Langcache Crossencoder V1 Ms Marco MiniLM L6 V2

🚀 Redis语义缓存CrossEncoder模型（在Quora问题对上微调）

这是一个基于Cross Encoder的模型，它在Quora问题对LangCache训练集上，从cross-encoder/ms-marco-MiniLM-L6-v2微调而来。该模型可以计算文本对的得分，可用于句子对分类任务。

✨ 主要特性

• 基于Cross Encoder架构，能够有效处理文本对分类任务。
• 在Quora问题对数据集上进行微调，适用于语义相似性判断、语义搜索等场景。
• 支持多种评估指标，如准确率、F1值等，可全面评估模型性能。

📦 安装指南

首先，你需要安装Sentence Transformers库：

pip install -U sentence-transformers

💻 使用示例

基础用法

安装完Sentence Transformers库后，你可以加载该模型并进行推理：

from sentence_transformers import CrossEncoder

# 从🤗 Hub下载模型
model = CrossEncoder("aditeyabaral-redis/langcache-crossencoder-v1-ms-marco-MiniLM-L6-v2")
# 获取文本对的得分
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,)

高级用法

你还可以根据与单个文本的相似度对不同文本进行排序：

# 对不同文本进行排序
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': ...}, ...]

📚 详细文档

模型详情

模型信息

模型来源

• 文档：Sentence Transformers文档
• 文档：Cross Encoder文档
• 仓库：GitHub上的Sentence Transformers
• Hugging Face：Hugging Face上的Cross Encoders

评估指标

交叉编码器分类

• 数据集：quora-eval
• 评估方法：使用CrossEncoderClassificationEvaluator进行评估

训练详情

训练数据集

Quora Question Pairs LangCache Train Set

• 数据集：Quora Question Pairs LangCache Train Set
• 规模：363,861个训练样本
• 列信息：sentence1、sentence2和label
• 基于前1000个样本的近似统计信息：

  	句子1	句子2	标签
  类型	字符串	字符串	整数
  详情	最小长度: 15个字符 平均长度: 60.22个字符 最大长度: 229个字符	最小长度: 14个字符 平均长度: 60.0个字符 最大长度: 274个字符	0: ~63.50% 1: ~36.50%

• 样本示例：

  句子1	句子2	标签
  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

• 损失函数：BinaryCrossEntropyLoss，参数如下：

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

评估数据集

Quora Question Pairs LangCache Validation Set

• 数据集：Quora Question Pairs LangCache Validation Set
• 规模：40,429个评估样本
• 列信息：sentence1、sentence2和label
• 基于前1000个样本的近似统计信息：

  	句子1	句子2	标签
  类型	字符串	字符串	整数
  详情	最小长度: 13个字符 平均长度: 59.91个字符 最大长度: 266个字符	最小长度: 13个字符 平均长度: 59.51个字符 最大长度: 293个字符	0: ~63.80% 1: ~36.20%

• 样本示例：

  句子1	句子2	标签
  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

• 损失函数：BinaryCrossEntropyLoss，参数如下：

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

训练超参数

非默认超参数

• 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

所有超参数

训练日志

📄 许可证

本模型使用Apache-2.0许可证。