5,497,319 AI resources indexedWorking toward the world’s largest AI resource index.

PDF

BitNet a4.8: 4-bit Activations for 1-bit LLMs

Research paper by Hongyu Wang and collaborators. Published 2024-11-07. Topics: 1-bit Large Language Models (LLMs), BitNet b1.58, BitNet a4.8, hybrid quantization, sparsification.

Resource information

Authors
Hongyu Wang, Shuming Ma, Furu Wei
Research topics
1-bit Large Language Models (LLMs), BitNet b1.58, BitNet a4.8, hybrid quantization, sparsification, quantization errors, 4-bit activations, attention layers, feed-forward network layers, 8-bit quantization, INT4/FP4 kernels, 3-bit KV cache
Publication date
2024-11-07
Publication
arXiv
Last record update
Nov 3, 2026