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