Monoelectra Large

🚀 文本排序交叉编码器

本模型是将 webis/monoelectra-large 模型从 lightning-ir 迁移至 Sentence Transformers 和 Transformers 的版本。

原始模型在论文 A Systematic Investigation of Distilling Large Language Models into Cross-Encoders for Passage Re-ranking 中被提出。有关训练原始模型的代码，请参阅 https://github.com/webis-de/rank-distillm。

该模型可在两阶段的“检索 - 重排”管道中用作重排器，它会根据给定的查询对检索器模型（例如嵌入模型或 BM25）返回的段落进行重新排序。更多详细信息请参阅 SBERT.net 检索与重排。

🚀 快速开始

本模型可作为两阶段“检索 - 重排”管道中的重排器，依据查询对检索器模型返回的段落重新排序。

✨ 主要特性

• 是 webis/monoelectra-large 模型向 Sentence Transformers 和 Transformers 的迁移版本。
• 可用于文本排序，在两阶段“检索 - 重排”管道中发挥重排作用。

📦 安装指南

若要使用该模型，需要安装 SentenceTransformers，可使用以下命令进行安装：

pip install sentence-transformers

💻 使用示例

基础用法

使用 Sentence Transformers

from sentence_transformers import CrossEncoder

model = CrossEncoder("cross-encoder/monoelectra-large", trust_remote_code=True)
scores = model.predict([
    ("How many people live in Berlin?", "Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers."),
    ("How many people live in Berlin?", "Berlin is well known for its museums."),
])
print(scores)
# [ 6.016401  -3.6922567]

使用 Transformers

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model = AutoModelForSequenceClassification.from_pretrained("cross-encoder/monoelectra-large", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("cross-encoder/monoelectra-large")

features = tokenizer(
    [
        ("How many people live in Berlin?", "Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers."),
        ("How many people live in Berlin?", "Berlin is well known for its museums."),
    ],
    padding=True,
    truncation=True,
    return_tensors="pt",
)

model.eval()
with torch.no_grad():
    scores = model(**features).logits.view(-1)
print(scores)
# tensor([ 6.0164, -3.6923])

📄 许可证

本项目采用 Apache-2.0 许可证。