Skip to content
Fossfits

attention.

Listed 4Updated Sep 4, 2026

  1. Rank 1. transfusion-pytorchPytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAIGitHub stars: 1.4k
  2. Rank 2. native-sparse-attention-pytorchImplementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paperGitHub stars: 813
  3. Rank 3. ScreenAIImplementation of the ScreenAI model from the paper: "A Vision-Language Model for UI and Infographics Understanding"GitHub stars: 388
  4. Rank 4. dreamer4Implementation of Danijar's latest iteration for his Dreamer line of workGitHub stars: 215