Instructions to use sachin/vit2distilgpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sachin/vit2distilgpt2 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="sachin/vit2distilgpt2")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("sachin/vit2distilgpt2") model = AutoModelForImageTextToText.from_pretrained("sachin/vit2distilgpt2") - Notebooks
- Google Colab
- Kaggle
can not run the demo
#1
by JuliaQuQu - opened
model = AutoModel.from_pretrained("sachin/vit2distilgpt2")
ValueError: Unrecognized configuration class <class 'transformers.models.vision_encoder_decoder.configuration_vision_encoder_decoder.VisionEncoderDecoderConfig'> for this kind of AutoModel: AutoModel.
It seems that AutoModel doesn't fit vit2distilgpt2