langcache-embed-v3 / README.md

radoslavralev

Add new SentenceTransformer model

ce94dd5 verified about 2 months ago

preview code

raw

history blame

15.6 kB

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:483820
  - loss:MultipleNegativesSymmetricRankingLoss
base_model: Alibaba-NLP/gte-modernbert-base
widget:
  - source_sentence: >-
      See Precambrian time scale # Proposed Geologic timeline for another set of
      periods 4600 -- 541 MYA .
    sentences:
      - >-
        In 2014 election , Biju Janata Dal candidate Tathagat Satapathy
        Bharatiya Janata party candidate Rudra Narayan Pany defeated with a
        margin of 1.37,340 votes .
      - >-
        In Scotland , the Strathclyde Partnership for Transport , formerly known
        as Strathclyde Passenger Transport Executive , comprises the former
        Strathclyde region , which includes the urban area around Glasgow .
      - >-
        See Precambrian Time Scale # Proposed Geological Timeline for another
        set of periods of 4600 -- 541 MYA .
  - source_sentence: >-
      It is also 5 kilometers northeast of Tamaqua , 27 miles south of Allentown
      and 9 miles northwest of Hazleton .
    sentences:
      - In 1948 he moved to Massachusetts , and eventually settled in Vermont .
      - >-
        Suddenly I remembered that I was a New Zealander , I caught the first
        plane home and came back .
      - >-
        It is also 5 miles northeast of Tamaqua , 27 miles south of Allentown ,
        and 9 miles northwest of Hazleton .
  - source_sentence: >-
      The party has a Member of Parliament , a member of the House of Lords ,
      three members of the London Assembly and two Members of the European
      Parliament .
    sentences:
      - >-
        The party has one Member of Parliament , one member of the House of
        Lords , three Members of the London Assembly and two Members of the
        European Parliament .
      - >-
        Grapsid crabs dominate in Australia , Malaysia and Panama , while
        gastropods Cerithidea scalariformis and Melampus coeffeus are important
        seed predators in Florida mangroves .
      - >-
        Music Story is a music service website and international music data
        provider that curates , aggregates and analyses metadata for digital
        music services .
  - source_sentence: >-
      The play received two 1969 Tony Award nominations : Best Actress in a Play
      ( Michael Annals ) and Best Costume Design ( Charlotte Rae ) .
    sentences:
      - >-
        Ravishanker is a fellow of the International Statistical Institute and
        an elected member of the American Statistical Association .
      - >-
        In 1969 , the play received two Tony - Award nominations : Best Actress
        in a Theatre Play ( Michael Annals ) and Best Costume Design ( Charlotte
        Rae ) .
      - >-
        AMD and Nvidia both have proprietary methods of scaling , CrossFireX for
        AMD , and SLI for Nvidia .
  - source_sentence: >-
      He was a close friend of Ángel Cabrera and is a cousin of golfer Tony
      Croatto .
    sentences:
      - >-
        He was a close friend of Ángel Cabrera , and is a cousin of golfer Tony
        Croatto .
      - >-
        Eugenijus Bartulis ( born December 7 , 1949 in Kaunas ) is a Lithuanian
        Roman Catholic priest , and Bishop of Šiauliai .
      - >-
        UWIRE also distributes its members content to professional media outlets
        , including Yahoo , CNN and CBS News .
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: 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 = [
    'He was a close friend of Ángel Cabrera and is a cousin of golfer Tony Croatto .',
    'He was a close friend of Ángel Cabrera , and is a cousin of golfer Tony Croatto .',
    'UWIRE also distributes its members content to professional media outlets , including Yahoo , CNN and CBS News .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[0.9922, 0.9922, 0.5352],
#         [0.9922, 0.9961, 0.5391],
#         [0.5352, 0.5391, 1.0000]], dtype=torch.bfloat16)

Evaluation

Metrics

Binary Classification

Dataset: test
Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.7038
cosine_accuracy_threshold	0.8524
cosine_f1	0.7122
cosine_f1_threshold	0.8119
cosine_precision	0.5989
cosine_recall	0.8784
cosine_ap	0.6477
cosine_mcc	0.4418

Training Details

Training Dataset

LangCache Sentence Pairs (all)

Dataset: LangCache Sentence Pairs (all)
Size: 26,850 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 8 tokens
mean: 27.35 tokens
max: 53 tokens

min: 8 tokens
mean: 27.27 tokens
max: 52 tokens

1: 100.00%

	sentence1	sentence2	label
type	string	string	int
details	min: 8 tokens mean: 27.35 tokens max: 53 tokens	min: 8 tokens mean: 27.27 tokens max: 52 tokens	1: 100.00%

Samples:

sentence1	sentence2	label
`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 .`	`1`
`After losing his second election , he resigned as opposition leader and was replaced by Geoff Pearsall .`	`Max Bingham resigned as opposition leader after losing his second election , and was replaced by Geoff Pearsall .`	`1`
`The 12F was officially homologated on August 21 , 1929 and exhibited at the Paris Salon in 1930 .`	`The 12F was officially homologated on 21 August 1929 and displayed at the 1930 Paris Salon .`	`1`

Loss: MultipleNegativesSymmetricRankingLoss 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: 26,850 evaluation samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 8 tokens
mean: 27.35 tokens
max: 53 tokens

min: 8 tokens
mean: 27.27 tokens
max: 52 tokens

1: 100.00%

	sentence1	sentence2	label
type	string	string	int
details	min: 8 tokens mean: 27.35 tokens max: 53 tokens	min: 8 tokens mean: 27.27 tokens max: 52 tokens	1: 100.00%

Samples:

sentence1	sentence2	label
`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 .`	`1`
`After losing his second election , he resigned as opposition leader and was replaced by Geoff Pearsall .`	`Max Bingham resigned as opposition leader after losing his second election , and was replaced by Geoff Pearsall .`	`1`
`The 12F was officially homologated on August 21 , 1929 and exhibited at the Paris Salon in 1930 .`	`The 12F was officially homologated on 21 August 1929 and displayed at the 1930 Paris Salon .`	`1`

Loss: MultipleNegativesSymmetricRankingLoss with these parameters:

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

Training Logs

Epoch	Step	test_cosine_ap
-1	-1	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",
}