nicola-decao/KnowledgeEditor
Code for Editing Factual Knowledge in Language Models
This tool helps researchers and AI practitioners modify the factual information stored within large language models without needing to retrain them from scratch. You provide an existing language model and the specific factual changes you want to make, and it outputs an updated model that reflects those changes. It's for anyone who needs to correct or update knowledge in language models efficiently.
142 stars. No commits in the last 6 months.
Use this if you need to quickly and precisely alter specific factual knowledge within a pre-trained language model, such as correcting an outdated fact or adding new information.
Not ideal if you want to teach a language model entirely new skills, capabilities, or generalize its understanding beyond specific factual edits.
Stars
142
Forks
15
Language
Python
License
MIT
Category
Last pushed
Jan 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/nicola-decao/KnowledgeEditor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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 &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
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.