Idiap/gated-deltanet-attn-0.4B-10B
0.4B • Updated • 19
hybrid-linear-sparse-attention
-
-
Idiap/gated-deltanet-attn-1.4B-30B
1B • Updated • 85 • 1 -
Idiap/gated-deltanet-lte-0.4B-10B
0.4B • Updated • 14 -
Idiap/gated-deltanet-lte-1.4B-30B
1B • Updated • 7 -
Idiap/gated-deltanet-nsa-0.4B-10B
0.4B • Updated • 9 -
Idiap/gated-deltanet-nsa-1.4B-30B
1B • Updated • 8 -
Idiap/gated-deltanet-swa-0.4B-10B
0.4B • Updated • 16 -
Idiap/gated-deltanet-swa-1.4B-30B
1B • Updated • 13