GeneZC/MiniMA-2-3B
Text Generation
•
Updated
•
9
•
17
MiniMA Family
The model family derived from MiniMA
-
-
GeneZC/MiniMA-2-1B
Text Generation • Updated • 7 • 2 -
GeneZC/MiniMA-3B
Text Generation • Updated • 14 • 21 -
GeneZC/MiniChat-2-3B
Text Generation • Updated • 2.75k • 25 -
GeneZC/MiniChat-1.5-3B
Text Generation • Updated • 93 • 36 -
GeneZC/MiniChat-3B
Text Generation • Updated • 367 • 33 -
GeneZC/MiniLoong-3B
Text Generation • Updated • 4 -
GeneZC/MiniMix-2_4x3B
Text Generation • Updated • 4 -
Towards the Law of Capacity Gap in Distilling Language Models
Paper • 2311.07052 • Published • 2 -
Distillation Scaling Laws
Paper • 2502.08606 • Published • 48