Finetuned Cross Encoder L6 V2

🚀 基於 cross-encoder/ms-marco-MiniLM-L6-v2 的交叉編碼器

這是一個基於 cross-encoder/ms-marco-MiniLM-L6-v2 微調的 交叉編碼器 模型，使用了 sentence-transformers 庫。它可以計算文本對的得分，可用於文本重排序和語義搜索。

🚀 快速開始

本模型可用於計算文本對的得分，適用於文本重排序和語義搜索等任務。下面將為你介紹如何使用該模型。

✨ 主要特性

• 基於 cross-encoder/ms-marco-MiniLM-L6-v2 微調，可計算文本對得分。
• 適用於文本重排序和語義搜索任務。

📦 安裝指南

首先，你需要安裝 sentence-transformers 庫：

pip install -U sentence-transformers

💻 使用示例

基礎用法

from sentence_transformers import CrossEncoder

# 從 Hugging Face Hub 下載模型
model = CrossEncoder("CharlesPing/finetuned-cross-encoder-l6-v2")
# 獲取文本對的得分
pairs = [
    ['‘Getting hung up on the exact nature of the records is interesting, and there’s lots of technical work that can be done there, but the main take-home response there is that the trends we’ve been seeing since the 1970s are continuing and have not paused in any way,’ he said.”', 'Rosenzweig also criticized the "waffling—encouraged by the NPOV policy—[which] means that it is hard to discern any overall interpretive stance in Wikipedia history".'],
    ['After the 9/11 terrorist attacks grounded commercial air traffic, "there was a temperature drop while the airplanes weren\'t flying, for the week afterwards."', 'Play media At 9:42\xa0a.m., the Federal Aviation Administration (FAA) grounded all civilian aircraft within the continental U.S., and civilian aircraft already in flight were told to land immediately.'],
    ['But the central message of the IPCC AR4, is confirmed by the peer reviewed literature.', 'Scientific consensus is normally achieved through communication at conferences, publication in the scientific literature, replication (reproducible results by others), and peer review.'],
    ['"Many people think the science of climate change is settled.', 'During his administration, the bridge from Filadelfia and Liberia was constructed, as was the Old National Theater.'],
    ['“Even if you could calculate some sort of meaningful global temperature statistic, the figure would be unimportant.', 'Quantitative information or data is based on quantities obtained using a quantifiable measurement process.'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# 或者根據與單個文本的相似度對不同文本進行排序
ranks = model.rank(
    '‘Getting hung up on the exact nature of the records is interesting, and there’s lots of technical work that can be done there, but the main take-home response there is that the trends we’ve been seeing since the 1970s are continuing and have not paused in any way,’ he said.”',
    [
        'Rosenzweig also criticized the "waffling—encouraged by the NPOV policy—[which] means that it is hard to discern any overall interpretive stance in Wikipedia history".',
        'Play media At 9:42\xa0a.m., the Federal Aviation Administration (FAA) grounded all civilian aircraft within the continental U.S., and civilian aircraft already in flight were told to land immediately.',
        'Scientific consensus is normally achieved through communication at conferences, publication in the scientific literature, replication (reproducible results by others), and peer review.',
        'During his administration, the bridge from Filadelfia and Liberia was constructed, as was the Old National Theater.',
        'Quantitative information or data is based on quantities obtained using a quantifiable measurement process.',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

📚 詳細文檔

模型詳情

模型描述

模型來源

• 文檔：Sentence Transformers 文檔
• 文檔：交叉編碼器文檔
• 倉庫：GitHub 上的 Sentence Transformers
• Hugging Face：Hugging Face 上的交叉編碼器

評估

指標

交叉編碼器重排序

• 數據集：cross-rerank-dev-mixed-neg
• 使用 CrossEncoderRerankingEvaluator 進行評估，參數如下：

  {
      "at_k": 10
  }
  

訓練詳情

訓練數據集

未命名數據集

• 大小：22,258 個訓練樣本
• 列：sentence_0、sentence_1 和 label
• 基於前 1000 個樣本的近似統計信息： | | sentence_0 | sentence_1 | label | |------|------|------|------| | 類型 | 字符串 | 字符串 | 浮點數 | | 詳情 |
  • 最小長度：26 個字符
  • 平均長度：121.91 個字符
  • 最大長度：319 個字符
  |
  • 最小長度：36 個字符
  • 平均長度：140.85 個字符
  • 最大長度：573 個字符
  |
  • 最小值：0.0
  • 平均值：0.16
  • 最大值：1.0
  |
• 樣本： | sentence_0 | sentence_1 | label | |------|------|------| | ‘Getting hung up on the exact nature of the records is interesting, and there’s lots of technical work that can be done there, but the main take-home response there is that the trends we’ve been seeing since the 1970s are continuing and have not paused in any way,’ he said.” | Rosenzweig also criticized the "waffling—encouraged by the NPOV policy—[which] means that it is hard to discern any overall interpretive stance in Wikipedia history". | 1.0 | | After the 9/11 terrorist attacks grounded commercial air traffic, "there was a temperature drop while the airplanes weren't flying, for the week afterwards." | Play media At 9:42 a.m., the Federal Aviation Administration (FAA) grounded all civilian aircraft within the continental U.S., and civilian aircraft already in flight were told to land immediately. | 1.0 | | But the central message of the IPCC AR4, is confirmed by the peer reviewed literature. | Scientific consensus is normally achieved through communication at conferences, publication in the scientific literature, replication (reproducible results by others), and peer review. | 1.0 |
• 損失函數：FitMixinLoss

訓練超參數

非默認超參數

• eval_strategy：按步數評估
• per_device_train_batch_size：16
• per_device_eval_batch_size：16

所有超參數

訓練日誌

框架版本

• Python: 3.11.12
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.6.0
• Datasets: 3.5.1
• Tokenizers: 0.21.1

🔧 技術細節

本模型基於 cross-encoder/ms-marco-MiniLM-L6-v2 微調，使用 sentence-transformers 庫進行訓練。訓練過程中使用了特定的超參數和損失函數，以優化模型在文本重排序任務上的性能。

📄 許可證

文檔中未提及相關許可證信息。

📖 引用

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}