@yhslgg: Everyone! Tsinghua University NLP Lab has put all 269 open-source projects on GitHub. AI folks will definitely miss out if they don't bookmark them. The project is called: THUNLP, Tsinghua University Natural Language Processing Lab. In a nutshell: 269 public repositories covering large model training, knowledge graphs, Prompt...

X AI KOLs Timeline News
nlp open-source github tsinghua large-language-models knowledge-graphs prompt-learning

Summary

Tsinghua University NLP Lab open-sourced 269 projects on GitHub, covering large model training, knowledge graphs, Prompt learning, parameter fine-tuning, and more, including well-known projects such as OpenPrompt, OpenNRE, OpenKE, UltraChat, and OpenDelta. Suitable for AI researchers and application developers.

Everyone! Tsinghua University NLP Lab has put all 269 open-source projects on GitHub. AI folks will definitely miss out if they don't bookmark them. The project is called: THUNLP, Tsinghua University Natural Language Processing Lab. In a nutshell: 269 public repositories covering large model training, knowledge graphs, Prompt learning, parameter fine-tuning, multi-turn dialogue... all open-source and free. Here are a few representative projects: (1) OpenPrompt (4,900 stars) — An open-source Prompt learning framework for studying how to write better prompts for large models, widely used in academia. (2) OpenNRE (4,500 stars) — A neural relation extraction toolkit that automatically identifies relationships between entities in text, essential for knowledge graphs. (3) OpenKE (4,000 stars) — A knowledge embedding toolkit that converts entities and relations in knowledge graphs into vectors for reasoning and completion. (4) UltraChat (2,900 stars) — A high-quality multi-turn dialogue dataset + model, ready to use as training data for dialogue AI. (5) OpenDelta (1,000 stars) — A parameter-efficient fine-tuning library that allows you to customize large models by tuning only a few parameters without full training, saving time and money. Research directions also cover: large model distillation, LLM agents, long-context attention mechanisms, mixture of experts (MoE), multi-modal visual grounding... basically any hot area in NLP and large models has a corresponding open-source project from this lab. The results are published in top conferences like ACL and ICLR. This is real academic work, not fluff. Whether you're doing AI research, building large model applications, looking for high-quality training data, or just want to understand the cutting edge of NLP — bookmark this organization. Browse it from time to time, and you'll always find something useful. GitHub: http://github.com/THUNLP Share this good stuff with friends who need it. #清华NLP #开源AI #大模型 #老杨啊分享
Original Article
View Cached Full Text

Cached at: 06/08/26, 11:34 PM

Hey everyone! Tsinghua University’s NLP Lab has put all 269 open-source projects on GitHub. If you’re into AI, you’ll definitely want to bookmark this.

The project is called: THUNLP, Tsinghua University Natural Language Processing Lab.

In a nutshell: 269 public repositories covering large model training, knowledge graphs, prompt learning, parameter-efficient fine-tuning, multi-turn dialogue… all open source and free.

Here are a few representative projects:

(1) OpenPrompt (4900 stars) — Open-source Prompt learning framework for researching how to write better prompts for large models. Widely used in academia.

(2) OpenNRE (4500 stars) — Neural relation extraction toolkit that automatically identifies relationships between entities from text. Essential for building knowledge graphs.

(3) OpenKE (4000 stars) — Knowledge embedding toolkit that converts entities and relations in knowledge graphs into vectors for reasoning and completion.

(4) UltraChat (2900 stars) — High-quality multi-turn dialogue dataset + model. Ready-to-use training data for dialogue AI.

(5) OpenDelta (1000 stars) — Parameter-efficient fine-tuning library. No need for full training — just adjust a small number of parameters to customize large models, saving cost and time.

Research directions also include: large model distillation, LLM Agents, long-context attention mechanisms, mixture of experts (MoE), multimodal visual grounding… Basically, for every hot direction in NLP and large models, this lab has a corresponding open-source project.

Results published at top conferences like ACL, ICLR — truly academic work, not just filler.

For AI researchers, large model practitioners, anyone looking for high-quality training data, or those wanting to understand cutting-edge NLP directions — bookmark this organization and browse occasionally. You’ll discover something new every time.

GitHub: http://github.com/THUNLP

Share this great stuff with friends who need it.

#TsinghuaNLP #OpenSourceAI #LargeModel #OldYangShares

Similar Articles

@FakeMaidenMaker: Folks, we've dug up another AI engineering treasure: Hands-On-AI-Engineering. Just open-sourced, it already hit 2.3K stars. One repo stuffed with over 50 real AI projects that you can run directly. The most practical part is it doesn't talk about vague theories; each project is a complete little…

X AI KOLs Timeline

Recommends the freshly open-sourced GitHub repo Hands-On-AI-Engineering with 2.3K stars, containing over 50 runnable AI projects covering RAG, AI agent, OCR, and more. Each project provides full code and instructions, suitable for hands-on learning.

@xiaoying_eth: These 10 GitHub repositories shouldn't only be known by programmers. 1. TradingAgents – an AI investment analyst team. Four analysts (fundamentals, sentiment, news, technical) discuss strategies together, backed by a risk manager and execution agents. It's like stuffing a mini Wall Street team into your...

X AI KOLs Timeline

Recommends 10 practical open-source GitHub projects, covering AI investment analysis, multi-model chat client, video generation engine, financial terminal, automated short video generation, AI email client, voice cloning, domain information collection, Claude skill sets, and API integration, etc.

@wsl8297: When learning AI, the scariest part is getting stuck at "understanding the theory" and freezing when it's time to write code — not knowing where to start, and unable to find decent practice projects. I unearthed a practical treasure trove on GitHub: AI-Project-Gallery. It collects 30+ high-quality AI projects, covering classic topics like house price prediction and disease classification, as well as hot applications like Gemini chatbot and document generator...

X AI KOLs Timeline

This post shares a curated GitHub repository containing over 30 practical AI projects, covering domains from regression to generative AI, with many end-to-end examples, suitable for learners and developers.

@waveking1314: Holy cow, there are a ton of ridiculously free projects on GitHub. Many of them can already replace the software you're paying for monthly. 1. TradingAgents AI multi-agent quantitative trading framework https://github.com/TauricResearch/…

X AI KOLs Timeline

Recommends 10 high-quality GitHub open-source projects covering quantitative trading, AI chat, video generation, financial terminal, short video creation, email assistant, voice cloning, OSINT analysis, AI skill library, and API integration platform, many of which are free alternatives to paid software.

@GenhuiP78950: Open-sourced my AI tools from the past six months. Not a big project, just scripts I use daily – transcribing Douyin/Bilibili videos, podcast-to-text, WeChat public account articles, industry news scanning… 11 in total. Used them privately, now unified with install scripts and docs.

X AI KOLs Timeline

Open-sourced a collection of 11 AI tool scripts for collecting and transcribing content from multiple channels like Douyin, Bilibili, and WeChat public accounts, making it easy to build a personal knowledge base. Supports direct installation by agents such as Claude Code, Codex, etc.