This new model is a complete replacement (smaller, faster and better).
This
Model2Vec model was created by using
Tokenlearn, with
nomic-embed-text-v2-moe as a base.
The output dimension is 768.
The evaluation in the model card, was executed using this model (distilled), not the original.
The process to create this one, was not a simple model2vec distill, this involved generating embeddings for 23M triplets (msmarco) with the original model, then training the tokenlearn model on it, with the nomic model as a base.
1from model2vec import StaticModel
2
3model = StaticModel.from_pretrained("cnmoro/nomic-embed-text-v2-moe-distilled-high-quality")
4
5# Compute text embeddings
6embeddings = model.encode(["Example sentence"])
1from sentence_transformers import SentenceTransformer
2
3model = SentenceTransformer('cnmoro/nomic-embed-text-v2-moe-distilled-high-quality')
4
5# Compute text embeddings
6embeddings = model.encode(["Example sentence"])
