coallaoh

Principles

NeglectedFreeLunch

twitter2slack

B-cos

B-cos Networks: Alignment is All we Need for Interpretability

coallaoh.github.io

email_students

arnheim

bdl-benchmarks

Bayesian Deep Learning Benchmarks

coco-annotation-tool

create-react-app-auth-amplify

Implements a basic authentication flow for signing up/signing in users as well as protected client side routing using AWS Amplify.

dash-sample-apps

Open-source demos hosted on Dash Gallery

Detic

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

Efficient-Dataset-Condensation

Official PyTorch implementation of "Dataset Condensation via Efficient Synthetic-Data Parameterization" (ICML'22)

FastChat

An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

imagenet-annotation-tool

LabelMeAnnotationTool

Source code for the LabelMe annotation tool.

llama

Inference code for LLaMA models

macroeconomic-data-visualization

NeglectedFreeLunch-1

Otter

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

PfLayer

Learning Features with Parameter-Free Layers, ICLR 2022

pytorch-transformer-ts

Repository of Transformer based PyTorch Time Series Models

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Quantus

Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations

scalabletrustworthyai.github.io

uncertainty-baselines

High-quality implementations of standard and SOTA methods on a variety of tasks.

w-ood

YaLM-100B

Pretrained language model with 100B parameters