Gguf Jina Reranker V1 Tiny En

🚀 jina-reranker-v1-tiny-en-GGUF

jina-reranker-v1-tiny-en-GGUF 模型專為實現極快的重排序速度而設計，同時保持了具有競爭力的性能。它基於 JinaBERT 模型，能夠處理長達 8192 個標記的文本序列，在文本重排序任務中表現出色。

🚀 快速開始

使用 Jina AI 的 Reranker API

使用 Jina AI 的 Reranker API 是開始使用 jina-reranker-v1-tiny-en 的最簡單方法。

curl https://api.jina.ai/v1/rerank \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "jina-reranker-v1-tiny-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
}'

使用 sentence-transformers 庫

你可以使用最新版本的 sentence-transformers>=0.27.0 庫與模型進行交互。首先，通過以下命令安裝該庫：

pip install -U sentence-transformers

然後，使用以下代碼與模型進行交互：

from sentence_transformers import CrossEncoder

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

使用 transformers 庫

你還可以使用 transformers 庫以編程方式與模型進行交互。

!pip install transformers
from transformers import AutoModelForSequenceClassification

model = AutoModelForSequenceClassification.from_pretrained(
    'jinaai/jina-reranker-v1-tiny-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)

使用 transformers.js 庫

你可以使用 transformers.js 庫直接在 JavaScript（瀏覽器、Node.js、Deno 等）中運行模型。首先，通過以下命令安裝該庫：

npm i @xenova/transformers

然後，使用以下代碼與模型進行交互：

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

const model_id = 'jinaai/jina-reranker-v1-tiny-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);

✨ 主要特性

• 極快的重排序速度：通過知識蒸餾技術，該模型在保持較高準確率的同時，實現了極快的推理速度。
• 長序列處理能力：基於 JinaBERT 模型，支持對稱雙向的 ALiBi，能夠處理長達 8192 個標記的文本序列。
• 多種使用方式：支持通過 Jina AI 的 Reranker API、sentence-transformers 庫、transformers 庫和 transformers.js 庫與模型進行交互。

📦 安裝指南

安裝 sentence-transformers 庫

pip install -U sentence-transformers

安裝 transformers 庫

pip install transformers

安裝 transformers.js 庫

npm i @xenova/transformers

📚 詳細文檔

模型信息

重排序模型對比

評估結果

為確保頂級性能和搜索相關性，我們在 3 個關鍵基準測試中對 Jina Reranker 進行了評估。

⚠️ 重要提示

• NDCG@10 是衡量排序質量的指標，分數越高表示搜索結果越好。命中率 衡量的是相關文檔出現在前 10 個搜索結果中的百分比。
• 由於其他模型不支持超過 512 個標記的長文檔，因此無法獲取它們在 LoCo 數據集上的結果。

更多詳細信息，請參考我們的 基準測試表。

📄 許可證

本項目採用 Apache-2.0 許可證。

🔗 聯繫我們

加入我們的 Discord 社區，與其他社區成員交流想法。