Instructions to use Heliosoph/vit-gpt2-image-captioning-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Heliosoph/vit-gpt2-image-captioning-onnx 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="Heliosoph/vit-gpt2-image-captioning-onnx")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("Heliosoph/vit-gpt2-image-captioning-onnx") model = AutoModelForImageTextToText.from_pretrained("Heliosoph/vit-gpt2-image-captioning-onnx") - Notebooks
- Google Colab
- Kaggle
File size: 187 Bytes
3dad833 | 1 2 3 4 5 6 7 8 9 | {
"_from_model_config": true,
"bos_token_id": 50256,
"decoder_start_token_id": 50256,
"eos_token_id": 50256,
"pad_token_id": 50256,
"transformers_version": "4.45.2"
}
|