redis/langcache-embed-v2

SentenceTransformer based on redis/langcache-embed-v1

This is a sentence-transformers model finetuned from redis/langcache-embed-v1 on the triplet dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• —Model Type: Sentence Transformer
• —Base model: redis/langcache-embed-v1 <!-- at revision 80fb95b5478a6b6d068faf4452faa2f5bc9f0dfa -->
• —Maximum Sequence Length: 8192 tokens
• —Output Dimensionality: 768 dimensions
• —Similarity Function: Cosine Similarity
• —Training Dataset:
• —triplet <!-- - Language: Unknown --> <!-- - License: Unknown -->

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

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-v2")
# Run inference
sentences = [
    'What are some examples of crimes understood as a moral turpitude?',
    'What are some examples of crimes of moral turpitude?',
    'What are some examples of crimes understood as a legal aptitude?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

<!--

Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details> -->

<!--

Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details> -->

<!--

Out-of-Scope Use

List how the model may foreseeably be misused and address what users ought not to do with the model. -->

<!--

Bias, Risks and Limitations

What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. -->

<!--

Recommendations

What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. -->

Training Details

• —Dataset: triplet
• —Size: 36,864 training samples
• —Columns: <code>anchor</code>, <code>positive</code>, <code>negative1</code>, <code>negative2</code>, and <code>negative3</code> <!-- * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative1 | negative2 | negative3 | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | string | string | string | | details | <ul><li>min: 6 tokens</li><li>mean: 13.88 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.89 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 18.68 tokens</li><li>max: 118 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.26 tokens</li><li>max: 117 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 18.07 tokens</li><li>max: 108 tokens</li></ul> | -->
• —Samples: | anchor | positive | negative1 | negative2 | negative_3 | |:---------------------------------------------------------------------------------------------|:--------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------| | <code>Is life really what I make of it?</code> | <code>Life is what you make it?</code> | <code>Is life hardly what I take of it?</code> | <code>Life is not entirely what I make of it.</code> | <code>Is life not what I make of it?</code> | | <code>When you visit a website, can a person running the website see your IP address?</code> | <code>Does every website I visit knows my public ip address?</code> | <code>When you avoid a website, can a person hiding the website see your MAC address?</code> | <code>When you send an email, can the recipient see your physical location?</code> | <code>When you visit a website, a person running the website cannot see your IP address.</code> | | <code>What are some cool features about iOS 10?</code> | <code>What are the best new features of iOS 10?</code> | <code>iOS 10 received criticism for its initial bugs and performance issues, and some users found the redesigned apps less intuitive compared to previous versions.</code> | <code>What are the drawbacks of using Android 14?</code> | <code>iOS 10 was widely criticized for its bugs, removal of beloved features, and generally being a downgrade from previous versions.</code> |
• —Loss: <code>MatryoshkaLoss</code> with these parameters:

  {
      "loss": "CachedMultipleNegativesRankingLoss",
      "matryoshka_dims": [768,512,256,128,64],
      "matryoshka_weights": [1,1,1,1,1],
      "n_dims_per_step": -1
  }

Evaluation

[image] [image] [image] [image]

<!-- ### Training Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: steps
• —per_device_train_batch_size: 2048
• —per_device_eval_batch_size: 1024
• —learning_rate: 1e-05
• —num_train_epochs: 1
• —lr_scheduler_type: constant
• —warmup_steps: 10
• —gradient_checkpointing: True
• —torch_compile: True
• —torch_compile_backend: inductor
• —batch_sampler: no_duplicates -->

<!-- #### All Hyperparameters <details><summary>Click to expand</summary>

• —overwrite_output_dir: False
• —do_predict: False
• —eval_strategy: steps
• —prediction_loss_only: True
• —per_device_train_batch_size: 2048
• —per_device_eval_batch_size: 1024
• —per_gpu_train_batch_size: None
• —per_gpu_eval_batch_size: None
• —gradient_accumulation_steps: 1
• —eval_accumulation_steps: None
• —torch_empty_cache_steps: None
• —learning_rate: 1e-05
• —weight_decay: 0.0
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —max_grad_norm: 1
• —num_train_epochs: 1
• —max_steps: -1
• —lr_scheduler_type: constant
• —lr_scheduler_kwargs: {}
• —warmup_ratio: 0.0
• —warmup_steps: 10
• —log_level: passive
• —log_level_replica: warning
• —log_on_each_node: True
• —logging_nan_inf_filter: True
• —save_safetensors: True
• —save_on_each_node: False
• —save_only_model: False
• —restore_callback_states_from_checkpoint: False
• —no_cuda: False
• —use_cpu: False
• —use_mps_device: False
• —seed: 42
• —data_seed: None
• —jit_mode_eval: False
• —use_ipex: False
• —bf16: False
• —fp16: False
• —fp16_opt_level: O1
• —half_precision_backend: auto
• —bf16_full_eval: False
• —fp16_full_eval: False
• —tf32: None
• —local_rank: 0
• —ddp_backend: None
• —tpu_num_cores: None
• —tpu_metrics_debug: False
• —debug: []
• —dataloader_drop_last: False
• —dataloader_num_workers: 0
• —dataloader_prefetch_factor: None
• —past_index: -1
• —disable_tqdm: False
• —remove_unused_columns: True
• —label_names: None
• —load_best_model_at_end: False
• —ignore_data_skip: False
• —fsdp: []
• —fsdp_min_num_params: 0
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —tp_size: 0
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —deepspeed: None
• —label_smoothing_factor: 0.0
• —optim: adamw_torch
• —optim_args: None
• —adafactor: False
• —group_by_length: False
• —length_column_name: length
• —ddp_find_unused_parameters: None
• —ddp_bucket_cap_mb: None
• —ddp_broadcast_buffers: False
• —dataloader_pin_memory: True
• —dataloader_persistent_workers: False
• —skip_memory_metrics: True
• —use_legacy_prediction_loop: False
• —push_to_hub: False
• —resume_from_checkpoint: None
• —hub_model_id: None
• —hub_strategy: every_save
• —hub_private_repo: None
• —hub_always_push: False
• —gradient_checkpointing: True
• —gradient_checkpointing_kwargs: None
• —include_inputs_for_metrics: False
• —include_for_metrics: []
• —eval_do_concat_batches: True
• —fp16_backend: auto
• —push_to_hub_model_id: None
• —push_to_hub_organization: None
• —mp_parameters:
• —auto_find_batch_size: False
• —full_determinism: False
• —torchdynamo: None
• —ray_scope: last
• —ddp_timeout: 1800
• —torch_compile: True
• —torch_compile_backend: inductor
• —torch_compile_mode: None
• —include_tokens_per_second: False
• —include_num_input_tokens_seen: False
• —neftune_noise_alpha: None
• —optim_target_modules: None
• —batch_eval_metrics: False
• —eval_on_start: False
• —use_liger_kernel: False
• —eval_use_gather_object: False
• —average_tokens_across_devices: False
• —prompts: None
• —batch_sampler: no_duplicates
• —multi_dataset_batch_sampler: proportional

</details>

Training Logs

Framework Versions

• —Python: 3.11.11
• —Sentence Transformers: 4.1.0
• —Transformers: 4.51.3
• —PyTorch: 2.6.0+cu124
• —Accelerate: 1.6.0
• —Datasets: 3.5.1
• —Tokenizers: 0.21.1 -->

Citation

Redis Langcache-embed Models

We encourage you to cite our work if you use our models or build upon our findings.

@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

@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",
}

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

<!--

Glossary

Clearly define terms in order to be accessible across audiences. -->

<!--

Model Card Authors

Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. -->

<!--

Model Card Contact

Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->