---
license: apache-2.0
language:
- en
library_name: transformers
pipeline_tag: image-text-to-text
tags:
- art
datasets:
- tomg-group-umd/pixelprose
---

Fine-tuned version of PaliGemma 224x224 on 7500 random examples from [PixelProse](https://huggingface.co/datasets/tomg-group-umd/pixelprose) dataset.

```
pip install git+https://github.com/huggingface/transformers
```

```python
from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
from PIL import Image
import requests
import torch

model_id = "gokaygokay/PaliGemma-PixelProse"

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)

model = PaliGemmaForConditionalGeneration.from_pretrained(model_id).to('cuda').eval()
processor = AutoProcessor.from_pretrained(model_id)

## prefix
prompt = "caption en"
model_inputs = processor(text=prompt, images=image, return_tensors="pt").to('cuda')
input_len = model_inputs["input_ids"].shape[-1]

with torch.inference_mode():
    generation = model.generate(**model_inputs, repetition_penalty=1.05, max_new_tokens=512, do_sample=False)
    generation = generation[0][input_len:]
    decoded = processor.decode(generation, skip_special_tokens=True)
    print(decoded)

```