Stars
The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
A cross-platform, customizable science fiction terminal emulator with advanced monitoring & touchscreen support.
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
A game theoretic approach to explain the output of any machine learning model.
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
Datasets, Transforms and Models specific to Computer Vision
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.
Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
A faster pytorch implementation of faster r-cnn
👮♂️The sensitive word tool for java.(敏感词/违禁词/违法词/脏词。基于 DFA 算法实现的高性能 java 敏感词过滤工具框架。内置支持单词标签分类分级。请勿发布涉及政治、广告、营销、翻墙、违反国家法律法规等内容。高性能敏感词检测过滤组件，附带繁体简体互换，支持全角半角互换，汉字转拼音，模糊搜索等功能。)
Model interpretability and understanding for PyTorch
A PyTorch Implementation of Single Shot MultiBox Detector
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
A collection of loss functions for medical image segmentation
SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese
A unified evaluation framework for large language models
A Python package to assess and improve fairness of machine learning models.
Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"
pytorch1.0 updated. Support cpu test and demo. (Use detectron2, it's a masterpiece)
Extensible, parallel implementations of t-SNE
Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。
convert dataset to coco/voc format