Question Answering on ARC Easy (Score, Relative Change, Gate Density)
76ScoreSelf-Pruned KV
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Self-Pruned KVAttention Mechanism=Self-Pruned KV, tau=0.5, Model Size=8.1B, Training Context=32k2026.05 | 76 | 0.4 | 52.4 | |
| VanillaAttention Mechanism=Full Attention, Model Size=8.1B, Training Context=32k2026.05 | 75.6 | — | — |