linzju/Bio-Medical-Llama-3-8B_EnchTable_FFN_Attention

EnchTable: Unified Safety Alignment Transfer (Bio-Medical + Hybrid)

This repository contains the Bio-Medical Llama-3-8B model aligned using the Hybrid (Attention + FFN) intervention of the EnchTable framework.

This model is part of the research presented in the paper:
"EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models", accepted at IEEE S&P 2026.

Model Details

• Name: Bio-Medical Llama-3-8B (EnchTable-Hybrid)
• Domain: Bio-Medical / Healthcare
• Method: EnchTable (Attention + FFN)
• Base Model: Llama-3-8B fine-tuned on medical datasets

EnchTable is a framework designed to transfer safety alignment capabilities.

In this checkpoint, we utilize a Hybrid strategy, injecting safety vectors into both Self-Attention and FFN layers. This combination aims to achieve the optimal balance between robust safety alignment and downstream medical performance.