Instructions to use google/pix2struct-screen2words-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/pix2struct-screen2words-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="google/pix2struct-screen2words-base")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/pix2struct-screen2words-base") model = AutoModelForMultimodalLM.from_pretrained("google/pix2struct-screen2words-base") - Notebooks
- Google Colab
- Kaggle
How can I finetune Screen2words Dataset on Pix2Struct-base model with multi-batchsize
#3
by HaiminWang - opened
The example only gives the condition "batch-size=1", which spends lots of time finetuning
HaiminWang changed discussion status to closed