EnchTable: Unified Safety Alignment Transfer (Bio-Medical + FFN)
This repository contains the Bio-Medical Llama-3-8B model aligned using the FFN-based 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-FFN)
- Domain: Bio-Medical / Healthcare
- Method: EnchTable (Feed-Forward Networks)
- Base Model: Llama-3-8B fine-tuned on medical datasets
EnchTable is a framework designed to transfer safety alignment capabilities to specialized models.
In this checkpoint, we apply safety vectors specifically to the Feed-Forward Network (FFN) layers. This approach mitigates safety risks effectively while preserving the factual knowledge required for biomedical tasks.
- Downloads last month
- 13
Model tree for linzju/Bio-Medical-Llama-3-8B_EnchTable_FFN
Base model
meta-llama/Meta-Llama-3-8B-Instruct
Finetuned
ContactDoctor/Bio-Medical-Llama-3-8B