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

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Entropy Based Sampling and Parallel CoT Decoding

Computations and statistics on manifolds with geometric structures.

⚡ Competitive Programming Library

A self-supervised learning framework for audio-visual speech

Code for the ALiBi method for transformer language models (ICLR 2022)

Pytorch implementation of Hyperspherical Variational Auto-Encoders

Tensorflow implementation of Hyperspherical Variational Auto-Encoders

roBERTa training for SQuAD

This is a repository for the paper on testing inductive bias with scaled-down RoBERTa models.