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
1,475 results
A low-latency & high-throughput serving engine for LLMs
PageTransformer for flutter
A Jest transformer using esbuild
FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.
Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022
[ECCV'2020] STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting
Mass-editing thousands of facts into a transformer memory (ICLR 2023)
Static suckless single batch CUDA-only qwen3-0.6B mini inference engine
A collection of view pager transformers
[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch
[ICLR 2022] Official implementation of the paper "DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR"
历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
NLP Paper
End-to-end ASR/LM implementation with PyTorch
multilspy is a lsp client library in Python intended to be used to build applications around language servers.
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (NeurIPS 2019)
[CVPR 2021, Oral] PREDATOR: Registration of 3D Point Clouds with Low Overlap.
Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.
[ECCV 2022] Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
This is an official implementation for "Self-Supervised Learning with Swin Transformers".
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 论文的中文翻译 Chinese Translation!
24,523 repositories in the index in total.
