KR SBERT V40K Kluenli Augsts

🚀 snunlp/KR-SBERT-V40K-klueNLI-augSTS

這是一個 sentence-transformers 模型，它可以將句子和段落映射到 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

本模型可通過 sentence-transformers 或 HuggingFace Transformers 兩種方式使用，下面為你詳細介紹。

📦 安裝指南

若要使用 sentence-transformers，可通過以下命令進行安裝：

pip install -U sentence-transformers

💻 使用示例

基礎用法（Sentence-Transformers）

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

model = SentenceTransformer('snunlp/KR-SBERT-V40K-klueNLI-augSTS')
embeddings = model.encode(sentences)
print(embeddings)

高級用法（HuggingFace Transformers）

若未安裝 sentence-transformers，可以按以下方式使用模型：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('snunlp/KR-SBERT-V40K-klueNLI-augSTS')
model = AutoModel.from_pretrained('snunlp/KR-SBERT-V40K-klueNLI-augSTS')

# 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, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

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

📚 詳細文檔

評估結果

若要對該模型進行自動評估，請參考 Sentence Embeddings Benchmark：https://seb.sbert.net

完整模型架構

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (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})
)

文檔分類應用

Google Colab 教程：https://colab.research.google.com/drive/1S6WSjOx9h6Wh_rX1Z2UXwx9i_uHLlOiM

📄 許可證

引用信息

@misc{kr-sbert,
  author = {Park, Suzi and Hyopil Shin},
  title = {KR-SBERT: A Pre-trained Korean-specific Sentence-BERT model},
  year = {2021},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/snunlp/KR-SBERT}}
}