Zhen Wu

LoRA Fine-Tuning Enables Controllable Mathematical Reasoning in Small Language Models: A Gating Pipeline on Qwen3.5-0.8B

We design a gating pipeline for LoRA fine-tuning of Qwen3.5-0.8B, a 24-layer hybrid of GatedDeltaNet and Full Attention, executed entirely on CPU. The pipeline runs three ablations: layer ablation selects full-module joint fine-tuning over single-module configurations; data curri...