Transformers How to use Ayansk11/Image_Caption_using_ViT_GPT2 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="Ayansk11/Image_Caption_using_ViT_GPT2") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM
tokenizer = AutoTokenizer.from_pretrained("Ayansk11/Image_Caption_using_ViT_GPT2")
model = AutoModelForMultimodalLM.from_pretrained("Ayansk11/Image_Caption_using_ViT_GPT2", device_map="auto") 
