Downloads · 30 days
14.4K
3% of all-time downloads
chuhac/BiomedCLIP-vit-bert-hf
BiomedCLIP-vit-bert-hf is a zero-shot classification model from chuhac. Use it when you need labels you did not train the model on. It is set up for transformers. The card lists the license as mit.
1. pure torch and huggingface-based implementation of the original microsoft/BiomedCLIP-PubMedBERT256-vitbasepatch16224 2. rename the checkpoint state key names.
Downloads · 30 days
14.4K
3% of all-time downloads
All-time downloads
506K
Public
Parameters
196M
1.6 GB on disk
Likes
8
Public
Click a slice to open those files.
.bin784 MB · 50%
From the Hugging Face model README
from transformers import AutoModel, AutoProcessor
model = AutoModel.from_pretrained("chuhac/BiomedCLIP-vit-bert-hf", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("chuhac/BiomedCLIP-vit-bert-hf", trust_remote_code=True)