---
base_model: google/gemma-3-4b-it
library_name: peft
tags:
- gemma3
- lora
- peft
- vllm
---

# UserGRPO Model for Retail Simulations

UserGRPO checkpoint based on Gemma-3 for agent simulations in [SalesSim](https://arxiv.org/html/2605.08334v1). This model has been trained to adhere to persona specifications in dialogue-based retail simulations, as specified by preferences and dealbreakers. 


## License

CC-BY-NC 4.0