A judge model to evaluate rebuttal quality, trained from Qwen3-8B using RL. Refer to https://github.com/ulab-uiuc/DRPG-RebuttalAgent for usage.

Downloads last month
1
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for HakHan/DRPG_JudgeModel

Quantizations
1 model

Collection including HakHan/DRPG_JudgeModel