E5-large

新闻（2023年5月）：请切换到 e5-large-v2 ，它具有更好的性能和相同的使用方法。

Text Embeddings by Weakly-Supervised Contrastive Pre-training .Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022

此模型共有24层，嵌入尺寸为1024。

使用方法

下面是一个示例，用于对MS-MARCO段落排序数据集中的查询和段落进行编码。

import torch.nn.functional as F

from torch import Tensor
from transformers import AutoTokenizer, AutoModel


def average_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]


# Each input text should start with "query: " or "passage: ".
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
               'query: summit define',
               "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
               "passage: Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."]

tokenizer = AutoTokenizer.from_pretrained('intfloat/e5-large')
model = AutoModel.from_pretrained('intfloat/e5-large')

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())

训练详情

请参阅我们在 https://arxiv.org/pdf/2212.03533.pdf 上的论文。

基准评估

查看 unilm/e5 以重现在 BEIR 和 MTEB benchmark 上的评估结果。

对sentence_transformers的支持

下面是与sentence_transformers一起使用的示例。

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/e5-large')
input_texts = [
    'query: how much protein should a female eat',
    'query: summit define',
    "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
    "passage: Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments."
]
embeddings = model.encode(input_texts, normalize_embeddings=True)

软件包要求

pip install sentence_transformers~=2.2.2

贡献者： michaelfeil

常见问题

1. 我需要在输入文本中添加前缀"query: "和"passage: "吗？

是的，这是模型训练的方式，否则性能会下降。

这里还有一些经验法则：

• 对于非对称任务（如开放式问答中的段落检索，自适应信息检索），相应地使用"query: "和"passage: "。

• 对于对称任务（如语义相似性，复述检索），使用"query: "前缀。

• 如果要将嵌入用作特征（例如线性探测分类，聚类），使用"query: "前缀。

2. 为什么我复现的结果与模型卡中报告的结果略有不同？

不同版本的 transformers 和 pytorch 可能导致微小但非零的性能差异。

引用

如果您发现我们的论文或模型有帮助，请考虑按以下方式引用：

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

限制

该模型仅适用于英文文本。长文本将被截断为最多512个标记。