mdajwadhossain

paligemma-3b-oral-mucosal-lora

README

Fine-tuned on HRruiH/Dataset-of-oral-mucosal-diseases (5 classes: Normal, OCA, OLK, OLP, OSF).

Test set results (n=135):

Zero-shot baseline on same data: ~30-45% accuracy (model defaulted to "Normal" almost always).

Prompt used: <image>answer en What oral condition is shown?

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Model Details

Model Provider

mdajwadhossain

Model Tree

Base

google/paligemma-3b-mix-224

Adapter

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated Endpoints