Finetune Llama 3.3, DeepSeek-R1, Reasoning, Phi-4 & Gemma 2 LLMs 2x faster with 70% less memory

Various Algorithms for Short Text Mining

Fast and memory-efficient exact attention

Repo for NAACL 2025 Paper "Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization"

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!

"MiniRAG: Making RAG Simpler with Small and Free Language Models"

WDEL是一个基于Wikidata知识库的实体链接系统。

Stay on top of trending topics on social media and the web with AI

Annif is a multi-algorithm automated subject indexing tool for libraries, archives and museums.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

State of the Art Natural Language Processing

Ext4 file system driver for Windows

支持 Android、iOS、macOS、Windows 平台的 Subsonic/Navidrome/Jellyfin/Emby/AudioStation 客户端。

cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，支持sso登录，大数据平台对接，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU，边缘计算，标注平台，自动化标注，大模型微调，vllm大模型推理，llmops，私有知识库，AI模型应用商店，支持模型一键开发/推理/微调，支持国产cpu/gpu/npu芯片，支持R…

An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

A tool for exploring each layer in a docker image

This repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-shot classification with Huggingface.

An easy way to chunk spaCy docs.

Train your custom NER Pipeline with Spacy in 5 simple steps

SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding

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

大语言模型微调，Qwen2VL、Qwen2、GLM4指令微调

Source code for "Packed Levitated Marker for Entity and Relation Extraction"

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Code for explaining and evaluating late chunking (chunked pooling)

Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

🎈 Updated daily! A list of popular BitTorrent Trackers! / 每天更新！全网热门 BT Tracker 列表！

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。