---
base_model: unsloth/Llama-3.2-3B-Instruct
library_name: transformers
pipeline_tag: text-generation
tags:
- llama
- merged
- worldpolicy
- grpo
---

# WorldPolicy GRPO 3B Merged

Standalone merged model for WorldPolicy debate inference.

- Base: `unsloth/Llama-3.2-3B-Instruct`
- Adapter: `krishpotanwar/worldpolicy-grpo-3b`
- Context capped for serving: `4096` tokens