Search Results for author:
Found 1 papers, 1 papers with code
Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
Interestingly, this memory model manifests a model-based interpretation of an outlier-efficient attention mechanism ($\text{Softmax}_1$): it is an approximation of the memory retrieval process of $\mathtt{OutEffHop}$.
Ranked #1 on
Quantization
on Wiki-40B
Cannot find the paper you are looking for? You can
Submit a new open access paper.
