Sentence Transformers Paraphrase Multilingual Mpnet Base V2

🚀 sentence-transformers/paraphrase-multilingual-mpnet-base-v2

這是一個 sentence-transformers 模型，它可以將句子和段落映射到一個 768 維的密集向量空間，可用於聚類或語義搜索等任務。

🚀 快速開始

此模型是原模型 'sentence-transformers/paraphrase-multilingual-mpnet-base-v2' 的備份，因為原模型曾暫時下線。我並非該模型的作者。

✨ 主要特性

• 基於 sentence-transformers 框架，能夠將句子和段落映射到 768 維的密集向量空間。
• 可用於聚類、語義搜索等多種自然語言處理任務。

📦 安裝指南

若要使用該模型，需安裝 sentence-transformers：

pip install -U sentence-transformers

💻 使用示例

基礎用法

當你安裝了 sentence-transformers 後，使用該模型會非常簡單：

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)

高級用法

若未安裝 sentence-transformers，你可以按以下方式使用該模型：首先，將輸入傳遞給 Transformer 模型，然後對上下文詞嵌入應用正確的池化操作。

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')
model = AutoModel.from_pretrained('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

📚 詳細文檔

你可以通過 Sentence Embeddings Benchmark 對該模型進行自動評估：https://seb.sbert.net

🔧 技術細節

模型的完整架構如下：

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

📄 許可證

該模型使用的許可證為 Apache-2.0。

📚 引用與作者

該模型由 sentence-transformers 訓練。

如果你覺得該模型有幫助，請引用我們的論文 Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks：

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "http://arxiv.org/abs/1908.10084",
}