This model is a 3-bit quantized version of
meta-llama/Llama-2-7b-hf using the
Bit-Plane Decomposition Quantization (BPDQ) 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, BPDQ expands the feasible set for error minimization, allowing for high-fidelity performance in extreme low-bit regimes (2–3 bits) where conventional fixed-grid PTQ methods typically degrade.
BPDQ is implemented as a patch on top of
GPTQModel at version
5.7.0. To use this model, you need to apply the patch provided in the official repository:
For detailed quantization and evaluation workflows, please refer to the
official repository.
1@article{chen2026bpdq,
2 title={BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models},
3 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},
4 journal={arXiv preprint arXiv:2602.04163},
5 year={2026}
6}
