metadata

language:
  - en
license: apache-2.0
tags:
  - biencoder
  - sentence-transformers
  - text-classification
  - sentence-pair-classification
  - semantic-similarity
  - semantic-search
  - retrieval
  - reranking
  - generated_from_trainer
  - dataset_size:1451941
  - loss:MultipleNegativesRankingLoss
base_model: Alibaba-NLP/gte-modernbert-base
widget:
  - source_sentence: >-
      Gocharya ji authored Krishna Cahrit Manas in the poetic form describing
      about the full life of Lord Krishna ( from birth to Nirvana ) .
    sentences:
      - 'Q: Can I buy coverage for prescription drugs right away?'
      - >-
        Krishna Cahrit Manas in poetic form , describing the full life of Lord
        Krishna ( from birth to nirvana ) , wrote Gocharya ji .
      - >-
        Baron played actress Violet Carson who portrayed Ena Sharples in the
        soap .
  - source_sentence: The Kilkenny line only reached Maryborough in 1867 .
    sentences:
      - It was also known formerly as ' Crotto ' .
      - The line from Maryborough only reached Kilkenny in 1867 .
      - The line from Kilkenny only reached Maryborough in 1867 .
  - source_sentence: >-
      Tokelau International Netball Team represents Tokelau in the national
      netball .
    sentences:
      - >-
        Ernest Dewey Albinson ( 1898 in Minneapolis , Minnesota - 1971 in Mexico
        ) was an American artist .
      - >-
        The Tokelau national netball team represents Tokelau in international
        netball .
      - >-
        The Tokelau international netball team represents Tokelau in national
        netball .
  - source_sentence: >-
      The real number is called the `` imaginary part `` of the real number ;
      the real number is called the `` complex part `` of .
    sentences:
      - >-
        The school board consists of Robbie Sanders , Bryan Richards , Linda
        Fullingim , Lori Lambert , & Kelly Teague .
      - Which web design company has the best templates?
      - >-
        The real number is called the `` imaginary part `` of the real number ,
        the real number of `` complex part `` of .
  - source_sentence: >-
      All For You was the third and last single of Kate Ryan 's third album ``
      Alive `` .
    sentences:
      - >-
        According to John Keay , he was `` country bred `` ( born and educated
        in India ) .
      - >-
        All For You was the third single of the third and last album `` Alive ``
        by Kate Ryan .
      - >-
        All For You was the third and last single of the third album of Kate
        Ryan `` Alive `` .
datasets:
  - redis/langcache-sentencepairs-v1
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_precision@1
  - cosine_recall@1
  - cosine_ndcg@10
  - cosine_mrr@1
  - cosine_map@100
model-index:
  - name: Redis fine-tuned BiEncoder model for semantic caching on LangCache
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: train
          type: train
        metrics:
          - type: cosine_accuracy@1
            value: 0.5579129681749296
            name: Cosine Accuracy@1
          - type: cosine_precision@1
            value: 0.5579129681749296
            name: Cosine Precision@1
          - type: cosine_recall@1
            value: 0.5359784831006956
            name: Cosine Recall@1
          - type: cosine_ndcg@10
            value: 0.7522148521266401
            name: Cosine Ndcg@10
          - type: cosine_mrr@1
            value: 0.5579129681749296
            name: Cosine Mrr@1
          - type: cosine_map@100
            value: 0.6974638651409195
            name: Cosine Map@100

Redis fine-tuned BiEncoder model for semantic caching on LangCache

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-modernbert-base on the LangCache Sentence Pairs (all) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for sentence pair similarity.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: Alibaba-NLP/gte-modernbert-base
Maximum Sequence Length: 100 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- LangCache Sentence Pairs (all)
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 100, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("redis/langcache-embed-v3")
# Run inference
sentences = [
    "All For You was the third and last single of Kate Ryan 's third album `` Alive `` .",
    'All For You was the third and last single of the third album of Kate Ryan `` Alive `` .',
    'All For You was the third single of the third and last album `` Alive `` by Kate Ryan .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[0.9961, 0.9922, 0.9961],
#         [0.9922, 1.0000, 0.9922],
#         [0.9961, 0.9922, 1.0078]], dtype=torch.bfloat16)

Evaluation

Metrics

Information Retrieval

Dataset: train
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.5579
cosine_precision@1	0.5579
cosine_recall@1	0.536
cosine_ndcg@10	0.7522
cosine_mrr@1	0.5579
cosine_map@100	0.6975

Training Details

Training Dataset

LangCache Sentence Pairs (all)

Dataset: LangCache Sentence Pairs (all)
Size: 109,885 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 8 tokens mean: 27.27 tokens max: 49 tokens	min: 8 tokens mean: 27.27 tokens max: 48 tokens	min: 7 tokens mean: 26.47 tokens max: 61 tokens

Samples:

anchor	positive	negative
`The newer Punts are still very much in existence today and race in the same fleets as the older boats .`	`The newer punts are still very much in existence today and run in the same fleets as the older boats .`	`how can I get financial freedom as soon as possible?`
`The newer punts are still very much in existence today and run in the same fleets as the older boats .`	`The newer Punts are still very much in existence today and race in the same fleets as the older boats .`	`The older Punts are still very much in existence today and race in the same fleets as the newer boats .`
`Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .`	`Turner Valley , , was located at Turner Valley Bar N Ranch Airport , southwest of Turner Valley Bar N Ranch , Alberta , Canada .`	`Turner Valley Bar N Ranch Airport , , was located at Turner Valley Bar N Ranch , southwest of Turner Valley , Alberta , Canada .`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Evaluation Dataset

LangCache Sentence Pairs (all)

Dataset: LangCache Sentence Pairs (all)
Size: 109,885 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 8 tokens mean: 27.27 tokens max: 49 tokens	min: 8 tokens mean: 27.27 tokens max: 48 tokens	min: 7 tokens mean: 26.47 tokens max: 61 tokens

Samples:

anchor	positive	negative
`The newer Punts are still very much in existence today and race in the same fleets as the older boats .`	`The newer punts are still very much in existence today and run in the same fleets as the older boats .`	`how can I get financial freedom as soon as possible?`
`The newer punts are still very much in existence today and run in the same fleets as the older boats .`	`The newer Punts are still very much in existence today and race in the same fleets as the older boats .`	`The older Punts are still very much in existence today and race in the same fleets as the newer boats .`
`Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .`	`Turner Valley , , was located at Turner Valley Bar N Ranch Airport , southwest of Turner Valley Bar N Ranch , Alberta , Canada .`	`Turner Valley Bar N Ranch Airport , , was located at Turner Valley Bar N Ranch , southwest of Turner Valley , Alberta , Canada .`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Training Logs

Epoch	Step	train_cosine_ndcg@10
-1	-1	0.7522

Framework Versions

Python: 3.12.3
Sentence Transformers: 5.1.0
Transformers: 4.56.0
PyTorch: 2.8.0+cu128
Accelerate: 1.10.1
Datasets: 4.0.0
Tokenizers: 0.22.0

Citation

BibTeX

Sentence Transformers

@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",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}