---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
base_model: BAAI/bge-small-en-v1.5
widget:
- source_sentence: Name a style of hot yoga.
  sentences:
  - Bikram.
  - Tallahassee is the capital of Florida
  - I want a redhead woman with tattoos and big boobs and a big ass
- source_sentence: What is Orchesis - either professional or amateur
  sentences:
  - Art of Dancing
  - The Price Brothers and Company
  - Steve Jobs. Because of his invention.
- source_sentence: What is the tiny piece at the end of a shoelace called?
  sentences:
  - Sinking Sand is most commonly known as Quicksand.
  - I would give the MVP award to Nikola Jokic.
  - An Aglet.
- source_sentence: Who was given Stockholm Water Prize 2022 ?
  sentences:
  - Prof.Wilfried Brutsaert
  - Kingfisher
  - If you have 3 dimes, you have 30 cents.
- source_sentence: How often is The Australian Chess Championship held?
  sentences:
  - Every two years
  - UC Berkeley; UCLA
  - Remove the - character and restore the split words in the markdown content.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---

# Kiel-2-Vector

**Kiel-2-Vector** is a dense embedding model based on `BAAI/bge-small-en-v1.5`. It maps inputs into a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

---

## Model Details

### Model Description
- **Model Type:** Sentence Transformer / Dense Embedding Backbone
- **Base Model:** [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5)
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 384 dimensions
- **Similarity Function:** Cosine Similarity
- **Supported Modality:** Text

### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face Hub:** [kiel2/Kiel-2-Vector](https://huggingface.co/kiel2/Kiel-2-Vector)

### Full Model Architecture
```text
SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', 'include_prompt': True})
  (2): Normalize({'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
)
Direct Usage (Sentence Transformers)
First, install the Sentence Transformers library:

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

Python
from sentence_transformers import SentenceTransformer

# Load from the 🤗 Hub
model = SentenceTransformer("kiel2/Kiel-2-Vector")

# Run inference
sentences = [
    'How often is The Australian Chess Championship held?',
    'Every two years',
    'Remove the - character and restore the split words in the markdown content.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# 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)",
}

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={[https://arxiv.org/abs/1807.03748](https://arxiv.org/abs/1807.03748)},
}