How to use M-CLIP/M-BERT-Base-ViT-B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="M-CLIP/M-BERT-Base-ViT-B")
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("M-CLIP/M-BERT-Base-ViT-B") model = AutoModel.from_pretrained("M-CLIP/M-BERT-Base-ViT-B", device_map="auto")
