How to use google/matcha-chartqa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="google/matcha-chartqa")
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/matcha-chartqa") model = AutoModelForMultimodalLM.from_pretrained("google/matcha-chartqa", device_map="auto")
https://huggingface.co/google/matcha-chartqa/resolve/main/tokenizer.json
hf download hf://google/matcha-chartqa/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/google/matcha-chartqa/resolve/main/tokenizer.json
