OASIS robinzixuan/Phi4_attn_residual Text Generation • 4B • Updated Oct 1 • 281 • 1 robinzixuan/Phi4_attn_OASIS Text Generation • 4B • Updated Oct 1 • 265 robinzixuan/Phi4_attn_AoS Text Generation • 4B • Updated Oct 1 • 268 Attention Sinks and Outliers in Attention Residuals Paper • 2605.17887 • Published May 18 • 5
OASIS robinzixuan/Phi4_attn_residual Text Generation • 4B • Updated Oct 1 • 281 • 1 robinzixuan/Phi4_attn_OASIS Text Generation • 4B • Updated Oct 1 • 265 robinzixuan/Phi4_attn_AoS Text Generation • 4B • Updated Oct 1 • 268 Attention Sinks and Outliers in Attention Residuals Paper • 2605.17887 • Published May 18 • 5