Starred repositories
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi...
No fortress, purely open ground. OpenManus is Coming.
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le...
Production-ready platform for agentic workflow development.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
开放式的缠论python实现框架,支持形态学/动力学买卖点分析计算,多级别K线联立,区间套策略,可视化绘图,多种数据接入,策略开发,交易系统对接;
TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning 🔥 ⚡ 🌈
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i...
State-of-the-Art Text Embeddings
TensorFlow code and pre-trained models for BERT
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Facilitating the design, comparison and sharing of deep text matching models.
复盘所有NLP比赛的TOP方案,只关注NLP比赛,持续更新中!
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, date/time, etc. in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV)....
Language, engine, and tooling for expressing, testing, and evaluating composable language rules on input strings.
Mining synonyms from unstructured and semi-structured data
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
综合了同义词词林扩展版与知网(Hownet)的词语相似度计算方法,词汇覆盖更多、结果更准确。
Train Wikidata with word2vec for word embedding tasks