Transformers How to use maze/CLIP-ViT-bigG-14 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="maze/CLIP-ViT-bigG-14") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("maze/CLIP-ViT-bigG-14")
model = AutoModel.from_pretrained("maze/CLIP-ViT-bigG-14", device_map="auto") 
