Hugging Face's logo

KMH158
/
medgemma-brats-reporter-v4-sequential

Safetensors
Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

MedGemma BraTS Reporter v4 — Multi-Modality Sequential

Best checkpoint epoch 9

Architecture: T1/T1CE/T2/FLAIR each encoded separately by SigLIP → 4 sequential vision tokens. Keyword-weighted CE loss for spatial accuracy.

Downloads last month
3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support