CompBench evaluates the comparative reasoning of multimodal large language models (MLLMs) with 40K image pairs and questions across 8 dimensions of relative comparison: visual attribute, existence,…

Neural Tangents for TensorFlow 2.x.

Course Presentation for STA4273 2021 Winter, University of Toronto

TruthfulQA: Measuring How Models Imitate Human Falsehoods

Inference code for Llama models

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Unsupervised text tokenizer for Neural Network-based text generation.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implicit Bayesian Inference"

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

Public repo for HF blog posts

The open source version of the AWS CLI User Guide

MariaDB server is a community developed fork of MySQL server. Started by core members of the original MySQL team, MariaDB actively works with outside developers to deliver the most featureful, stab…

Deep learning library for Java, with fully connected, convolutional, and recurrent layers. Also features many gradient descent optimization algorithms.

An Engine-Agnostic Deep Learning Framework in Java

Statistical Machine Intelligence & Learning Engine

Amazon RDS Support Tools contains utilities, sql, scripts and views which are useful in a RDS environment

Lightweight library of stochastic gradient MCMC algorithms written in JAX.

[ICCV 2017] Torch code for Grad-CAM

Code release for ConvNeXt model

An empirical study on evaluation metrics of generative adversarial networks.

GANs with spectral normalization and projection discriminator

ExCon: Explanation-driven Supervised Contrastive Learning

Generic image compressor for machine learning. Pytorch code for our paper "Lossy compression for lossless prediction".

A PyTorch library and evaluation platform for end-to-end compression research

Official Pytorch implementation of "DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network" (CVPR'21)