LaLa Trainers Launcher

[TMLR 2024] Efficient Large Language Models: A Survey

This dataset contains results from all rounds of Adversarial Nibbler. This data includes adversarial prompts fed into public generative text2image models and validations for unsafe images. There wi…

A list of all named GANs!

Python Wrapped LibFFM

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Diagrams for visualizing neural network architecture (Created with diagrams.net)

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Flops counter for convolutional networks in pytorch framework

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

This is the code of ICLR 2022 Oral paper 'Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization'.

A data augmentations library for audio, image, text, and video.

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

Python implementation of CMA-ES

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

A Non-Euclidean Rendering Engine for 3D scenes.

Code for visualizing the loss landscape of neural nets

MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

Approximating Wasserstein distances with PyTorch

DCT (discrete cosine transform) functions for pytorch

auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

A smaller subset of 10 easily classified classes from Imagenet, and a little more French

95.47% on CIFAR10 with PyTorch