Instructions to use google/matcha-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/matcha-base 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-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/matcha-base") model = AutoModelForMultimodalLM.from_pretrained("google/matcha-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
Update README.md 8a3e424
Update README.md 2c884b7
Update README.md b1c5087
Update README.md b5e9052
Update config.json 0a970b6
Create README.md c55ea87
Upload Pix2StructForConditionalGeneration bfd6fff
Upload processor 7885c22
initial commit 1070995
Younes Belkada commited on