Mod1_2-no-ref

Overview

This repository contains a medical LLM-as-a-Judge model based on Gemma-3-4B and fine-tuned for medical response evaluation tasks.

This version combines evaluation modules 1 and 2 without reference answers.

Base Model

• Base architecture: Gemma-3-4B
• Frameworks:
  • Transformers
  • PEFT / LoRA
  • TRL

Training Objective

The model is designed to evaluate generated medical answers according to predefined clinical evaluation criteria.

Depending on the version, the model may operate:

• with expert reference answers (with-ref)
• without reference answers (no-ref)