---
library_name: transformers
license: other
base_model: meta-llama/Llama-3.2-3B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: GuardReasoner 3B
  results: []
pipeline_tag: text-generation
---

# GuardReasoner 3B

This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) via R-SFT and HS-DPO, as described in [GuardReasoner: Towards Reasoning-based LLM Safeguards](https://huggingface.co/papers/2501.18492).