Code for RoboFlamingo

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

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.

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

This is an official implementation for "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos" (ECCV 2022)

「Pytorch」Try to resolve Face Alignment problems by LinearModel,ResNet18,MobileNetV2(PFLD)

Automatic Gaze Analysis ‘in-the-wild’: A Survey

Gaze estimation using MPIIGaze and MPIIFaceGaze

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)