Instructions to use timm/eva02_base_patch14_224.mim_in22k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/eva02_base_patch14_224.mim_in22k with timm:
import timm model = timm.create_model("hf_hub:timm/eva02_base_patch14_224.mim_in22k", pretrained=True) - Transformers
How to use timm/eva02_base_patch14_224.mim_in22k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="timm/eva02_base_patch14_224.mim_in22k")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/eva02_base_patch14_224.mim_in22k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
convert parameters
hi, May I ask if this model is the same as this one(https://huggingface.co/Yuxin-CV/EVA-02/blob/main/eva02/pt/eva02_B_pt_in21k_p14.pt)
Could you please let me know how to convert the original model into the Timm model? Thank you.
@alxemade conversion fn is in timm, https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/eva.py#L562-L638
@alxemade forgot to ans the other q, but maybe you see it, below that code linked above for the conversion, you can see the commented out original URL for each weight if you are trying to figure out what the original for each one is...
Thank you for your help and patience.