How to use ydshieh/vit-gpt2-coco-en with Transformers:
# 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="ydshieh/vit-gpt2-coco-en")
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("ydshieh/vit-gpt2-coco-en") model = AutoModelForMultimodalLM.from_pretrained("ydshieh/vit-gpt2-coco-en", device_map="auto")
SFconvertbot