goodman20241017/Llama-2-7B-BPD2-G64

This repository contains a 2-bit quantized version of meta-llama/Llama-2-7b-hf using the BPDQ (Bit-Plane Decomposition Quantization) algorithm.

BPDQ is a post-training quantization (PTQ) method that constructs a variable quantization grid via bit-plane decomposition and scalar coefficients. By iteratively refining these using second-order information, it maintains high fidelity even in extremely low-bit regimes (2–3 bits) where conventional PTQ methods typically degrade.

Resources

• Paper: BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models
• GitHub: KingdalfGoodman/BPDQ

Citation

If you find BPDQ useful in your research, please cite:

@article{chen2026bpdq,
  title={BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models},
  author={Chen, Junyu and Li, Jungang and Xiong, Jing and Wang, Wenjie and Yang, Qingyao and Xiao, He and Li, Zhen and Wu, Taiqiang and Chen, Mengzhao and Peng, Zhen and others},
  journal={arXiv preprint arXiv:2602.04163},
  year={2026}
}