GuardReasoner-8B / README.md
nielsr's picture
nielsr HF Staff
Add pipeline tag
2bde55c verified
|
raw
history blame
512 Bytes
metadata
library_name: transformers
license: other
base_model: meta-llama/Llama-3.1-8B
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: GuardReasoner 8B
    results: []
pipeline_tag: text-classification

GuardReasoner 8B

This model is a fine-tuned version of meta-llama/Llama-3.1-8B via R-SFT and HS-DPO. This model is based on the paper GuardReasoner: Towards Reasoning-based LLM Safeguards.