E5 Small Korean

🚀 upskyy/e5-small-korean

This model is a fine - tuned version of intfloat/multilingual-e5-small on korsts and kornli datasets. It maps sentences and paragraphs into a 384 - dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, etc.

🚀 Quick Start

This model is a fine - tuned version of intfloat/multilingual-e5-small on korsts and kornli datasets. It can map sentences and paragraphs to a 384 - dimensional dense vector space, which is useful for various NLP tasks such as semantic textual similarity, semantic search, paraphrase mining, text classification, and clustering.

✨ Features

• Multilingual Support: Supports multiple languages including Korean, which broadens its application scope.
• High - Dimensional Embeddings: Outputs 384 - dimensional dense vector embeddings for sentences and paragraphs.
• Cosine Similarity: Uses cosine similarity as the similarity function, which is effective for measuring semantic similarity.

📦 Installation

First, you need to install the Sentence Transformers library:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("upskyy/e5-small-korean")

# Run inference
sentences = [
    '아이를 가진 엄마가 해변을 걷는다.',
    '두 사람이 해변을 걷는다.',
    '한 남자가 해변에서 개를 산책시킨다.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Advanced Usage

Without using the sentence - transformers library, you can use the model as follows. First, pass your input through the transformer model, and then apply the appropriate pooling operation on the contextualized word embeddings.

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 = ["안녕하세요?", "한국어 문장 임베딩을 위한 버트 모델입니다."]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained("upskyy/e5-small-korean")
model = AutoModel.from_pretrained("upskyy/e5-small-korean")

# 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)

📚 Documentation

Model Details

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Evaluation

Semantic Similarity

• Dataset: sts-dev
• Evaluated with EmbeddingSimilarityEvaluator

Framework Versions

• Python: 3.10.13
• Sentence Transformers: 3.0.1
• Transformers: 4.42.4
• PyTorch: 2.3.0+cu121
• Accelerate: 0.30.1
• Datasets: 2.16.1
• Tokenizers: 0.19.1

🔧 Technical Details

The model is based on the SentenceTransformer framework. It consists of a Transformer layer and a Pooling layer. The Transformer layer uses a BertModel to generate contextualized word embeddings, and the Pooling layer aggregates these embeddings to obtain sentence - level embeddings.

📄 License

This model is released under the MIT license.

📖 Citation

BibTeX

@article{wang2024multilingual,
  title={Multilingual E5 Text Embeddings: A Technical Report},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Yang, Linjun and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2402.05672},
  year={2024}
}

@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 = "https://arxiv.org/abs/1908.10084",
}