Combiner
Official implementation of Combiner: Full Attention Transformer with Sparse Computation Cost.
- from
- JAX
- added
- 2026-10-10
- likes
- 0
similar
-
fantasy-combinators github.com
-
Vision Transformer github.com
Official implementation of An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.
-
JAX Toolbox github.com
Nightly CI and optimized examples for JAX on NVIDIA GPUs using libraries such as T5x, Paxml, and Transformer Engine.
-
combine github.com
-
-
JAX › Models and Projects > Flax: “Official implementation of Combiner: Full Attention Transformer with Sparse Computation Cost.”