Modelpublic

redis/langcache-embed-v1

sourceHugging Faceupdated 10mo agoView on Hugging Face

16likes151kdownloads

Model Card

WARNING: This is an outdated model.

🚀 Check out our new v3-small model, trained for improved inference speed, lighter footprint, and better semantic matching for caching.

Redis semantic caching embedding model based on Alibaba-NLP/gte-modernbert-base

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-modernbert-base on the Quora dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity for the purpose of semantic caching.

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:
—Quora

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}) with Transformer model: 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

First install the Sentence Transformers library:

bash

pip install -U sentence-transformers

Then you can load this model and run inference.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("redis/langcache-embed-v1")
# Run inference
sentences = [
    'Will the value of Indian rupee increase after the ban of 500 and 1000 rupee notes?',
    'What will be the implications of banning 500 and 1000 rupees currency notes on Indian economy?',
    "Are Danish Sait's prank calls fake?",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)

Binary Classification

Metric	Value
cosine_accuracy	0.90
cosine_f1	0.87
cosine_precision	0.84
cosine_recall	0.90
cosine_ap	0.92

Training Dataset

Quora

—Dataset: Quora
—Size: 323491 training samples
—Columns: <code>question1</code>, <code>question2</code>, and <code>label</code>

Evaluation Dataset

Quora

—Dataset: Quora
—Size: 53486 evaluation samples
—Columns: <code>question1</code>, <code>question2</code>, and <code>label</code>

Citation

BibTeX

Redis Langcache-embed Models

bibtex

@inproceedings{langcache-embed-v1,
    title = "Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Data",
    author = "Gill, Cechmanek, Hutcherson, Rajamohan, Agarwal, Gulzar, Singh, Dion",
    month = "04",
    year = "2025",
    url = "https://arxiv.org/abs/2504.02268",
}

Sentence Transformers

bibtex

@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",
}

<!--