Kiel-2-Poly

Kiel-2-Poly

Kiel-2-Poly is a specialized multilingual text embedding model based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2.

This is a sentence-transformers model that maps sentences and paragraphs across multiple languages into a 768-dimensional dense vector space optimized for cross-lingual semantic similarity, retrieval, and clustering tasks.

---

Model Details

Model Description

• Model Type: Sentence Transformer / Multilingual Dense Embedding Backbone
• Base Model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text (Multilingual)

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face Hub: kiel2/Kiel-2-Poly

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
)
Direct Usage (Sentence Transformers)
First, install the Sentence Transformers library:

Bash
pip install -U sentence-transformers
Then load your model and run inference:

Python
from sentence_transformers import SentenceTransformer

# Load your model from the Hugging Face Hub
model = SentenceTransformer("kiel2/Kiel-2-Poly")

# Run inference
sentences = [
    '" Any decision on Charleroi will have huge implications for regional airports in France , " he said .',
    '" A bad decision on Charleroi would have huge implications for state-owned regional airports in France .',
    "He said the ferry 's crew will be interviewed and tested for drugs and alcohol .",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
Citation
Code snippet
@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](https://arxiv.org/abs/1908.10084)",
}