Langcache Crossencoder V1 Ms Marco MiniLM L6 V2

🚀 Redis語義緩存CrossEncoder模型（在Quora問題對上微調）

這是一個基於Cross Encoder的模型，它在Quora問題對LangCache訓練集上，從cross-encoder/ms-marco-MiniLM-L6-v2微調而來。該模型可以計算文本對的得分，可用於句子對分類任務。

✨ 主要特性

• 基於Cross Encoder架構，能夠有效處理文本對分類任務。
• 在Quora問題對數據集上進行微調，適用於語義相似性判斷、語義搜索等場景。
• 支持多種評估指標，如準確率、F1值等，可全面評估模型性能。

📦 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

安裝完Sentence Transformers庫後，你可以加載該模型並進行推理：

from sentence_transformers import CrossEncoder

# 從🤗 Hub下載模型
model = CrossEncoder("aditeyabaral-redis/langcache-crossencoder-v1-ms-marco-MiniLM-L6-v2")
# 獲取文本對的得分
pairs = [
    ['How can I get a list of my Gmail accounts?', 'How can I find all my old Gmail accounts?'],
    ['How can I stop Quora from modifying and editing other people’s questions on Quora?', 'Can I prevent a Quora user from editing my question on Quora?'],
    ['How much does it cost to design a logo in india?', 'How much does it cost to design a logo?'],
    ['What is screenedrenters.com?', 'What is allmyapps.com?'],
    ['What are the best colleges for an MBA in Australia?', 'What are the top MBA schools in Australia?'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

高級用法

你還可以根據與單個文本的相似度對不同文本進行排序：

# 對不同文本進行排序
ranks = model.rank(
    'How can I get a list of my Gmail accounts?',
    [
        'How can I find all my old Gmail accounts?',
        'Can I prevent a Quora user from editing my question on Quora?',
        'How much does it cost to design a logo?',
        'What is allmyapps.com?',
        'What are the top MBA schools in Australia?',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

📚 詳細文檔

模型詳情

模型信息

模型來源

• 文檔：Sentence Transformers文檔
• 文檔：Cross Encoder文檔
• 倉庫：GitHub上的Sentence Transformers
• Hugging Face：Hugging Face上的Cross Encoders

評估指標

交叉編碼器分類

• 數據集：quora-eval
• 評估方法：使用CrossEncoderClassificationEvaluator進行評估

訓練詳情

訓練數據集

Quora Question Pairs LangCache Train Set

• 數據集：Quora Question Pairs LangCache Train Set
• 規模：363,861個訓練樣本
• 列信息：sentence1、sentence2和label
• 基於前1000個樣本的近似統計信息：

  	句子1	句子2	標籤
  類型	字符串	字符串	整數
  詳情	最小長度: 15個字符 平均長度: 60.22個字符 最大長度: 229個字符	最小長度: 14個字符 平均長度: 60.0個字符 最大長度: 274個字符	0: ~63.50% 1: ~36.50%

• 樣本示例：

  句子1	句子2	標籤
  Why do people believe in God and how can they say he/she exists?	Why do we kill each other in the name of God?	0
  What are the chances of a bee sting when a bee buzzes around you?	How can I tell if my bees are agitated/likely to sting?	0
  If a man from Syro Malankara church marries a Syro-Malabar girl, can they join a Syro-Malabar parish?	Is Malabar Hills of Mumbai anyhow related to Malabar of Kerala?	0

• 損失函數：BinaryCrossEntropyLoss，參數如下：

{
    "activation_fn": "torch.nn.modules.linear.Identity",
    "pos_weight": null
}

評估數據集

Quora Question Pairs LangCache Validation Set

• 數據集：Quora Question Pairs LangCache Validation Set
• 規模：40,429個評估樣本
• 列信息：sentence1、sentence2和label
• 基於前1000個樣本的近似統計信息：

  	句子1	句子2	標籤
  類型	字符串	字符串	整數
  詳情	最小長度: 13個字符 平均長度: 59.91個字符 最大長度: 266個字符	最小長度: 13個字符 平均長度: 59.51個字符 最大長度: 293個字符	0: ~63.80% 1: ~36.20%

• 樣本示例：

  句子1	句子2	標籤
  How can I get a list of my Gmail accounts?	How can I find all my old Gmail accounts?	1
  How can I stop Quora from modifying and editing other people’s questions on Quora?	Can I prevent a Quora user from editing my question on Quora?	1
  How much does it cost to design a logo in india?	How much does it cost to design a logo?	0

• 損失函數：BinaryCrossEntropyLoss，參數如下：

{
    "activation_fn": "torch.nn.modules.linear.Identity",
    "pos_weight": null
}

訓練超參數

非默認超參數

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• learning_rate: 0.0002
• num_train_epochs: 15
• load_best_model_at_end: True
• push_to_hub: True
• hub_model_id: aditeyabaral-redis/langcache-crossencoder-v1-ms-marco-MiniLM-L6-v2

所有超參數

訓練日誌

📄 許可證

本模型使用Apache-2.0許可證。