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 Sources

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("aditeyabaral-redis/langcache-embed-v3")
# Run inference
sentences = [
    'The band pursued `` signals `` in January 2012 in three weeks , and drums were recorded in a day and a half .',
    'The band tracked `` Signals `` in three weeks in January 2012 . Drums were recorded in a day and a half .',
    'Contributors include actor Anton LaVey , Satanist Christopher Lee , serial killer expert Clive Barker , author Karen Greenlee , and necrophile Robert Ressler .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9599, 0.4944],
#         [0.9599, 1.0000, 0.5097],
#         [0.4944, 0.5097, 1.0000]])

Evaluation

Metrics

Binary Classification

Metric val test
cosine_accuracy 0.763 0.7035
cosine_accuracy_threshold 0.864 0.8521
cosine_f1 0.6907 0.7118
cosine_f1_threshold 0.8262 0.811
cosine_precision 0.6291 0.5979
cosine_recall 0.7658 0.8794
cosine_ap 0.7351 0.6474
cosine_mcc 0.4771 0.4409

Training Details

Training Dataset

LangCache Sentence Pairs (all)

  • Dataset: LangCache Sentence Pairs (all)
  • Size: 62,021 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: 27.46 tokens
    • max: 53 tokens
    • min: 9 tokens
    • mean: 27.36 tokens
    • max: 52 tokens
    • 0: ~50.30%
    • 1: ~49.70%
  • 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
    Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the 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 . 0
    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
  • 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: 62,021 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: 27.46 tokens
    • max: 53 tokens
    • min: 9 tokens
    • mean: 27.36 tokens
    • max: 52 tokens
    • 0: ~50.30%
    • 1: ~49.70%
  • 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
    Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the 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 . 0
    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
  • 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 0.7351 0.6474

Framework Versions

  • Python: 3.12.3
  • Sentence Transformers: 5.1.0
  • Transformers: 4.55.0
  • PyTorch: 2.8.0+cu128
  • Accelerate: 1.10.0
  • Datasets: 4.0.0
  • Tokenizers: 0.21.4

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},
}
Downloads last month
96
Safetensors
Model size
149M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for aditeyabaral-redis/langcache-embed-v3

Finetuned
(14)
this model

Dataset used to train aditeyabaral-redis/langcache-embed-v3

Evaluation results