redis/langcache-embed-v3

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: 8192 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • LangCache Sentence Pairs (all)
• 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': 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("redis/langcache-embed-v3")
# Run inference
sentences = [
    'A European Union spokesman said the Commission was consulting EU member states " with a view to taking appropriate action if necessary " on the matter .',
    "Laos 's second most important export destination - said it was consulting EU member states ' ' with a view to taking appropriate action if necessary ' ' on the matter .",
    'the form data assumes and the possible range of values that the attribute defined as that type of data may express  1. text 2. numerical',
]
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, 0.8789, 0.4961],
#         [0.8789, 1.0000, 0.4648],
#         [0.4961, 0.4648, 1.0078]], dtype=torch.bfloat16)

Evaluation

Metrics

Binary Classification

• Datasets: val and test
• Evaluated with BinaryClassificationEvaluator

Metric	val	test
cosine_accuracy	0.7638	0.7038
cosine_accuracy_threshold	0.8641	0.8524
cosine_f1	0.6913	0.7122
cosine_f1_threshold	0.8258	0.8119
cosine_precision	0.6289	0.5989
cosine_recall	0.7673	0.8784
cosine_ap	0.7354	0.6477
cosine_mcc	0.4778	0.4418

Training Details

Training Dataset

LangCache Sentence Pairs (all)

• Dataset: LangCache Sentence Pairs (all)
• Size: 8,405 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 6 tokens mean: 24.89 tokens max: 50 tokens	min: 6 tokens mean: 24.3 tokens max: 43 tokens	0: ~45.80% 1: ~54.20%

• Samples:

  sentence1	sentence2	label
  He said the foodservice pie business doesn 't fit the company 's long-term growth strategy .	" The foodservice pie business does not fit our long-term growth strategy .	1
  Magnarelli said Racicot hated the Iraqi regime and looked forward to using his long years of training in the war .	His wife said he was " 100 percent behind George Bush " and looked forward to using his years of training in the war .	0
  The dollar was at 116.92 yen against the yen , flat on the session , and at 1.2891 against the Swiss franc , also flat .	The dollar was at 116.78 yen JPY = , virtually flat on the session , and at 1.2871 against the Swiss franc CHF = , down 0.1 percent .	0

• 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: 8,405 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 6 tokens mean: 24.89 tokens max: 50 tokens	min: 6 tokens mean: 24.3 tokens max: 43 tokens	0: ~45.80% 1: ~54.20%

• Samples:

  sentence1	sentence2	label
  He said the foodservice pie business doesn 't fit the company 's long-term growth strategy .	" The foodservice pie business does not fit our long-term growth strategy .	1
  Magnarelli said Racicot hated the Iraqi regime and looked forward to using his long years of training in the war .	His wife said he was " 100 percent behind George Bush " and looked forward to using his years of training in the war .	0
  The dollar was at 116.92 yen against the yen , flat on the session , and at 1.2891 against the Swiss franc , also flat .	The dollar was at 116.78 yen JPY = , virtually flat on the session , and at 1.2871 against the Swiss franc CHF = , down 0.1 percent .	0

• 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	0.7354	0.6477

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",
}

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},
}