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:1047690
  - loss:CoSENTLoss
base_model: Alibaba-NLP/gte-modernbert-base
widget:
  - source_sentence: >-
      That is evident from their failure , three times in a row , to get a big
      enough turnout to elect a president .
    sentences:
      - >-
        given a text, decide to which of a predefined set of classes it
        belongs.  examples: language identification, genre classification,
        sentiment analysis, and spam detection
      - >-
        Three times in a row , they failed to get a big _ enough turnout to
        elect a president .
      - >-
        He said the Government still did not know the real reason the original
        Saudi buyer pulled out on August 21 .
  - source_sentence: >-
      these use built-in and learned knowledge to make decisions and accomplish
      tasks that fulfill the intentions of the user.
    sentences:
      - >-
        It also features a 4.5 in back-lit LCD screen and memory expansion
        facilities .
      - >-
        - set of interrelated components - collect, process, store and
        distribute info. - support decision-making, coordination, and control
      - >-
        software programs that work without direct human intervention to carry
        out specific tasks for an individual user, business process, or software
        application -siri adapts to your preferences over time
  - source_sentence: >-
      any location in storage can be accessed at any moment in approximately the
      same amount of time.
    sentences:
      - >-
        your study can adopt the original model used by the cited theorist but
        you can modify different variables depending on your study of the whole
        theory
      - >-
        an access method that can access any storage location directly and in
        any order; primary storage devices and disk storage devices use random
        access...
      - >-
        Branson said that his preference would be to operate a fully commercial
        service on routes to New York , Barbados and Dubai .
  - source_sentence: >-
      United issued a statement saying it will " work professionally and
      cooperatively with all its unions . "
    sentences:
      - network that acts like the human brain; type of ai
      - >-
        a database system consists of one or more databases and a database
        management system (dbms).
      - >-
        Senior vice president Sara Fields said the airline " will work
        professionally and cooperatively with all our unions . "
  - source_sentence: >-
      A European Union spokesman said the Commission was consulting EU member
      states " with a view to taking appropriate action if necessary " on the
      matter .
    sentences:
      - >-
        Justice Minister Martin Cauchon and Prime Minister Jean Chretien both
        have said the government will introduce legislation to decriminalize
        possession of small amounts of pot .
      - >-
        Laos 's second most important export destination - said it was
        consulting EU member states ' ' with a view to taking appropriate action
        if necessary ' ' on the matter .
      - >-
        the form data assumes and the possible range of values that the
        attribute defined as that type of data may express  1. text 2. numerical
datasets:
  - redis/langcache-sentencepairs-v1
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - cosine_mcc
model-index:
  - name: Redis fine-tuned BiEncoder model for semantic caching on LangCache
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: val
          type: val
        metrics:
          - type: cosine_accuracy
            value: 0.7638310529446758
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.8640533685684204
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.6912742186395134
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.825770378112793
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.6289243437982501
            name: Cosine Precision
          - type: cosine_recall
            value: 0.7673469387755102
            name: Cosine Recall
          - type: cosine_ap
            value: 0.7353968345121902
            name: Cosine Ap
          - type: cosine_mcc
            value: 0.4778469995044085
            name: Cosine Mcc
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: test
          type: test
        metrics:
          - type: cosine_accuracy
            value: 0.7037777526966672
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.8524033427238464
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.7122170715871171
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.8118724822998047
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.5989283084033827
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8783612662942272
            name: Cosine Recall
          - type: cosine_ap
            value: 0.6476665223951498
            name: Cosine Ap
          - type: cosine_mcc
            value: 0.44182914870985407
            name: Cosine Mcc

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: 8192 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': 8192, '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 = [
    'A European Union spokesman said the Commission was consulting EU member states " with a view to taking appropriate action if necessary " on the matter .',
    "Laos 's second most important export destination - said it was consulting EU member states ' ' with a view to taking appropriate action if necessary ' ' on the matter .",
    'the form data assumes and the possible range of values that the attribute defined as that type of data may express  1. text 2. numerical',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0078, 0.8789, 0.4961],
#         [0.8789, 1.0000, 0.4648],
#         [0.4961, 0.4648, 1.0078]], dtype=torch.bfloat16)

Evaluation

Metrics

Binary Classification

Datasets: val and test
Evaluated with BinaryClassificationEvaluator

Metric	val	test
cosine_accuracy	0.7638	0.7038
cosine_accuracy_threshold	0.8641	0.8524
cosine_f1	0.6913	0.7122
cosine_f1_threshold	0.8258	0.8119
cosine_precision	0.6289	0.5989
cosine_recall	0.7673	0.8784
cosine_ap	0.7354	0.6477
cosine_mcc	0.4778	0.4418

Training Details

Training Dataset

LangCache Sentence Pairs (all)

Dataset: LangCache Sentence Pairs (all)
Size: 8,405 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 6 tokens
mean: 24.89 tokens
max: 50 tokens

min: 6 tokens
mean: 24.3 tokens
max: 43 tokens

0: ~45.80%
1: ~54.20%

	sentence1	sentence2	label
type	string	string	int
details	min: 6 tokens mean: 24.89 tokens max: 50 tokens	min: 6 tokens mean: 24.3 tokens max: 43 tokens	0: ~45.80% 1: ~54.20%

Samples:

sentence1	sentence2	label
`He said the foodservice pie business doesn 't fit the company 's long-term growth strategy .`	`" The foodservice pie business does not fit our long-term growth strategy .`	`1`
`Magnarelli said Racicot hated the Iraqi regime and looked forward to using his long years of training in the war .`	`His wife said he was " 100 percent behind George Bush " and looked forward to using his years of training in the war .`	`0`
`The dollar was at 116.92 yen against the yen , flat on the session , and at 1.2891 against the Swiss franc , also flat .`	`The dollar was at 116.78 yen JPY = , virtually flat on the session , and at 1.2871 against the Swiss franc CHF = , down 0.1 percent .`	`0`

Loss: CoSENTLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "pairwise_cos_sim"
}

Evaluation Dataset

LangCache Sentence Pairs (all)

Dataset: LangCache Sentence Pairs (all)
Size: 8,405 evaluation samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 6 tokens
mean: 24.89 tokens
max: 50 tokens

min: 6 tokens
mean: 24.3 tokens
max: 43 tokens

0: ~45.80%
1: ~54.20%

	sentence1	sentence2	label
type	string	string	int
details	min: 6 tokens mean: 24.89 tokens max: 50 tokens	min: 6 tokens mean: 24.3 tokens max: 43 tokens	0: ~45.80% 1: ~54.20%

Samples:

sentence1	sentence2	label
`He said the foodservice pie business doesn 't fit the company 's long-term growth strategy .`	`" The foodservice pie business does not fit our long-term growth strategy .`	`1`
`Magnarelli said Racicot hated the Iraqi regime and looked forward to using his long years of training in the war .`	`His wife said he was " 100 percent behind George Bush " and looked forward to using his years of training in the war .`	`0`
`The dollar was at 116.92 yen against the yen , flat on the session , and at 1.2891 against the Swiss franc , also flat .`	`The dollar was at 116.78 yen JPY = , virtually flat on the session , and at 1.2871 against the Swiss franc CHF = , down 0.1 percent .`	`0`

Loss: CoSENTLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "pairwise_cos_sim"
}

Training Logs

Epoch	Step	val_cosine_ap	test_cosine_ap
-1	-1	0.7354	0.6477

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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}