Instructions to use baseplate/vit-gpt2-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use baseplate/vit-gpt2-image-captioning 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="baseplate/vit-gpt2-image-captioning")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("baseplate/vit-gpt2-image-captioning") model = AutoModelForMultimodalLM.from_pretrained("baseplate/vit-gpt2-image-captioning", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from baseplate/vit-gpt2-image-captioning: direct link, hf CLI and curl.
- Browser
- Download file 1.36 MB
-
https://huggingface.co/baseplate/vit-gpt2-image-captioning/resolve/main/tokenizer.json
- Command line
-
hf download hf://baseplate/vit-gpt2-image-captioning/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/baseplate/vit-gpt2-image-captioning/resolve/main/tokenizer.json
1.36 MB
File too large to display, you can check the raw version instead.