Instructions to use UCSC-VLAA/openvision-vit-base-patch16-384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use UCSC-VLAA/openvision-vit-base-patch16-384 with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:UCSC-VLAA/openvision-vit-base-patch16-384') tokenizer = open_clip.get_tokenizer('hf-hub:UCSC-VLAA/openvision-vit-base-patch16-384') - Notebooks
- Google Colab
- Kaggle
Error
Looking for some guidance .
I am new to using this model so looking for some help
While trying to run test python script --
from transformers import AutoProcessor, AutoModel
from PIL import Image
import requests
processor = AutoProcessor.from_pretrained("UCSC-VLAA/openvision-vit-base-patch16-384")
model = AutoModel.from_pretrained("UCSC-VLAA/openvision-vit-base-patch16-384") i got this error
Error ------------
OSError: UCSC-VLAA/openvision-vit-base-patch16-384 does not appear to have a file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt or flax_model.msgpack.
@viks555 you need to use their codebase linked in the README. This isn't a Transformers model
You can also use OpenCLIP as of the latest release, BUT the models need to be updated so these ones wouldn't work.
This one for example was a test model I updated to work with OpenCLIP https://huggingface.co/rwightman/openvision-vit-base-patch16-384 ... nothing in that model card, but see OpenCLIP or the official source code links here to see usage examples.