Starred repositories
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
A Comprehensive Toolkit for High-Quality PDF Content Extraction
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
tensorflow实战练习,包括强化学习、推荐系统、nlp等
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
推荐系统入门教程,在线阅读地址:https://datawhalechina.github.io/fun-rec/
pycorrector is a toolkit for text error correction. 文本纠错,实现了Kenlm,T5,MacBERT,ChatGLM3,Qwen2.5等模型应用在纠错场景,开箱即用。
A code-first agent framework for seamlessly planning and executing data analytics tasks.
Not Suitable for Work (NSFW) classification using deep neural network Caffe models.
keras implement of transformers for humans
text2vec, text to vector. 文本向量表征工具,把文本转化为向量矩阵,实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型,开箱即用。
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
General technology for enabling AI capabilities w/ LLMs and MLLMs
Deep Learning Tutorial notes and code. See the wiki for more info.
中文 NLP 预处理、解析工具包,准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com
A high performance and generic framework for distributed DNN training
fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.
Aggregates RSS and web content(Calibre recipe), sends to Kindle, and includes an e-ink optimized online reader.