Bimokuncoro/medgemma-4b-crc-finetuned

from unsloth import FastVisionModel
from peft import PeftModel
import torch

# Load base model + adapter
model, processor = FastVisionModel.from_pretrained(
    "unsloth/medgemma-4b-it",
    load_in_4bit=False,
)
model = PeftModel.from_pretrained(model, "Bimokuncoro/medgemma-4b-crc-finetuned")
FastVisionModel.for_inference(model)

# Run inference
from PIL import Image
image = Image.open("your_tissue_image.png")
messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": "What type of tissue is shown in this histological image? 
        Reply with ONLY one word from this list: ADI, BACK, DEB, LYM, MUC, MUS, NORM, STR, TUM. 
        Do not explain."}
    ]
}]
input_text = processor.tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)
inputs = processor(images=image, text=input_text,
                   add_special_tokens=False, return_tensors="pt").to("cuda")
input_length = inputs["input_ids"].shape[1]
with torch.no_grad():
    out = model.generate(**inputs, max_new_tokens=50, use_cache=True)
new_tokens = out[0][input_length:]
result = processor.tokenizer.decode(new_tokens, skip_special_tokens=True).strip()
print(result)  # e.g. "TUM"