Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "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
+}

README.md

@@ -0,0 +1,479 @@
+---
+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:49642
+- loss:ArcFaceInBatchLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: '"How much would I need to narrate a ""Let''s Play"" video in order
+    to make money from it on YouTube?"'
+  sentences:
+  - How much money do people make from YouTube videos with 1 million views?
+  - '"How much would I need to narrate a ""Let''s Play"" video in order to make money
+    from it on YouTube?"'
+  - '"Does the sentence, ""I expect to be disappointed,"" make sense?"'
+- source_sentence: '"I appreciate that.'
+  sentences:
+  - '"How is the Mariner rewarded in ""The Rime of the Ancient Mariner"" by Samuel
+    Taylor Coleridge?"'
+  - '"I appreciate that.'
+  - I can appreciate that.
+- source_sentence: '"""It is very easy to defeat someone, but too hard to win some
+    one"". What does the previous sentence mean?"'
+  sentences:
+  - '"How can you use the word ""visceral"" in a sentence?"'
+  - '"""It is very easy to defeat someone, but too hard to win some one"". What does
+    the previous sentence mean?"'
+  - '"What does ""The loudest one in the room is the weakest one in the room."" Mean?"'
+- source_sentence: '" We condemn this raid which is in our view illegal and morally
+    and politically unjustifiable , " London-based NCRI official Ali Safavi told Reuters
+    by telephone .'
+  sentences:
+  - 'London-based NCRI official Ali Safavi told Reuters : " We condemn this raid ,
+    which is in our view illegal and morally and politically unjustifiable . "'
+  - The social awkwardness is complicated by the fact that Marianne is a white girl
+    living with a black family .
+  - art's cause, this in my opinion
+- source_sentence: '"If you click ""like"" on an old post that someone made on your
+    wall yet you''re no longer Facebook friends, will they still receive a notification?"'
+  sentences:
+  - '"Is there is any two wheeler having a gear box which has the feature ""automatic
+    neutral"" when the engine is off while it is in gear?"'
+  - '"If you click ""like"" on an old post that someone made on your wall yet you''re
+    no longer Facebook friends, will they still receive a notification?"'
+  - '"If your teenage son posted ""La commedia e finita"" on his Facebook wall, would
+    you be concerned?"'
+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
+- 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: 0.5761591648590022
+      name: Cosine Accuracy@1
+    - type: cosine_precision@1
+      value: 0.5761591648590022
+      name: Cosine Precision@1
+    - type: cosine_recall@1
+      value: 0.5588122182164516
+      name: Cosine Recall@1
+    - type: cosine_ndcg@10
+      value: 0.7618942742503089
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@1
+      value: 0.5761591648590022
+      name: Cosine Mrr@1
+    - type: cosine_map@100
+      value: 0.7107009769861719
+      name: Cosine Map@100
+    - type: cosine_auc_precision_cache_hit_ratio
+      value: 0.3491200519822629
+      name: Cosine Auc Precision Cache Hit Ratio
+    - type: cosine_auc_similarity_distribution
+      value: 0.1635457705044361
+      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) on the [LangCache Sentence Pairs (all)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v2) dataset. 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:** 100 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [LangCache Sentence Pairs (all)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v2)
+- **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': 100, '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 = [
+    '"If you click ""like"" on an old post that someone made on your wall yet you\'re no longer Facebook friends, will they still receive a notification?"',
+    '"If you click ""like"" on an old post that someone made on your wall yet you\'re no longer Facebook friends, will they still receive a notification?"',
+    '"If your teenage son posted ""La commedia e finita"" on his Facebook wall, would you be concerned?"',
+]
+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, 1.0000, 0.3764],
+#         [1.0000, 1.0000, 0.3764],
+#         [0.3764, 0.3764, 1.0000]])
+```
+
+<!--
+### 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>
+
+| Metric                               | Value      |
+|:-------------------------------------|:-----------|
+| cosine_accuracy@1                    | 0.5762     |
+| cosine_precision@1                   | 0.5762     |
+| cosine_recall@1                      | 0.5588     |
+| **cosine_ndcg@10**                   | **0.7619** |
+| cosine_mrr@1                         | 0.5762     |
+| cosine_map@100                       | 0.7107     |
+| cosine_auc_precision_cache_hit_ratio | 0.3491     |
+| cosine_auc_similarity_distribution   | 0.1635     |
+
+<!--
+## 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 Dataset
+
+#### LangCache Sentence Pairs (all)
+
+* Dataset: [LangCache Sentence Pairs (all)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v2)
+* Size: 132,354 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                           | negative                                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 27.15 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.59 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.39 tokens</li><li>max: 64 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                        | positive                                                                                      | negative                                                                                       |
+  |:----------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|
+  | <code> What high potential jobs are there other than computer science?</code>                 | <code> What high potential jobs are there other than computer science?</code>                 | <code>Why IT or Computer Science jobs are being over rated than other Engineering jobs?</code> |
+  | <code> Would India ever be able to develop a missile system like S300 or S400 missile?</code> | <code> Would India ever be able to develop a missile system like S300 or S400 missile?</code> | <code>Should India buy the Russian S400 air defence missile system?</code>                     |
+  | <code> water from the faucet is being drunk by a yellow dog</code>                            | <code>A yellow dog is drinking water from the faucet</code>                                   | <code>Childlessness is low in Eastern European countries.</code>                               |
+* Loss: <code>losses.ArcFaceInBatchLoss</code> with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Evaluation Dataset
+
+#### LangCache Sentence Pairs (all)
+
+* Dataset: [LangCache Sentence Pairs (all)](https://huggingface.co/datasets/redis/langcache-sentencepairs-v2)
+* Size: 132,354 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                           | negative                                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 27.15 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.59 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.39 tokens</li><li>max: 64 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                        | positive                                                                                      | negative                                                                                       |
+  |:----------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|
+  | <code> What high potential jobs are there other than computer science?</code>                 | <code> What high potential jobs are there other than computer science?</code>                 | <code>Why IT or Computer Science jobs are being over rated than other Engineering jobs?</code> |
+  | <code> Would India ever be able to develop a missile system like S300 or S400 missile?</code> | <code> Would India ever be able to develop a missile system like S300 or S400 missile?</code> | <code>Should India buy the Russian S400 air defence missile system?</code>                     |
+  | <code> water from the faucet is being drunk by a yellow dog</code>                            | <code>A yellow dog is drinking water from the faucet</code>                                   | <code>Childlessness is low in Eastern European countries.</code>                               |
+* Loss: <code>losses.ArcFaceInBatchLoss</code> with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 512
+- `per_device_eval_batch_size`: 512
+- `gradient_accumulation_steps`: 2
+- `weight_decay`: 0.001
+- `adam_beta2`: 0.98
+- `adam_epsilon`: 1e-06
+- `num_train_epochs`: 2
+- `warmup_ratio`: 0.05
+- `bf16`: True
+- `load_best_model_at_end`: True
+- `optim`: stable_adamw
+- `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`: 512
+- `per_device_eval_batch_size`: 512
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `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`: 2
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.05
+- `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`: stable_adamw
+- `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 | Validation Loss | test_cosine_ndcg@10 |
+|:-----:|:----:|:---------------:|:-------------------:|
+| 0     | 0    | 0.5769          | 0.7619              |
+
+
+### 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.*
+-->

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "dtype": "bfloat16",
+  "dtype": "float32",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.1",
+    "transformers": "4.57.0",
+    "pytorch": "2.8.0+cu128"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:544b605fdcc7a5c57b7c4b3af9900b0d2e90a6a1ee38679483821ffdd73eb645
-size 45437864
+oid sha256:22301df8a57c3981b4c040d6fc519aaf20e7b7936910eaf29636e26c701d6b92
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 100,
+    "do_lower_case": false
+}