FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation
FreeSolo adds linear-time sparse attention that extrapolates context length without long-context fine-tuning.
1 stories, newest first · one card per story
FreeSolo adds linear-time sparse attention that extrapolates context length without long-context fine-tuning.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views