TernaryLM: Memory-Efficient Language Modeling via Native 1-Bit Quantization with Adaptive Layer-wise Scaling Paper โข 2602.07374 โข Published Feb 7 โข 1
TernaryLM: Memory-Efficient Language Modeling via Native 1-Bit Quantization with Adaptive Layer-wise Scaling Paper โข 2602.07374 โข Published Feb 7 โข 1