NativeTernary encodes ternary weights at exactly 2 bits each with 460x lower overhead than GGUF for BitNet-style models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NativeTernary: A Self-Delimiting Binary Encoding with Unary Run-Length Hierarchy Markers for Ternary Neural Network Weights, Structured Data, and General Computing Infrastructure
NativeTernary encodes ternary weights at exactly 2 bits each with 460x lower overhead than GGUF for BitNet-style models.