Hybrid wave-attention beats tiny transformers on perplexity, not memory
A 10.94M hybrid scores 5.95 perplexity, but its peak VRAM matches the pure transformer.
1 stories, newest first · one card per story
A 10.94M hybrid scores 5.95 perplexity, but its peak VRAM matches the pure transformer.
Today 1.6K readers · 2.5K views · 778 reads · all time 189K views