EasyEdit logo

EasyEdit

zjunlp/EasyEdit

Easy-to-use knowledge editing framework for LLMs

GraphCanon updated 1w · GitHub synced 1w

2.9k stars371 forksLast push 1mo Jupyter Notebook MIT

Decision brief

EasyEdit is an easy-to-use knowledge editing framework for LLMs tailored to model customization and optimization.

Good fit when

  • In situations where you need a user-friendly tool for customizing and optimizing large language models.
  • You are working with Python 3.9 or above as EasyEdit explicitly supports these versions.

Avoid when

  • If your project requires minimal GPU memory usage; tools like AdaLoRA can operate with about 29GB on llama-2-7B, whereas EasyEdit may demand more resources.
  • You require a solution that works exclusively within CPU-only environments without the option to adjust for specific backends via tools such as uv.
Requirements:
Installation requires Python 3.9+ and Conda.

Observed Jul 14, 2026 · Source: enrich:decision_facts

Verify the decision

Adoption

Package downloads where a registry match exists. GitHub stars (2,895) are secondary evidence.

Docker Hub pulls (30d)
935·Docker Hub API·1w

Maintenance and security

Full trust report
Maintenance
Active (24d since push)
As of 1w
Provenance
Not a fork · Organization account
As of 1w
Security (OSV)
25 low (25 low)
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/zjunlp/EasyEdit

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs targeted at model customization and optimization.

Capability facts

Deploy
Self-host

Source: dockerfile:Dockerfile · Aug 8, 2026

Docker
Dockerfile present

Source: dockerfile:Dockerfile · Aug 8, 2026

Languages
jupyter notebook

Source: github.language · Aug 8, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 8, 2026)

**Note: Please use Python 3.9+ for EasyEdit**
Source link

Tags

README

Requirements

🔧Pip Installation

Note: Please use Python 3.9+ for EasyEdit To get started with pip, simply install conda and run:

git clone https://github.com/zjunlp/EasyEdit.git
cd EasyEdit
conda create -n EasyEdit python=3.10
conda activate EasyEdit
pip install -r requirements.txt

⚡uv Installation

You can also use uv for faster dependency installation:

git clone https://github.com/zjunlp/EasyEdit.git
cd EasyEdit
conda create -n EasyEdit python=3.10
conda activate EasyEdit
pip install uv
uv pip install --torch-backend cu128 -r requirements.txt

If you are installing for a CPU-only environment, replace the last command with:

uv pip install --torch-backend cpu -r requirements.txt

After installation, you can verify the environment with:

uv pip check

Editing GPU memory usage

Our results are all based on the default configuration

llama-2-7Bchatglm2gpt-j-6bgpt-xl
FT60GB58GB55GB7GB
SERAC42GB32GB31GB10GB
IKE52GB38GB38GB10GB
MEND46GB37GB37GB13GB
KN42GB39GB40GB12GB
ROME31GB29GB27GB10GB
MEMIT33GB31GB31GB11GB
AdaLoRA29GB24GB25GB8GB
GRACE27GB23GB6GB
WISE34GB27GB7GB

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.