E5 Base Unsupervised

🚀 E5-base-無監督模型

本模型與 e5-base 類似，但未經過有監督的微調。

通過弱監督對比預訓練生成文本嵌入。 梁旺、楊楠、黃曉龍、焦秉興、楊林軍、蔣大新、蘭甘·馬朱姆德、魏富如，arXiv 2022

該模型有 12 層，嵌入維度為 768。

🚀 快速開始

本模型可用於對文本進行編碼，下面將詳細介紹其使用方法。

✨ 主要特性

• 與 e5-base 類似，但未經過有監督的微調。
• 模型有 12 層，嵌入維度為 768。

💻 使用示例

基礎用法

以下是一個對 MS-MARCO 段落排名數據集中的查詢和段落進行編碼的示例：

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-base-unsupervised')
model = AutoModel.from_pretrained('intfloat/e5-base-unsupervised')

# 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())

高級用法

以下是使用 sentence_transformers 庫的示例：

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/e5-base-unsupervised')
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)

包依賴： pip install sentence_transformers~=2.2.2

📚 詳細文檔

訓練詳情

請參考我們的論文 https://arxiv.org/pdf/2212.03533.pdf。

基準評估

請查看 unilm/e5 以復現該模型在 BEIR 和 MTEB 基準 上的評估結果。

常見問題解答

⚠️ 重要提示

以下是使用該模型時的常見問題解答。

💡 使用建議

在使用模型前，建議仔細閱讀常見問題解答部分，以避免常見錯誤。

1. 是否需要在輸入文本前添加 "query: " 和 "passage: " 前綴？ 是的，模型是按照這種方式進行訓練的，否則模型性能會下降。 以下是一些使用建議：

• 對於非對稱任務，如開放問答中的段落檢索、即席信息檢索，應分別使用 "query: " 和 "passage: " 前綴。
• 對於對稱任務，如語義相似度、釋義檢索，使用 "query: " 前綴。
• 如果想將嵌入用作特徵，如線性探測分類、聚類，使用 "query: " 前綴。

2. 為什麼我復現的結果與模型卡片中報告的結果略有不同？ 不同版本的 transformers 和 pytorch 可能會導致性能出現細微但非零的差異。

引用

如果您覺得我們的論文或模型有幫助，請按以下格式引用：

@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}
}

侷限性

該模型僅適用於英文文本，長文本將被截斷為最多 512 個詞元。

📄 許可證

本模型採用 MIT 許可證。

貢獻者：michaelfeil