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-v2-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: 76,348,209 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: 6 characters mean: 55.35 characters max: 1131 characters	min: 5 characters mean: 55.02 characters max: 1131 characters	min: 8 characters mean: 76.33 characters max: 560 characters

Samples:

anchor	positive	negative_1
`"There aren't many places in Gold Coast where you can find a wide variety of wedding dresses."`	`"There aren't many places in Gold Coast where you can find a wide variety of wedding dresses."`	`Where can I get a wide variety of wedding dresses in Gold Coast?`
`It's easy to say it's good having siblings, but people often suggest it as a universal truth without considering that not everyone enjoys sibling relationships. Having siblings can lead to conflicts, competition, and stress, which might overshadow any potential benefits like companionship or support. Additionally, individual experiences with siblings can vary greatly depending on personality, family dynamics, and cultural background.`	`It's easy to say it's good having siblings, but people often suggest it as a universal truth without considering that not everyone enjoys sibling relationships. Having siblings can lead to conflicts, competition, and stress, which might overshadow any potential benefits like companionship or support. Additionally, individual experiences with siblings can vary greatly depending on personality, family dynamics, and cultural background.`	`What's it like having siblings?`
To reconcile the idea that 'Education is the Key to Success' with the presence of underemployed graduates and successful criminals, it's important to emphasize that education is one among many factors that contribute to success. Education equips individuals with knowledge, critical thinking skills, and problem-solving abilities, which are essential tools for navigating life's challenges and seizing opportunities. However, success is also influenced by other elements such as personal drive, social connections, opportunities presented, and sometimes sheer luck. Education does not guarantee success on its own; rather, it provides a foundation upon which individuals can build their careers and personal lives. Additionally, the definition of success can be subjective and varies across different cultures and individuals. It's crucial to address practical considerations like ensuring that educational curricula are relevant to the current job market and fostering environments where both hard ...	To reconcile the idea that 'Education is the Key to Success' with the presence of underemployed graduates and successful criminals, it's important to emphasize that education is one among many factors that contribute to success. Education equips individuals with knowledge, critical thinking skills, and problem-solving abilities, which are essential tools for navigating life's challenges and seizing opportunities. However, success is also influenced by other elements such as personal drive, social connections, opportunities presented, and sometimes sheer luck. Education does not guarantee success on its own; rather, it provides a foundation upon which individuals can build their careers and personal lives. Additionally, the definition of success can be subjective and varies across different cultures and individuals. It's crucial to address practical considerations like ensuring that educational curricula are relevant to the current job market and fostering environments where both hard ...	`How do you convince the upcoming generation that "Education is The Key of Success " when we are surrounded by poor graduates and rich criminals?`

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: 132,354 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: 96.44 characters max: 314 characters	min: 3 characters mean: 95.52 characters max: 314 characters	min: 10 characters mean: 72.75 characters max: 244 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`	`Childlessness is low in Eastern European countries.`

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",
}