List your company

Suitability Score Prediction on Amazon Reviews

1.078MAERL
1.071061.1179051.164751.211595Dec 12, 2025

Evaluation results

MethodLinks
RLTraining Mode=Reinforcement Learning, Optimization=PPO2025.121.0780.562976.4
SFTTraining Mode=Supervised Fine-Tuning, Framework=Tinker Cookbook2025.121.1130.558377.2
BaseBackbone=Qwen-4B2025.121.23620.423370.07
IPTFull Name=Instruction Prompt Tuning Model2025.121.25150.449868.9