https://martinuke0.github.io/tags/4bit-quantization/ Recent content in 4bit-Quantization on martinuke0's Blog https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E https://martinuke0.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E Hugo -- 0.152.2 en Fri, 11 Sep 2026 12:00:50 +0000 https://martinuke0.github.io/posts/2026-09-11-hands-on-build-guide-qlora-finetuner-from-scratch-in-pytorch-with-nf4-quantization-and-lora-merging/ Fri, 11 Sep 2026 12:00:50 +0000 https://martinuke0.github.io/posts/2026-09-11-hands-on-build-guide-qlora-finetuner-from-scratch-in-pytorch-with-nf4-quantization-and-lora-merging/ Build a QLoRA fine‑tuner from scratch in PyTorch, implementing NF4 4‑bit quantization and LoRA weight merging for efficient CV model customization.