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