Generative Pre-trained Transformer in PyTorch

🚀🚀🚀 A collection of some awesome public YOLO object detection series projects.

Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"

A compilation of the best multi-agent papers

Julia Implementation of Transformer models

The official PyTorch implementation of the paper "SAITS: Self-Attention-based Imputation for Time Series". A fast and state-of-the-art (SOTA) deep-learning neural network model for efficient time-series imputation (impute multivariate incomplete time series containing NaN missing data/values with machine learning). https://arxiv.org/abs/2202.08516

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

My Attempt(s) In The World Of ML/DL....

Explainable Neural Subgraph Matching with Graph Learnable Multi-hop Attention Networks

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

[CVPR 2024] Official implementation of the paper "Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement"

[CVPRW2024 FGVC11 (Best paper award)] Official pytorch implementation of the paper: "ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery"

transformer based chatbot with pytorch

Zeta implemantion of "Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers"

A browser extension that redirects bbc news visits to bbc weather

Attention temporal convolutional network for EEG-based motor imagery classification

[TGRS 2024] The official repository for Journal Article “FactoFormer: Factorized Hyperspectral Transformers with Self-Supervised Pre-Training”, Accepted to IEEE Transactions on Geoscience and Remote Sensing, December 2023.

Own version of the original transformer

Scenic: A Jax Library for Computer Vision Research and Beyond