jina-reranker-v1-turbo-en-GGUF

Model creator: Jina AI
Original model: jina-reranker-v1-turbo-en
GGUF quantization: based on llama.cpp release cc298

Trained by Jina AI.

jina-reranker-v1-turbo-en

This model is designed for blazing-fast reranking while maintaining competitive performance. What's more, it leverages the power of our JinaBERT model as its foundation. JinaBERT itself is a unique variant of the BERT architecture that supports the symmetric bidirectional variant of ALiBi. This allows jina-reranker-v1-turbo-en to process significantly longer sequences of text compared to other reranking models, up to an impressive 8,192 tokens.

To achieve the remarkable speed, the jina-reranker-v1-turbo-en employ a technique called knowledge distillation. Here, a complex, but slower, model (like our original jina-reranker-v1-base-en) acts as a teacher, condensing its knowledge into a smaller, faster student model. This student retains most of the teacher's knowledge, allowing it to deliver similar accuracy in a fraction of the time.

Here's a breakdown of the reranker models we provide:

Currently, the jina-reranker-v1-base-en model is not available on Hugging Face. You can access it via the Jina AI Reranker API.

As you can see, the jina-reranker-v1-turbo-en offers a balanced approach with 6 layers and 37.8 million parameters. This translates to fast search and reranking while preserving a high degree of accuracy. The jina-reranker-v1-tiny-en prioritizes speed even further, achieving the fastest inference speeds with its 4-layer, 33.0 million parameter architecture. This makes it ideal for scenarios where absolute top accuracy is less crucial.

Usage

1. The easiest way to starting using jina-reranker-v1-turbo-en is to use Jina AI's Reranker API.

curl https://api.jina.ai/v1/rerank \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "jina-reranker-v1-turbo-en",
  "query": "Organic skincare products for sensitive skin",
  "documents": [
    "Eco-friendly kitchenware for modern homes",
    "Biodegradable cleaning supplies for eco-conscious consumers",
    "Organic cotton baby clothes for sensitive skin",
    "Natural organic skincare range for sensitive skin",
    "Tech gadgets for smart homes: 2024 edition",
    "Sustainable gardening tools and compost solutions",
    "Sensitive skin-friendly facial cleansers and toners",
    "Organic food wraps and storage solutions",
    "All-natural pet food for dogs with allergies",
    "Yoga mats made from recycled materials"
  ],
  "top_n": 3
}'

2. Alternatively, you can use the latest version of the sentence-transformers>=0.27.0 library. You can install it via pip:

pip install -U sentence-transformers

Then, you can use the following code to interact with the model:

from sentence_transformers import CrossEncoder

# Load the model, here we use our turbo sized model
model = CrossEncoder("jinaai/jina-reranker-v1-turbo-en", trust_remote_code=True)

# Example query and documents
query = "Organic skincare products for sensitive skin"
documents = [
    "Eco-friendly kitchenware for modern homes",
    "Biodegradable cleaning supplies for eco-conscious consumers",
    "Organic cotton baby clothes for sensitive skin",
    "Natural organic skincare range for sensitive skin",
    "Tech gadgets for smart homes: 2024 edition",
    "Sustainable gardening tools and compost solutions",
    "Sensitive skin-friendly facial cleansers and toners",
    "Organic food wraps and storage solutions",
    "All-natural pet food for dogs with allergies",
    "Yoga mats made from recycled materials"
]

results = model.rank(query, documents, return_documents=True, top_k=3)

3. You can also use the transformers library to interact with the model programmatically.

!pip install transformers
from transformers import AutoModelForSequenceClassification

model = AutoModelForSequenceClassification.from_pretrained(
    'jinaai/jina-reranker-v1-turbo-en', num_labels=1, trust_remote_code=True
)

# Example query and documents
query = "Organic skincare products for sensitive skin"
documents = [
    "Eco-friendly kitchenware for modern homes",
    "Biodegradable cleaning supplies for eco-conscious consumers",
    "Organic cotton baby clothes for sensitive skin",
    "Natural organic skincare range for sensitive skin",
    "Tech gadgets for smart homes: 2024 edition",
    "Sustainable gardening tools and compost solutions",
    "Sensitive skin-friendly facial cleansers and toners",
    "Organic food wraps and storage solutions",
    "All-natural pet food for dogs with allergies",
    "Yoga mats made from recycled materials"
]

# construct sentence pairs
sentence_pairs = [[query, doc] for doc in documents]

scores = model.compute_score(sentence_pairs)

4. You can also use the transformers.js library to run the model directly in JavaScript (in-browser, Node.js, Deno, etc.)!

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @xenova/transformers

Then, you can use the following code to interact with the model:

import { AutoTokenizer, AutoModelForSequenceClassification } from '@xenova/transformers';

const model_id = 'jinaai/jina-reranker-v1-turbo-en';
const model = await AutoModelForSequenceClassification.from_pretrained(model_id, { quantized: false });
const tokenizer = await AutoTokenizer.from_pretrained(model_id);

/**
 * Performs ranking with the CrossEncoder on the given query and documents. Returns a sorted list with the document indices and scores.
 * @param {string} query A single query
 * @param {string[]} documents A list of documents
 * @param {Object} options Options for ranking
 * @param {number} [options.top_k=undefined] Return the top-k documents. If undefined, all documents are returned.
 * @param {number} [options.return_documents=false] If true, also returns the documents. If false, only returns the indices and scores.
 */
async function rank(query, documents, {
    top_k = undefined,
    return_documents = false,
} = {}) {
    const inputs = tokenizer(
        new Array(documents.length).fill(query),
        { text_pair: documents, padding: true, truncation: true }
    )
    const { logits } = await model(inputs);
    return logits.sigmoid().tolist()
        .map(([score], i) => ({
            corpus_id: i,
            score,
            ...(return_documents ? { text: documents[i] } : {})
        })).sort((a, b) => b.score - a.score).slice(0, top_k);
}

// Example usage:
const query = "Organic skincare products for sensitive skin"
const documents = [
    "Eco-friendly kitchenware for modern homes",
    "Biodegradable cleaning supplies for eco-conscious consumers",
    "Organic cotton baby clothes for sensitive skin",
    "Natural organic skincare range for sensitive skin",
    "Tech gadgets for smart homes: 2024 edition",
    "Sustainable gardening tools and compost solutions",
    "Sensitive skin-friendly facial cleansers and toners",
    "Organic food wraps and storage solutions",
    "All-natural pet food for dogs with allergies",
    "Yoga mats made from recycled materials",
]

const results = await rank(query, documents, { return_documents: true, top_k: 3 });
console.log(results);

That's it! You can now use the jina-reranker-v1-turbo-en model in your projects.

Evaluation

We evaluated Jina Reranker on 3 key benchmarks to ensure top-tier performance and search relevance.

Note:

• NDCG@10 is a measure of ranking quality, with higher scores indicating better search results. Hit Rate measures the percentage of relevant documents that appear in the top 10 search results.
• The results of LoCo datasets on other models are not available since they do not support long documents more than 512 tokens.

For more details, please refer to our benchmarking sheets.

Contact

Join our Discord community and chat with other community members about ideas.