Search

Train transformer language models with reinforcement learning.

Ongoing research training transformer models at scale

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

Corpus legislativo brasileiro em larga escala e modelo Transformer causal treinado do zero em PyTorch puro.

An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.

TimeGPT-2.1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

A Jest transformer with source map support that lets you use Jest to test projects written in TypeScript.

Axios transformer/interceptor that converts snake_case/camelCase

🐊 Pluggable and configurable JavaScript Linter, code transformer and formatter with superpowers 💪: built-in support of js, jsx, ts, markdown, yaml, toml, json and ignore. Write declarative codemods in a simplest possible way 😏

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Fast inference engine for Transformer models

experimental CPS transformer for dotty

Eclipse Transformer provides tools and runtime components that transform Java binaries, such as individual class files and complete JARs and WARs, mapping changes to Java packages, type names, and related resource names.

A concise but complete full-attention transformer with a set of promising experimental features from various papers

快速上手AI理论及应用实战：基础知识、Transformer、NLP、ML、DL、竞赛。含大量注释及数据集，力求每一位能看懂并复现。

DeepImageSearch is a Python library for fast and accurate image search. It offers seamless integration with Python, GPU support, and advanced capabilities for identifying complex image patterns using the Vision Transformer models.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.

An extremely fast CSS parser, transformer, bundler, and minifier written in Rust.

This repository is a paper digest of Transformer-related approaches in visual tracking tasks.

De Novo Mass Spectrometry Peptide Sequencing with a Transformer Model

A curated list of Decision Transformer resources (continually updated)

Foundation Models for Genomics & Transcriptomics

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

CVPR 2024-Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention

Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various configurations for the Transformer 5 models including Qwen 3.0

Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding