kmeng01/memit

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

46
/ 100
Emerging

This project helps machine learning engineers and researchers efficiently update the knowledge within large language models. You input specific factual corrections or new information, like changing "LeBron James plays football" to "LeBron James plays basketball," and it outputs a modified language model that reflects these changes, potentially thousands at once. It's designed for those who work directly with transformer-based language models and need to inject new facts or correct misinformation.

543 stars. No commits in the last 6 months.

Use this if you need to programmatically edit or update many facts directly within a pre-trained transformer model's memory without retraining the entire model.

Not ideal if you are an end-user of a language model and don't have the technical expertise to work with model weights and Python code.

large-language-models model-editing knowledge-injection transformer-models machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

543

Forks

72

Language

Python

License

MIT

Last pushed

Jan 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kmeng01/memit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.