kmseong/Llama-3.2-3B-only-rsn-tuned_10

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Mar 17, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

kmseong/Llama-3.2-3B-only-rsn-tuned_10 is a 3.2 billion parameter Llama-3.2-3B-Instruct model fine-tuned by kmseong using Safety Neuron Tuning (SN-Tune). This model is specifically enhanced for safety alignment by selectively fine-tuning only critical safety neurons on the Circuit Breakers dataset. It maintains general capabilities while providing improved safety, making it suitable for applications requiring robust safety features.

Loading preview...

Model Overview

kmseong/Llama-3.2-3B-only-rsn-tuned_10 is a 3.2 billion parameter language model based on the meta-llama/Llama-3.2-3B-Instruct architecture. This model has undergone a specialized fine-tuning process called SN-Tune (Safety Neuron Tuning), developed by kmseong, to enhance its safety alignment.

Key Capabilities & Features

  • Enhanced Safety Alignment: The primary differentiator of this model is its improved safety, achieved through SN-Tune.
  • Parameter-Efficient Fine-tuning: SN-Tune selectively fine-tunes only a small set of "safety neurons" while freezing other parameters, ensuring efficient training.
  • Minimal Impact on General Capabilities: This selective tuning approach aims to enhance safety without significantly degrading the model's original general performance.
  • Base Model: Built upon the robust Llama-3.2-3B-Instruct foundation, inheriting its general language understanding and generation abilities.

What is SN-Tune?

SN-Tune is a method that:

  • Identifies specific neurons within the model that are critical for safety responses.
  • Freezes the majority of the model's parameters.
  • Fine-tunes only these identified safety neurons using dedicated safety datasets, such as the Circuit Breakers dataset.

Ideal Use Cases

This model is particularly well-suited for applications where:

  • Safety is a critical requirement: Developers needing a language model with improved safeguards against generating harmful or undesirable content.
  • Resource efficiency is important: The parameter-efficient SN-Tune method makes it a good choice for deployment where computational resources are a consideration, while still benefiting from enhanced safety.
  • Building on Llama-3.2-3B-Instruct: Users already familiar with or planning to use the base Llama-3.2-3B-Instruct model but require an additional layer of safety alignment.