| You can use these models as follows (example on a ChatQA dataset): | |
| thon | |
| from transformers import AutoProcessor, Pix2StructForConditionalGeneration | |
| import requests | |
| from PIL import Image | |
| model = Pix2StructForConditionalGeneration.from_pretrained("google/matcha-chartqa").to(0) | |
| processor = AutoProcessor.from_pretrained("google/matcha-chartqa") | |
| url = "https://raw.githubusercontent.com/vis-nlp/ChartQA/main/ChartQA%20Dataset/val/png/20294671002019.png" | |
| image = Image.open(requests.get(url, stream=True).raw) | |
| inputs = processor(images=image, text="Is the sum of all 4 places greater than Laos? |