kmseong/llama3.2_3b_gsm8k_ft_3e-5_after_rsn_tuned_lr3e-5_fz
TEXT GENERATIONConcurrency Cost:1Model Size:3.2BQuant:BF16Ctx Length:32kPublished:Apr 8, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The kmseong/llama3.2_3b_gsm8k_ft_3e-5_after_rsn_tuned_lr3e-5_fz is a 3.2 billion parameter Llama-3.2-3B-Instruct model, developed by kmseong, that has been fine-tuned using the Safety Neuron Tuning (SN-Tune) method. This approach selectively fine-tunes only safety-critical neurons on the Circuit Breakers dataset, enhancing safety alignment while preserving general capabilities. It is optimized for improved safety performance with minimal impact on the base model's original functions.

Loading preview...

Model Overview

This model, kmseong/llama3.2_3b_gsm8k_ft_3e-5_after_rsn_tuned_lr3e-5_fz, is a 3.2 billion parameter variant of the meta-llama/Llama-3.2-3B-Instruct base model. It has undergone a specialized fine-tuning process known as Safety Neuron Tuning (SN-Tune), developed by kmseong, to enhance its safety alignment.

Key Capabilities & Features

  • Enhanced Safety Alignment: Utilizes SN-Tune to specifically target and improve the model's safety responses.
  • Parameter-Efficient Fine-tuning: The SN-Tune method selectively fine-tunes only a small set of "safety neurons" while freezing other parameters, minimizing computational overhead and preserving general capabilities.
  • Minimal Impact on General Performance: Designed to improve safety without significantly degrading the base model's original performance across various tasks.
  • Based on Llama-3.2-3B-Instruct: Inherits the foundational capabilities of the Llama-3.2-3B-Instruct architecture.

What is SN-Tune?

SN-Tune is a novel fine-tuning approach that involves:

  1. Identifying specific "safety neurons" within the model that are crucial for safety-related responses.
  2. Freezing all other non-safety parameters.
  3. Fine-tuning only these identified safety neurons using dedicated safety alignment data, such as the Circuit Breakers dataset.

Intended Use Cases

This model is particularly suitable for applications where:

  • Safety and responsible AI are paramount: Ideal for deployments requiring robust safety guardrails.
  • Maintaining base model capabilities is important: Users want improved safety without sacrificing the general utility of the Llama-3.2-3B-Instruct model.
  • Efficient safety updates are desired: The parameter-efficient nature of SN-Tune allows for targeted safety improvements.