Rank-One Model Editing for Locating and Editing Factual Knowledge in GPT

Overview

Rank-One Model Editing (ROME)

This repository provides an implementation of Rank-One Model Editing (ROME) on auto-regressive transformers (GPU-only). We currently support OpenAI's GPT-2 XL (1.5B) and EleutherAI's GPT-J (6B). The release of a 20B GPT-like model from EleutherAI is expected soon; we hope to support it ASAP.

Feel free to open an issue if you find any problems; we are actively developing this repository and will monitor tickets closely.

Colab ROME Demo

causal tracing GIF

Table of Contents

  1. Installation
  2. Causal Tracing
  3. Rank-One Model Editing (ROME)
  4. CounterFact Dataset
  5. Evaluation
  6. How to Cite

Installation

We recommend conda for managing Python, CUDA, and PyTorch-related dependencies, and pip for everything else. To get started, simply install conda and run:

./scripts/setup_conda.sh

Causal Tracing

notebooks/causal_trace.ipynb demonstrates Causal Tracing, which can be modified to apply tracing to the processing of any statement.

causal tracing GIF

Rank-One Model Editing (ROME)

notebooks/rome.ipynb demonstrates ROME. The API is simple; one simply has to specify a requested rewrite of the following form:

request = {
    "prompt": "{} plays the sport of",
    "subject": "LeBron James",
    "target_new": {
        "str": "football"
    }
}

Several similar examples are included in the notebook.

CounterFact

Description coming soon!

Evaluation

Paper Baselines

We compare ROME against several state-of-the-art model editors. All are implemented in baselines/ in their respective folders. Implementations are not our own; they are adapted slightly to plug into our evaluation system.

Running the Full Evaluation Suite

Description coming soon!

How to Cite

@article{meng2022locating,
  title={Locating and Editing Factual Knowledge in GPT},
  author={Kevin Meng and David Bau and Alex Andonian and Yonatan Belinkov},
  journal={arXiv preprint arXiv:2202.05262},
  year={2022}
}
Owner
Kevin Meng
MIT ugrad interested in interpretability and its applications to NLP, bioinformatics, and robotics.
Kevin Meng
Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis

MLP Singer Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis. Audio samples are available on our demo page.

Neosapience 103 Dec 23, 2022
Official PyTorch implementation of SegFormer

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Figure 1: Performance of SegFormer-B0 to SegFormer-B5. Project page

NVIDIA Research Projects 1.4k Dec 29, 2022
Control the classic General Instrument SP0256-AL2 speech chip and AY-3-8910 sound generator with a Raspberry Pi and this Python library.

GI-Pi Control the classic General Instrument SP0256-AL2 speech chip and AY-3-8910 sound generator with a Raspberry Pi and this Python library. The SP0

Nick Bild 8 Dec 15, 2021
Build Text Rerankers with Deep Language Models

Reranker is a lightweight, effective and efficient package for training and deploying deep languge model reranker in information retrieval (IR), question answering (QA) and many other natural languag

Luyu Gao 140 Dec 06, 2022
Code repository for "It's About Time: Analog clock Reading in the Wild"

it's about time Code repository for "It's About Time: Analog clock Reading in the Wild" Packages required: pytorch (used 1.9, any reasonable version s

52 Nov 10, 2022
A machine learning model for analyzing text for user sentiment and determine whether its a positive, neutral, or negative review.

Sentiment Analysis on Yelp's Dataset Author: Roberto Sanchez, Talent Path: D1 Group Docker Deployment: Deployment of this application can be found her

Roberto Sanchez 0 Aug 04, 2021
FastFormers - highly efficient transformer models for NLU

FastFormers FastFormers provides a set of recipes and methods to achieve highly efficient inference of Transformer models for Natural Language Underst

Microsoft 678 Jan 05, 2023
Phomber is infomation grathering tool that reverse search phone numbers and get their details, written in python3.

A Infomation Grathering tool that reverse search phone numbers and get their details ! What is phomber? Phomber is one of the best tools available fo

S41R4J 121 Dec 27, 2022
PyTorch impelementations of BERT-based Spelling Error Correction Models.

PyTorch impelementations of BERT-based Spelling Error Correction Models

Heng Cai 209 Dec 30, 2022
Which Apple Keeps Which Doctor Away? Colorful Word Representations with Visual Oracles

Which Apple Keeps Which Doctor Away? Colorful Word Representations with Visual Oracles (TASLP 2022)

Zhuosheng Zhang 3 Apr 14, 2022
๐Ÿ›ธ Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy

spacy-transformers: Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy This package provides spaCy components and architectures to use tr

Explosion 1.2k Jan 08, 2023
Code for paper: An Effective, Robust and Fairness-awareHate Speech Detection Framework

BiQQLSTM_HS Code and data for paper: Title: An Effective, Robust and Fairness-awareHate Speech Detection Framework. Authors: Guanyi Mou and Kyumin Lee

Guanyi Mou 2 Dec 27, 2022
State-of-the-art NLP through transformer models in a modular design and consistent APIs.

Trapper (Transformers wRAPPER) Trapper is an NLP library that aims to make it easier to train transformer based models on downstream tasks. It wraps h

Open Business Software Solutions 42 Sep 21, 2022
A collection of GNN-based fake news detection models.

This repo includes the Pytorch-Geometric implementation of a series of Graph Neural Network (GNN) based fake news detection models. All GNN models are implemented and evaluated under the User Prefere

SafeGraph 251 Jan 01, 2023
Wind Speed Prediction using LSTMs in PyTorch

Implementation of Deep-Forecast using PyTorch Deep Forecast: Deep Learning-based Spatio-Temporal Forecasting Adapted from original implementation Setu

Onur Kaplan 151 Dec 14, 2022
Training code for Korean multi-class sentiment analysis

KoSentimentAnalysis Bert implementation for the Korean multi-class sentiment analysis ์™œ ํ•œ๊ตญ์–ด ๊ฐ์ • ๋‹ค์ค‘๋ถ„๋ฅ˜ ๋ชจ๋ธ์€ ๊ฑฐ์˜ ์—†๋Š” ๊ฒƒ์ผ๊นŒ?์—์„œ ์‹œ์ž‘๋œ ํ”„๋กœ์ ํŠธ Environment: Pytorch, Da

Donghoon Shin 3 Dec 02, 2022
A 30000+ Chinese MRC dataset - Delta Reading Comprehension Dataset

Delta Reading Comprehension Dataset ๅฐ้”้–ฑ่ฎ€็†่งฃ่ณ‡ๆ–™้›† Delta Reading Comprehension Dataset (DRCD) ๅฑฌๆ–ผ้€š็”จ้ ˜ๅŸŸ็น้ซ”ไธญๆ–‡ๆฉŸๅ™จ้–ฑ่ฎ€็†่งฃ่ณ‡ๆ–™้›†ใ€‚ ๆœฌ่ณ‡ๆ–™้›†ๆœŸๆœ›ๆˆ็‚บ้ฉ็”จๆ–ผ้ท็งปๅญธ็ฟ’ไน‹ๆจ™ๆบ–ไธญๆ–‡้–ฑ่ฎ€็†่งฃ่ณ‡ๆ–™้›†ใ€‚ ๆœฌ่ณ‡ๆ–™้›†ๅพž2,108็ฏ‡

272 Dec 15, 2022
Rethinking the Truly Unsupervised Image-to-Image Translation - Official PyTorch Implementation (ICCV 2021)

Rethinking the Truly Unsupervised Image-to-Image Translation (ICCV 2021) Each image is generated with the source image in the left and the average sty

Clova AI Research 436 Dec 27, 2022
Codes to pre-train Japanese T5 models

t5-japanese Codes to pre-train a T5 (Text-to-Text Transfer Transformer) model pre-trained on Japanese web texts. The model is available at https://hug

Megagon Labs 37 Dec 25, 2022
Bpe algorithm can finetune tokenizer - Bpe algorithm can finetune tokenizer

"# bpe_algorithm_can_finetune_tokenizer" this is an implyment for https://github

ๅผ ๅš 1 Feb 02, 2022