dptam

BayesianTransferLearning

BIG-bench

Beyond the Imitation Game collaborative benchmark for enormous language models

BIG-Bench-Hard

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

CLIP

Contrastive Language-Image Pretraining

continual-learning

PyTorch implementation of various methods for continual learning (XdG, EWC, online EWC, SI, LwF, DGR, DGR+distill, RtF, iCaRL).

curvlinops

scipy linear operators for the Hessian, Fisher/GGN, and more in PyTorch

dptam.github.io

factCC

Resources for the "Evaluating the Factual Consistency of Abstractive Text Summarization" paper

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

FLAN

frank

FRANK: Factuality Evaluation Benchmark

mend

MEND: Fast Model Editing at Scale

metaseq

Repo for external large-scale work

git-theta

git extension for {collaborative, communal, continual} model development

MFMA

Factual consistency checking model for abstractive summaries (NAACL-22 Findings)

modifying-memory

open_clip

pet

This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

promptsource

Toolkit for creating, sharing and using natural language prompts.

PyTorchDiscreteFlows

Discrete Normalizing Flows implemented in PyTorch

realistic_evaluation_of_model_merging

SummEval

Resources for the "SummEval: Re-evaluating Summarization Evaluation" paper

swa_gaussian

Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"

t-few

Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"

tangent_task_arithmetic

Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".

task_vectors

Editing Models with Task Arithmetic

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

uda

Unsupervised Data Augmentation (UDA)

UDA_pytorch

UDA(Unsupervised Data Augmentation) implemented by pytorch

wise-ft

Robust fine-tuning of zero-shot models