README.md

---
language:
- en
license: apache-2.0
tags:
- biencoder
- sentence-transformers
- text-classification
- sentence-pair-classification
- semantic-similarity
- semantic-search
- retrieval
- reranking
- generated_from_trainer
- loss:ArcFaceInBatchLoss
base_model: sentence-transformers/all-MiniLM-L6-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
- cosine_auc_precision_cache_hit_ratio
- cosine_auc_similarity_distribution
model-index:
- name: Redis fine-tuned BiEncoder model for semantic caching on LangCache
  results:
  - task:
      type: custom-information-retrieval
      name: Custom Information Retrieval
    dataset:
      name: test
      type: test
    metrics:
    - type: cosine_accuracy@1
      value: 0.5474394601032155
      name: Cosine Accuracy@1
    - type: cosine_precision@1
      value: 0.5474394601032155
      name: Cosine Precision@1
    - type: cosine_recall@1
      value: 0.5284894589479743
      name: Cosine Recall@1
    - type: cosine_ndcg@10
      value: 0.7464232866184599
      name: Cosine Ndcg@10
    - type: cosine_mrr@1
      value: 0.5474394601032155
      name: Cosine Mrr@1
    - type: cosine_map@100
      value: 0.6905199963377163
      name: Cosine Map@100
    - type: cosine_auc_precision_cache_hit_ratio
      value: 0.31524254043885996
      name: Cosine Auc Precision Cache Hit Ratio
    - type: cosine_auc_similarity_distribution
      value: 0.16089488030492544
      name: Cosine Auc Similarity Distribution
---

# Redis fine-tuned BiEncoder model for semantic caching on LangCache

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for sentence pair similarity.

## Model Details

### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
- **Maximum Sequence Length:** 128 tokens
- **Output Dimensionality:** 384 dimensions
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
- **Language:** en
- **License:** apache-2.0

### Model Sources

- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)

### Full Model Architecture

```
SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)
```

## Usage

### Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

```bash
pip install -U sentence-transformers
```

Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("redis/langcache-embed-v3-mini")
# Run inference
sentences = [
    'The weather is lovely today.',
    "It's so sunny outside!",
    'He drove to the stadium.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6650, 0.1040],
#         [0.6650, 1.0000, 0.1401],
#         [0.1040, 0.1401, 0.9999]])
```

<!--
### 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.*
-->

## Evaluation

### Metrics

#### Custom Information Retrieval

* Dataset: `test`
* Evaluated with <code>ir_evaluator.CustomInformationRetrievalEvaluator</code> with these parameters:
  ```json
  {
      "query_prompt": "query:",
      "corpus_prompt": "query:"
  }
  ```

| Metric                               | Value      |
|:-------------------------------------|:-----------|
| cosine_accuracy@1                    | 0.5474     |
| cosine_precision@1                   | 0.5474     |
| cosine_recall@1                      | 0.5285     |
| **cosine_ndcg@10**                   | **0.7464** |
| cosine_mrr@1                         | 0.5474     |
| cosine_map@100                       | 0.6905     |
| cosine_auc_precision_cache_hit_ratio | 0.3152     |
| cosine_auc_similarity_distribution   | 0.1609     |

<!--
## 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

### Training Hyperparameters
#### Non-Default Hyperparameters

- `eval_strategy`: steps
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `weight_decay`: 0.001
- `adam_beta2`: 0.98
- `adam_epsilon`: 1e-06
- `max_steps`: 100000
- `warmup_ratio`: 0.15
- `bf16`: True
- `load_best_model_at_end`: True
- `ddp_find_unused_parameters`: False
- `push_to_hub`: True
- `hub_model_id`: redis/langcache-embed-v3-mini
- `eval_on_start`: True
- `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`: 64
- `per_device_eval_batch_size`: 64
- `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`: 5e-05
- `weight_decay`: 0.001
- `adam_beta1`: 0.9
- `adam_beta2`: 0.98
- `adam_epsilon`: 1e-06
- `max_grad_norm`: 1.0
- `num_train_epochs`: 3.0
- `max_steps`: 100000
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.15
- `warmup_steps`: 0
- `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
- `bf16`: True
- `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`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `parallelism_config`: None
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch_fused
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `project`: huggingface
- `trackio_space_id`: trackio
- `ddp_find_unused_parameters`: False
- `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`: True
- `resume_from_checkpoint`: None
- `hub_model_id`: redis/langcache-embed-v3-mini
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `hub_revision`: None
- `gradient_checkpointing`: False
- `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`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: no
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: True
- `use_liger_kernel`: False
- `liger_kernel_config`: None
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: True
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}

</details>

### Training Logs
| Epoch | Step | test_cosine_ndcg@10 |
|:-----:|:----:|:-------------------:|
| 0     | 0    | 0.7464              |


### Framework Versions
- Python: 3.12.3
- Sentence Transformers: 5.1.1
- Transformers: 4.57.0
- PyTorch: 2.8.0+cu128
- Accelerate: 1.10.1
- Datasets: 4.1.1
- Tokenizers: 0.22.1

## Citation

### BibTeX

#### Sentence Transformers
```bibtex
@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",
}
```

<!--
## 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.*
-->