Instructions to use google/matcha-chartqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/matcha-chartqa with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="google/matcha-chartqa")# pip install -U transformers accelerate # 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") - Notebooks
- Google Colab
- Kaggle
Results on PlotQA v1 does not match with the paper
#5
by AliFarahani - opened
AliFarahani changed discussion title from Results on PlotQA does not match with the paper to Results on does not match with the paper
AliFarahani changed discussion status to closed
AliFarahani changed discussion title from Results on does not match with the paper to Results on PlotQA v1 does not match with the paper