Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Released model weights, reference implementations and architecture research.
Signals: large-language-models, llm, foundation-models, transformer, gpt, llama, mistral, qwen
1,455 results
OpenAI compatible API for LLMs and embeddings (LLaMA, Vicuna, ChatGLM and many others)
A copilot for your terminal
Using Transformer deep learning architecture to predict stock prices.
Train a language model to chat like you using your personal conversations from WhatsApp, Telegram, Signal, or other platforms.
[TNNLS] A Comprehensive Survey of Awesome Visual Transformer Literatures.
Easy Attributed String Creator
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to build applications around language servers.
(CVPR 2022) TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers.
[TPAMI2023] RestoreFormer++
[CoRL 2022] SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
An electrocardiogram analysis foundation model.
[AAAI2023] A PyTorch implementation of PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction.
Implementation for CenterFormer: Center-based Transformer for 3D Object Detection (ECCV 2022)
[CoRL'22] PlanT: Explainable Planning Transformers via Object-Level Representations
List of molecules (small molecules, RNA, peptide, protein, enzymes, antibody, and PPIs) conformations and molecular dynamics (force fields) using generative artificial intelligence and deep learning
PyTorch implementation of a collections of scalable Video Transformer Benchmarks.
JAX library for training sub-4B foundation models for edge
[NeurIPS 2021 Spotlight] & [IJCV 2024] SOFT: Softmax-free Transformer with Linear Complexity
Laravel 5 JSON API Transformer Package
MoH: Multi-Head Attention as Mixture-of-Head Attention
Official implementation of All Atom Diffusion Transformers (ICML 2025)
💬 Chatbot web app + HTTP and Websocket endpoints for LLM inference with the Petals client
This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Source and Target Contributions to NMT Predictions".
Understanding the Difficulty of Training Transformers
24,540 repositories in the index in total.
