Instructions to use mixedbread-ai/mxbai-rerank-xsmall-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mixedbread-ai/mxbai-rerank-xsmall-v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mixedbread-ai/mxbai-rerank-xsmall-v1") model = AutoModelForSequenceClassification.from_pretrained("mixedbread-ai/mxbai-rerank-xsmall-v1", device_map="auto") - Transformers.js
How to use mixedbread-ai/mxbai-rerank-xsmall-v1 with Transformers.js:
// npm i @huggingface/transformers import { AutoTokenizer, AutoModelForSequenceClassification } from '@huggingface/transformers'; const tokenizer = await AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); const model = await AutoModelForSequenceClassification.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); const query = 'Which planet is known as the Red Planet?'; const documents = [ 'Mars, known for its reddish appearance, is often referred to as the Red Planet.', 'Venus is often called the twin of Earth because of its similar size and proximity.', ]; const inputs = tokenizer(new Array(documents.length).fill(query), { text_pair: documents, padding: true, truncation: true }); const { logits } = await model(inputs); console.log(logits.sigmoid().tolist()); // one relevance score per document - sentence-transformers
How to use mixedbread-ai/mxbai-rerank-xsmall-v1 with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("mixedbread-ai/mxbai-rerank-xsmall-v1") 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) - Notebooks
- Google Colab
- Kaggle
How to interpret the score?
Hi,
I am trying the rerank-xsmall model. I can see even for 2 same sentences the score is under 0.25.
So, I was wondering if I am interpreting it incorrectly.
I was trying "What a day. What a day"
Thanks
Hey @Jr92 ,
our reranker is mostly designed to work like a search engine and in this iteration is not mean for STS tasks. This means you should design your query to be a question. E.g. "Who wrote 'To Kill a Mockingbird'?" + "'To Kill a Mockingbird' is a novel by Harper Lee published in 1960. It was immediately successful, winning the Pulitzer Prize, and has become a classic of modern American literature.". We're aware that this is a downfall and are working to fix this in V2.
Have a nice day!