kmseong/llama3.1_8b_base_gsm8k_ft_freeze_rsn_lr3e-5
The kmseong/llama3.1_8b_base_gsm8k_ft_freeze_rsn_lr3e-5 is an 8 billion parameter Llama-3.2-3B-Instruct model fine-tuned by kmseong using the Safety Neuron Tuning (SN-Tune) method. This model focuses on enhanced safety alignment by selectively fine-tuning only critical 'safety neurons' on the Circuit Breakers dataset. It maintains general capabilities while improving safety, making it suitable for applications requiring robust safety features.
Loading preview...
Model Overview
This model, kmseong/llama3.1_8b_base_gsm8k_ft_freeze_rsn_lr3e-5, is an 8 billion parameter variant of the meta-llama/Llama-3.2-3B-Instruct base model. It has been fine-tuned using a specialized technique called Safety Neuron Tuning (SN-Tune), developed by kmseong, to significantly enhance its safety alignment.
Key Capabilities & Features
- Enhanced Safety Alignment: Utilizes SN-Tune to improve safety performance by focusing on specific 'safety neurons'.
- Parameter-Efficient Fine-tuning: Only a small subset of critical neurons are fine-tuned, freezing all other parameters, which makes the process highly efficient.
- Minimal Impact on General Capabilities: The selective tuning approach aims to preserve the base model's broad capabilities while integrating safety improvements.
- Based on Llama-3.2-3B-Instruct: Inherits the foundational strengths of the Llama 3.2 architecture.
Good For
- Applications where safety and responsible AI behavior are paramount.
- Developers looking for a Llama 3.2-based model with improved safety guardrails without sacrificing general performance.
- Use cases requiring a model that has undergone targeted safety fine-tuning using a neuron-specific approach.