Starred repositories
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
A Simple and Versatile Framework for Object Detection and Instance Recognition
Resources and Implementations of Generative Adversarial Nets: GAN, DCGAN, WGAN, CGAN, InfoGAN
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.
Toolkit for creating, sharing and using natural language prompts.
MTEB: Massive Text Embedding Benchmark
Text preprocessing, representation and visualization from zero to hero.
CTPN + DenseNet + CTC based end-to-end Chinese OCR implemented using tensorflow and keras
Material inspired stylesheet for PySide2, PySide6, PyQt5 and PyQt6
A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
Anaconda turns your Sublime Text 3 in a full featured Python development IDE including autocompletion, code linting, IDE features, autopep8 formating, McCabe complexity checker Vagrant and Docker s…
Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"
Awesome Deep Learning papers for industrial Search, Recommendation and Advertisement. They focus on Embedding, Matching, Pre-Ranking, Ranking (CTR/CVR prediction), Post Ranking, Relevance, LLM, Rei…
TFX is an end-to-end platform for deploying production ML pipelines
MoBA: Mixture of Block Attention for Long-Context LLMs
OpenDAN is an open source Personal AI OS , which consolidates various AI modules in one place for your personal use.
Netease Youdao's open-source embedding and reranker models for RAG products.
中文对话0.2B小模型(ChatLM-Chinese-0.2B),开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调,给出三元组信息抽取微调示例。
Documents, papers and codes related to Natural Language Processing, including Topic Model, Word Embedding, Named Entity Recognition, Text Classificatin, Text Generation, Text Similarity, Machine Tr…
Crime assistant including crime type prediction and crime consult service based on nlp methods and crime kg,罪名法务智能项目,内容包括856项罪名知识图谱, 基于280万罪名训练库的罪名预测,基于20W法务问答对的13类问题分类与法律资讯问答功能.
Code for paper Fine-tune BERT for Extractive Summarization
An open-source chatgpt tool ecosystem where you can combine tools with chatgpt and use natural language to do anything.
Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States