from transformers import AutoProcessor, AutoModelForImageTextToText
from PIL import Image

processor = AutoProcessor.from_pretrained("akazen/paligemma-3b-ft-vizwizvqa-16bit")
model = AutoModelForImageTextToText.from_pretrained(
    "akazen/paligemma-3b-ft-vizwizvqa-16bit",
    device_map="auto"
)

# Process an image
image = Image.open("your_image.jpg").convert("RGB")
question = "What's in this image?"
prompt = f"<image>\nQuestion: {question}\nAnswer:"

inputs = processor(images=image, text=prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=20)
answer = processor.decode(outputs[0], skip_special_tokens=True)

akazen/paligemma-3b-vizwizv-16Q

Paligemma-3b-ft-vizwizvqa-224 (16-bit Quantized)

Usage

akazen/
paligemma-3b-vizwizv-16Q