metadata
license: apache-2.0
base_model: google/medgemma-4b-it
tags:
- medical
- anti-hallucination
- pharmacovigilance
- medgemma
- rlfr
MedGemma 4B Anti-Hallucination
MedGemma 4B fine-tuned with RLFR (Reinforcement Learning from Feature Rewards) to reduce hallucination in pharmacovigilance document generation.
- Base model:
google/medgemma-4b-it - Method: RLFR with 6 reward features (factual accuracy, completeness, format compliance, etc.)
- Task: Generate MedWatch 3500A pharmacovigilance narratives from CRF data
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("AlphaRaven/medgemma-4b-antihallu")
tokenizer = AutoTokenizer.from_pretrained("AlphaRaven/medgemma-4b-antihallu")
Part of the Clinical Trial Simulation Engine pipeline.