zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
This framework helps you update, insert, or remove specific facts or behaviors in large language models (LLMs) without needing to retrain the entire model. You provide the LLM and the knowledge you want to change, and the framework helps you ensure the LLM outputs updated information. It's designed for AI researchers and practitioners who need precise control over their LLM's knowledge.
2,744 stars. Actively maintained with 3 commits in the last 30 days.
Use this if you need to correct factual errors, update outdated information, or steer the behavior of an LLM after it has already been trained.
Not ideal if you want to make broad, systemic changes across the entire LLM's understanding, as this tool focuses on targeted knowledge adjustments.
Stars
2,744
Forks
347
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/zjunlp/EasyEdit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.
PKU-Alignment/align-anything
Align Anything: Training All-modality Model with Feedback