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:400
- loss:AdaFaceInBatchLoss
base_model: Alibaba-NLP/gte-modernbert-base
widget:
- source_sentence: >-
The aversive or evitative case ( abbreviated ) is a grammatical case that
is found in Australian Aboriginal languages and indicates that the marked
noun is avoided or feared .
sentences:
- >-
The aversive or evitative case ( abbreviated ) is a grammatical case
that is found in Australian Aboriginal languages and indicates that the
marked noun is avoided or feared .
- He was born in Ryno , Johannesburg , died in North West .
- >-
The aversive or evitative case ( abbreviated ) is a marked case found in
Australian Aboriginal languages that indicates that the grammatical noun
is avoided or feared .
- source_sentence: >-
Three ships of the Royal Australian Navy ( RAN ) were named after Perth ,
the capital city of Western Australia , as HMAS `` Perth `` .
sentences:
- >-
Three ships of the Royal Australian Navy ( RAN ) have been named HMAS ``
Western Australia `` after Perth , the capital city of Perth .
- >-
Three ships of the Royal Australian Navy ( RAN ) were named after Perth
, the capital city of Western Australia , as HMAS `` Perth `` .
- >-
He lost the title to Rees after Iestyn Rees purchased his title shot at
PWE Jingle All The Galloway .
- source_sentence: >-
Oxynoe azuropunctata is a kind of small sea snail or sea snail , a bubble
snail , a marine gastropod mollusk in the Oxynoidae family .
sentences:
- >-
It is located at Ellison Bay , in the town of Liberty Grove , Wisconsin
.
- >-
Oxynoe azuropunctata is a kind of small sea snail or sea snail , a
bubble snail , a marine gastropod mollusk in the Oxynoidae family .
- >-
Oxynoe azuropunctata is a species of marine sea snail or sea slug , a
bubble snail , a small gastropod mollusk in the family Oxynoidae .
- source_sentence: >-
It included the original six tracks , re-worked with new vocals and live
drums , three remixes , and new two tracks .
sentences:
- >-
It included the original six tracks , overhauled with new vocals and
live drums , three remixes and two new tracks .
- >-
Punish Lichfield , garrison Birmingham , and clear the country as far as
possible .
- >-
Antoninus , or known as Antoninus , was a Roman who lived in the 1st
century .
- source_sentence: >-
It is known from Australia , including South Australia , Tasmania ,
Queensland , New South Wales and Victoria .
sentences:
- >-
It is famous from Australia , including South Australia , Tasmania ,
Queensland , New South Wales and Victoria .
- In 1995 Franz married Joanie Zeck , whom he met in 1982 .
- >-
In 1792 , the family moved to Kingston in Toronto and then York ( later
renamed Upper Canada ) .
datasets:
- redis/langcache-sentencepairs-v2
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- cosine_accuracy@1
- cosine_precision@1
- cosine_recall@1
- cosine_ndcg@10
- cosine_mrr@1
- cosine_map@100
model-index:
- name: Redis fine-tuned BiEncoder model for semantic caching on LangCache
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: test
type: test
metrics:
- type: cosine_accuracy@1
value: 0.5861241448475948
name: Cosine Accuracy@1
- type: cosine_precision@1
value: 0.5861241448475948
name: Cosine Precision@1
- type: cosine_recall@1
value: 0.5679885764966713
name: Cosine Recall@1
- type: cosine_ndcg@10
value: 0.7729838064849864
name: Cosine Ndcg@10
- type: cosine_mrr@1
value: 0.5861241448475948
name: Cosine Mrr@1
- type: cosine_map@100
value: 0.7216697804426214
name: Cosine Map@100
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: 100 tokens
- Output Dimensionality: 768 dimensions
- Similarity Function: Cosine Similarity
- Training Dataset:
- 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': 100, '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 = [
'It is known from Australia , including South Australia , Tasmania , Queensland , New South Wales and Victoria .',
'It is famous from Australia , including South Australia , Tasmania , Queensland , New South Wales and Victoria .',
'In 1792 , the family moved to Kingston in Toronto and then York ( later renamed Upper Canada ) .',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0078, 0.9531, 0.5898],
# [0.9531, 0.9961, 0.5898],
# [0.5898, 0.5898, 0.9922]], dtype=torch.bfloat16)
Evaluation
Metrics
Information Retrieval
- Dataset:
test
- Evaluated with
InformationRetrievalEvaluator
Metric | Value |
---|---|
cosine_accuracy@1 | 0.5861 |
cosine_precision@1 | 0.5861 |
cosine_recall@1 | 0.568 |
cosine_ndcg@10 | 0.773 |
cosine_mrr@1 | 0.5861 |
cosine_map@100 | 0.7217 |
Training Details
Training Dataset
LangCache Sentence Pairs (all)
- Dataset: LangCache Sentence Pairs (all)
- Size: 199 training samples
- Columns:
anchor
,positive
, andnegative
- Approximate statistics based on the first 199 samples:
anchor positive negative type string string string details - min: 9 tokens
- mean: 26.47 tokens
- max: 42 tokens
- min: 9 tokens
- mean: 26.47 tokens
- max: 42 tokens
- min: 9 tokens
- mean: 25.93 tokens
- max: 42 tokens
- Samples:
anchor positive negative 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 .
He was at the Westminster School under Richard Busby and studied at Christ Church , Oxford with Henry Aldrich .
The newer punts are still very much in existence today and run in the same fleets as the older boats .
The newer Punts are still very much in existence today and race in the same fleets as the older boats .
Richard Cheyne was the son and heir of Robert Cralle of Shurland and Margery , daughter and coheiress of Cheyne of Cralle , Sussex .
Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .
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 .
- Loss:
losses.AdaFaceInBatchLoss
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: 199 evaluation samples
- Columns:
anchor
,positive
, andnegative
- Approximate statistics based on the first 199 samples:
anchor positive negative type string string string details - min: 9 tokens
- mean: 26.47 tokens
- max: 42 tokens
- min: 9 tokens
- mean: 26.47 tokens
- max: 42 tokens
- min: 9 tokens
- mean: 25.93 tokens
- max: 42 tokens
- Samples:
anchor positive negative 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 .
He was at the Westminster School under Richard Busby and studied at Christ Church , Oxford with Henry Aldrich .
The newer punts are still very much in existence today and run in the same fleets as the older boats .
The newer Punts are still very much in existence today and race in the same fleets as the older boats .
Richard Cheyne was the son and heir of Robert Cralle of Shurland and Margery , daughter and coheiress of Cheyne of Cralle , Sussex .
Turner Valley , was at the Turner Valley Bar N Ranch Airport , southwest of the Turner Valley Bar N Ranch , Alberta , Canada .
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 .
- Loss:
losses.AdaFaceInBatchLoss
with these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false }
Training Logs
Epoch | Step | test_cosine_ndcg@10 |
---|---|---|
-1 | -1 | 0.7730 |
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",
}