ms-marco-MiniLM-L6-v2

cross-encoder text-ranking sentence-transformers en

cross-encoder/ms-marco-MiniLM-L6-v2

45,928,464

下载量

412

收藏数

79

浏览量

apache-2.0

许可

简介

该模型在MS Marco段落排序任务上进行了训练。

模型卡片

许可协议 apache-2.0

语言

en

框架 sentence-transformers

任务 text-ranking

数据集

msmarco

transformers

模型配置

模型类型 bert

架构 BertForSequenceClassification

模型详情

已翻译

面向 MS Marco 的 Cross-Encoder 模型

该模型基于 MS Marco 段落排序任务进行训练。

该模型可用于信息检索：给定一个查询，将查询与所有可能的段落（例如通过 ElasticSearch 检索到的段落）进行编码，然后按降序对段落进行排序。更多详情请参见 SBERT.net 检索与重排序。训练代码可在此处获取：SBERT.net 训练 MS Marco

与 SentenceTransformers 配合使用

安装 SentenceTransformers 后，使用起来非常简便。您可以像这样使用预训练模型：

from sentence_transformers import CrossEncoder

model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L6-v2')
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)
# [ 8.607138 -4.320078]

与 Transformers 配合使用

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/ms-marco-MiniLM-L6-v2')
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/ms-marco-MiniLM-L6-v2')

features = tokenizer(['How many people live in Berlin?', 'How many people live in Berlin?'], ['Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers.', 'New York City is famous for the Metropolitan Museum of Art.'],  padding=True, truncation=True, return_tensors="pt")

model.eval()
with torch.no_grad():
    scores = model(**features).logits
    print(scores)

性能表现

下表列出了多种预训练的 Cross-Encoder 模型及其在 TREC Deep Learning 2019 和 MS Marco 段落重排序数据集上的性能表现。

模型名称	NDCG@10 (TREC DL 19)	MRR@10 (MS Marco Dev)	文档数/秒
版本 2 模型
cross-encoder/ms-marco-TinyBERT-L2-v2	69.84	32.56	9000
cross-encoder/ms-marco-MiniLM-L2-v2	71.01	34.85	4100
cross-encoder/ms-marco-MiniLM-L4-v2	73.04	37.70	2500
cross-encoder/ms-marco-MiniLM-L6-v2	74.30	39.01	1800
cross-encoder/ms-marco-MiniLM-L12-v2	74.31	39.02	960
版本 1 模型
cross-encoder/ms-marco-TinyBERT-L2	67.43	30.15	9000
cross-encoder/ms-marco-TinyBERT-L4	68.09	34.50	2900
cross-encoder/ms-marco-TinyBERT-L6	69.57	36.13	680
cross-encoder/ms-marco-electra-base	71.99	36.41	340
其他模型
nboost/pt-tinybert-msmarco	63.63	28.80	2900
nboost/pt-bert-base-uncased-msmarco	70.94	34.75	340
nboost/pt-bert-large-msmarco	73.36	36.48	100
Capreolus/electra-base-msmarco	71.23	36.89	340
amberoad/bert-multilingual-passage-reranking-msmarco	68.40	35.54	330
sebastian-hofstaetter/distilbert-cat-margin_mse-T2-msmarco	72.82	37.88	720

注：运行时间基于 V100 GPU 计算得出。