Sherry-1.25bit Collection The 1.25-bit models via Sherry, 3:4 sparse ternary quantization. • 3 items • Updated 3 days ago
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification Paper • 2601.07892 • Published 25 days ago • 2 • 1
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification Paper • 2601.07892 • Published 25 days ago • 2