collin-burns

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

marvin

✨ Build AI interfaces that spark joy

PromptPapers

Must-read papers on prompt-based tuning for pre-trained language models.

generative_inpainting

DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

weak-to-strong

RL4LMs

A modular RL library to fine-tune language models to human preferences

chess-alpha-zero

Chess reinforcement learning by AlphaGo Zero methods.

keyboard

⌨ Toward a more useful keyboard

CLIP_prefix_caption

Simple image captioning model

diplomacy_cicero

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

PrefixTuning

Prefix-Tuning: Optimizing Continuous Prompts for Generation

EfficientZero

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

natural-adv-examples

A Harder ImageNet Test Set (CVPR 2021)

mistral

Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.

TruthfulQA

TruthfulQA: Measuring How Models Imitate Human Falsehoods

linformer-pytorch

My take on a practical implementation of Linformer for Pytorch.

unrestricted-adversarial-examples

Contest Proposal and infrastructure for the Unrestricted Adversarial Examples Challenge

Awesome-Sentence-Embedding

A curated list of research papers in Sentence Reprsentation Learning and a sts leaderboard of sentence embeddings.

imagenet-r

ImageNet-R(endition) and DeepAugment (ICCV 2021)

backprop

Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.

elk

Keeping language models honest by directly eliciting knowledge encoded in their activations.

PTR

Prompt Tuning with Rules

treason

A clone of the card game Coup written in Node.js

3db

A framework for analyzing computer vision models with simulated data

interpretability

PAIR.withgoogle.com and friend's work on interpretability methods

BIFI

[ICML 2021] Break-It-Fix-It: Unsupervised Learning for Program Repair

xsum_hallucination_annotations

Faithfulness and factuality annotations of XSum summaries from our paper "On Faithfulness and Factuality in Abstractive Summarization" (https://www.aclweb.org/anthology/2020.acl-main.173.pdf).

pycallcc

Discount jupyter.

natural-instructions-v1

Benchmarking Generalization to New Tasks from Natural Language Instructions

awesome-disentanglement-in-nlp

A curated list of disentanglement in NLP. :-)