UrbanGovLM-8B-A

Model Description

UrbanGovLM-8B-A is a Chinese domain-specific language model for applied urban governance tasks. The model is fine-tuned from Qwen3-8B using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) on UrbanGovQA dataset (applied subset).

This variant focuses on:

• Scenario-based reasoning
• Policy implementation analysis
• Decision support and recommendations
• Actionable and structured responses

Due to network constraints, we have uploaded the model to the ModelScope platform. Please refer to this link for details.