Reproduction and exploration of QBB-based low-bit LLM quantization on TinyLlama, with 2-bit/4-bit experiments and WikiText-2 PPL evaluation.
-
Updated
Apr 5, 2026 - Python
Reproduction and exploration of QBB-based low-bit LLM quantization on TinyLlama, with 2-bit/4-bit experiments and WikiText-2 PPL evaluation.
Add a description, image, and links to the qbb topic page so that developers can more easily learn about it.
To associate your repository with the qbb topic, visit your repo's landing page and select "manage topics."