QuintinPope

academic-budget-bert

Repository containing code for "How to Train BERT with an Academic Budget"

Basin-connectivity-SLT

Trying to connect basin connectivity between models with the tools of singular learning theory

CLOSS

Code that implements the CLOSS method of adversarial attack on language-model based classifiers.

dioptra

Test Software for the Characterization of AI Technologies

epi-smt

FASTA_Perceiver

Code to prepare FASTA data and train a perceiver language model with masked language modeling

grokking

PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"

learn2gradienthack

Uses learn2learn to train a fully connected network that implements the constant function and resists SGD

LM-data-curation

Code to investigate how LLMs can curate their own training data.

rome

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

QuintinPope/CLOSS

Code that implements the CLOSS method of adversarial attack on language-model based classifiers.

QuintinPope/LM-data-curation

Code to investigate how LLMs can curate their own training data.

QuintinPope/Basin-connectivity-SLT

Trying to connect basin connectivity between models with the tools of singular learning theory

QuintinPope/learn2gradienthack

Uses learn2learn to train a fully connected network that implements the constant function and resists SGD

QuintinPope/rome

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

QuintinPope/academic-budget-bert

Repository containing code for "How to Train BERT with an Academic Budget"

QuintinPope/dioptra

Test Software for the Characterization of AI Technologies

QuintinPope/epi-smt

QuintinPope/FASTA_Perceiver

Code to prepare FASTA data and train a perceiver language model with masked language modeling

QuintinPope/grokking

PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"

QuintinPope/knowledge-neurons

A library for finding knowledge neurons in pretrained transformer models.

QuintinPope/methylmercury-website

Code for a website showing a pharamacokinetic model of methylmercury elimination in a human body.

QuintinPope/microbiome_transformers

QuintinPope/perceiver-pytorch

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

QuintinPope/pz_dilemma

petting zoo game theory

QuintinPope/Reflectivity_benchmarks

Datasets to probe language model competence at various subtasks associated with reflectivity / metacognition / etc

QuintinPope/S2ML-Art-Generator

Two notebooks which allow the use of VQGAN+CLIP as well as CLIP-guided diffusion for generating images from text or image prompts. Includes ESRGAN implementation for upscaling and ffmpeg for video generation.

QuintinPope/Terrible_PRNG

A VERY bad pseudorandom number generator.

QuintinPope/TextAttack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/latest/

QuintinPope/Unsupervised_behavior_evaluation

Scalable and flexible characterization of language model behavior

QuintinPope/val-eval

Systematically uncover differences in language model behaviors and "values"