Redis fine-tuned CrossEncoder model for semantic caching on LangCache

This is a Cross Encoder model finetuned from Alibaba-NLP/gte-reranker-modernbert-base on the LangCache Sentence Pairs (subsets=['all'], train+val=True) dataset using the sentence-transformers library. It computes scores for pairs of texts, which can be used for sentence pair classification.

Model Details

Model Description

Model Type: Cross Encoder
Base model: Alibaba-NLP/gte-reranker-modernbert-base
Maximum Sequence Length: 8192 tokens
Number of Output Labels: 1 label
Training Dataset:
- LangCache Sentence Pairs (subsets=['all'], train+val=True)
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Cross Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Cross Encoders on Hugging Face

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 CrossEncoder

# Download from the 🤗 Hub
model = CrossEncoder("redis/langcache-reranker-v1-softmnrl-triplet")
# Get scores for pairs of texts
pairs = [
    [' What high potential jobs are there other than computer science?', ' What high potential jobs are there other than computer science?'],
    [' Would India ever be able to develop a missile system like S300 or S400 missile?', ' Would India ever be able to develop a missile system like S300 or S400 missile?'],
    [' water from the faucet is being drunk by a yellow dog', 'A yellow dog is drinking water from the faucet'],
    [' water from the faucet is being drunk by a yellow dog', 'The yellow dog is drinking water from a bottle'],
    ['! colspan = `` 14 `` `` Players who appeared for Colchester who left during the season ``', '! colspan = `` 14 `` `` Players who appeared for Colchester who left during the season ``'],
]
scores = model.predict(pairs)
print(scores.shape)
# (5,)

# Or rank different texts based on similarity to a single text
ranks = model.rank(
    ' What high potential jobs are there other than computer science?',
    [
        ' What high potential jobs are there other than computer science?',
        ' Would India ever be able to develop a missile system like S300 or S400 missile?',
        'A yellow dog is drinking water from the faucet',
        'The yellow dog is drinking water from a bottle',
        '! colspan = `` 14 `` `` Players who appeared for Colchester who left during the season ``',
    ]
)
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...]

Training Details

Training Dataset

LangCache Sentence Pairs (subsets=['all'], train+val=True)

Dataset: LangCache Sentence Pairs (subsets=['all'], train+val=True)
Size: 1,452,533 training samples
Columns: anchor, positive, and negative_1

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1
type	string	string	string
details	min: 24 characters mean: 114.25 characters max: 268 characters	min: 19 characters mean: 114.1 characters max: 226 characters	min: 4 characters mean: 93.04 characters max: 234 characters

Samples:

anchor	positive	negative_1
`Any Canadian teachers (B.Ed. holders) teaching in U.S. schools?`	`Any Canadian teachers (B.Ed. holders) teaching in U.S. schools?`	`Are there many Canadians living and working illegally in the United States?`
`Are there any underlying psychological tricks/tactics that are used when designing the lines for rides at amusement parks?`	`Are there any underlying psychological tricks/tactics that are used when designing the lines for rides at amusement parks?`	`Is there any tricks for straight lines mcqs?`
`Can I pay with a debit card on PayPal?`	`Can I pay with a debit card on PayPal?`	`Can you transfer PayPal funds onto a debit card/credit card?`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "num_negatives": 1,
    "activation_fn": "torch.nn.modules.activation.Sigmoid"
}

Evaluation Dataset

LangCache Sentence Pairs (split=test)

Dataset: LangCache Sentence Pairs (split=test)
Size: 110,066 evaluation samples
Columns: anchor, positive, and negative_1

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1
type	string	string	string
details	min: 3 characters mean: 97.95 characters max: 314 characters	min: 3 characters mean: 97.03 characters max: 314 characters	min: 11 characters mean: 74.49 characters max: 295 characters

Samples:

anchor	positive	negative_1
`What high potential jobs are there other than computer science?`	`What high potential jobs are there other than computer science?`	`Why IT or Computer Science jobs are being over rated than other Engineering jobs?`
`Would India ever be able to develop a missile system like S300 or S400 missile?`	`Would India ever be able to develop a missile system like S300 or S400 missile?`	`Should India buy the Russian S400 air defence missile system?`
`water from the faucet is being drunk by a yellow dog`	`A yellow dog is drinking water from the faucet`	`Do you get more homework in 9th grade than 8th?`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "num_negatives": 1,
    "activation_fn": "torch.nn.modules.activation.Sigmoid"
}

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",
}