# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText
tokenizer = AutoTokenizer.from_pretrained("yuewu/toc_titler")
model = AutoModelForImageTextToText.from_pretrained("yuewu/toc_titler")Quick Links
A model that inputs chemistry journal article table of contents (ToC) images and generates appropriate titles. Trained on all JACS ToCs and titles.
- Downloads last month
- 18
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" 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("image-to-text", model="yuewu/toc_titler")