Starred repositories
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Image Forgery Detection and Localization (and related) Papers List
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
基于分词原理修改写的一个过滤敏感词库，可以改成动态，支持返回敏感词，高亮敏感词，替换敏感词等操作，本敏感词收集了5W多个违法词、敏感词、违禁词，已去重，最新追加了将近1W个最新词，几十个矫正词、变异词。
🔥🔥NSFW implement in pytorch（色情图&性感图识别，本程序经过了线上大数据集测试，性能优异效果良好）🔥🔥
Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合
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。
The Largest-scale Chinese Medical QA Dataset： with 26,000,000 question answer pairs.
Chinese medical dialogue data 中文医疗对话数据集
This repository aims to collect all LegalAI data to facilitate the development of intelligent justice systems
ChatGPT 中文指南🔥，ChatGPT 中文调教指南，指令指南，应用开发指南，精选资源清单，更好的使用 chatGPT 让你的生产力 up up up! 🚀
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
NSFW This repository contains many racial slurs, sexual terms, and more. These lists are designed to be used to help censor and filter X-rated words from your application.
7
Updated Dec 11, 2021
Free, open-source Chinese character data
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)