MedGemma 4B - DIPG Safety v2 (GRPO-Trained)
Fine-tuned MedGemma 4B using GRPO (Group Relative Policy Optimization) on the DIPG Safety Gym benchmark.
Training Details
- Base Model: MedGemma 4B IT
- Method: GRPO with LoRA (rank=64, alpha=64)
- Training Steps: 100
- Focus: Medical safety — hallucination reduction, evidence-grounded responses
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("surfiniaburger/medgemma-4b-dipg-safety-v2")
model = AutoModelForCausalLM.from_pretrained(
"surfiniaburger/medgemma-4b-dipg-safety-v2",
torch_dtype="bfloat16",
device_map="auto"
)
SafeClaw Project
Part of the DIPG Safety Gym ecosystem.