How to use mixedbread-ai/mxbai-edge-colbert-v0-32m with sentence-transformers:
from pylate import models queries = [ "Which planet is known as the Red Planet?", "What is the largest planet in our solar system?", ] documents = [ ["Mars is the Red Planet.", "Venus is Earth's twin."], ["Jupiter is the largest planet.", "Saturn has rings."], ] model = models.ColBERT(model_name_or_path="mixedbread-ai/mxbai-edge-colbert-v0-32m") queries_emb = model.encode(queries, is_query=True) docs_emb = model.encode(documents, is_query=False)
How to use mixedbread-ai/mxbai-edge-colbert-v0-32m with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("mixedbread-ai/mxbai-edge-colbert-v0-32m") model = AutoModel.from_pretrained("mixedbread-ai/mxbai-edge-colbert-v0-32m", device_map="auto")
