Instructions to use cross-encoder/ms-marco-MiniLM-L6-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use cross-encoder/ms-marco-MiniLM-L6-v2 with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2") query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Transformers
How to use cross-encoder/ms-marco-MiniLM-L6-v2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("cross-encoder/ms-marco-MiniLM-L6-v2") model = AutoModelForSequenceClassification.from_pretrained("cross-encoder/ms-marco-MiniLM-L6-v2") - Notebooks
- Google Colab
- Kaggle
Article to deepen my understanding and reference it in my work
Hello, does anyone know in which article this model was introduced ? I would like to reference it and read it so I can undestand it more precisely.
Hello!
I think this model was actually not included in a paper, although I may be wrong. There are some details for the related models here: https://www.sbert.net/docs/pretrained-models/msmarco-v5.html (this docs page is not usually shown). I'm pretty sure this model was trained using BinaryCrossEntropyLoss.
On CrossEncoder models overall, you can learn more here: https://www.sbert.net/docs/cross_encoder/usage/usage.html
- Tom Aarsen
Okey, thanks a lot for your help !
Hello!
I think this model was actually not included in a paper, although I may be wrong. There are some details for the related models here: https://www.sbert.net/docs/pretrained-models/msmarco-v5.html (this docs page is not usually shown). I'm pretty sure this model was trained using BinaryCrossEntropyLoss.
On CrossEncoder models overall, you can learn more here: https://www.sbert.net/docs/cross_encoder/usage/usage.html
- Tom Aarsen