L
LightThinker
zjunlp/LightThinker
[EMNLP 2025] LightThinker: Thinking Step-by-Step Compression
★165stars
Python
MIT
Updated: 3w ago
📋 Project at a Glance
Tap to expand
What's this?A , built with Python open-source project in the Models category, core strengths: artificial-intelligence/compression
Who made it?Maintained by zjunlp team, 165⭐ on GitHub, #2356 out of 3201 in Models
Why does it exist?The zjunlp team recognized that existing artificial-intelligence tools in Models were hard to use. LightThinker was designed to make compression more accessible.
What can it do?Key use cases: efficiency, generation, large-language-model
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/zjunlp/LightThinker
🔗 github.com/zjunlp/LightThinker
Topics
artificial-intelligencecompressionefficiencygenerationlarge-language-modellightthinkernatural-language-processingreasoningslow-thinkingstep-by-step