README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
base_model: microsoft/codebert-base
widget:
  - source_sentence: >-
      But Close wondered whether the package would be worth the cost of
      licensing the third-party software , along with Salesforce.com 's rental
      price .
    sentences:
      - >-
        Close also questions whether it would be worth the cost of licensing
        third-party software , along with Salesforce.com 's rental price .
      - >-
        No tumors were detected ; rather , empty cavities and scar tissue were
        found in their place .
      - >-
        A race observer sits in the passenger seat of the follow vehicle to
        record any broken rules and also keep track of the car 's time .
  - source_sentence: >-
      Almihdhar and Alhazmi were aboard American Airlines Flight 77 , which
      crashed into the Pentagon .
    sentences:
      - >-
        Both have been identified as some of the hijackers who flew American
        Airlines Flight 77 into the Pentagon .
      - >-
        " The Congress of the United States has never — ever — outlawed a
        medical procedure , " said Rep. Louise McIntosh Slaughter ( D-N.Y. ) .
      - >-
        The agency wants him to return the illegal proceeds with interest and
        pay civil monetary penalties .
  - source_sentence: >-
      He also called Hovan a " person of good reputation " who had worked as a
      bus driver since 1967 .
    sentences:
      - >-
        The other victim , Michael Walker , of 550 Barbey Street , was struck in
        the neck .
      - >-
        The Fijian military installed an all-indigenous government led by Mr
        Qarase , who won democratic elections in September 2001 .
      - >-
        Hovan , a resident of Trumbull , Conn . , had worked as a bus driver
        since 1967 and had no prior criminal record .
  - source_sentence: >-
      Had the creditors turned down the bailout plan , LG Group might have been
      forced to close down its credit card business .
    sentences:
      - >-
        If the creditors turn down the bailout plan , LG Group may have to
        closedown its card business .
      - >-
        Passengers on that cruise are to be given a refund and voucher for
        another trip .
      - >-
        " People who were on their way home , all of a sudden taken from us , "
        Mr. Bloomberg said of the collision .
  - source_sentence: >-
      " Any decision on Charleroi will have huge implications for regional
      airports in France , " he said .
    sentences:
      - >-
        " A bad decision on Charleroi would have huge implications for
        state-owned regional airports in France .
      - >-
        Launched from space shuttle Atlantis ( news - web sites ) in 1989 ,
        Galileo will have traveled about 2.8 billion miles by the time it hits
        Jupiter .
      - >-
        He said the ferry 's crew will be interviewed and tested for drugs and
        alcohol .
pipeline_tag: sentence-similarity
library_name: sentence-transformers

Kiel-2-Matrix

Kiel-2-Matrix is a specialized dense embedding model based on microsoft/codebert-base for code and text representation.

This is a sentence-transformers model that maps sentences and code blocks into a 768-dimensional dense vector space optimized for semantic textual similarity, semantic search, and clustering tasks.

---

Model Details

Model Description

• Model Type: Sentence Transformer / Dense Embedding Backbone
• Base Model: microsoft/codebert-base
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text & Code

Model Sources

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

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': 'RobertaModel'})
  (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-Matrix")

# 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)",
}