Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "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_SparseLayer/config.json

@@ -0,0 +1 @@
+{"dim": 768, "vocab_size": 262144, "k": 64}

2_SparseLayer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1c2461440ae590d870e31d3cad68b22661d441f692cc456960cd2200d5d949
+size 806356949

README.md

@@ -0,0 +1,519 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:102127
+- loss:SpladeLoss
+- loss:SparseMultipleNegativesRankingLoss
+- loss:FlopsLoss
+base_model: seregadgl/splade_gemma_google_base_checkpoint_100_clear
+widget:
+- source_sentence: 'query: 6460338 acdelco'
+  sentences:
+  - 'document: очиститель тормозов rsqprofessional арт  072589767pl volkswagen id  buzz
+    янтарный'
+  - 'document: гтц 6460338 для chevrolet traverse'
+  - 'document: гтц 6960358 для chevrolet traverse'
+- source_sentence: 'query: audioquest cinnamon usb 0 7500 см '
+  sentences:
+  - 'document: кабель usb аудиоквест cinnamon 0 7500 см 8712516'
+  - 'document: задняя камера рамке номерного знака интерпауэр ip616 54785862'
+  - 'document: аудиокабель soundwave 200 см'
+- source_sentence: 'query: акустическое пианино weber w 121 pw '
+  sentences:
+  - 'document: акустическое пианино steinway model s'
+  - 'document: инструмент для игры на пианино вебер w 121 pw'
+  - 'document: велосипед сильвербек strela sport 700c 54 см blue 60097000435025'
+- source_sentence: 'query: шкаф шрм24'
+  sentences:
+  - 'document: wardrobe shrm 24 4348563'
+  - 'document: духовой шкаф бертаццони f6011provtn'
+  - 'document: шкаф мдф30'
+- source_sentence: 'query: 1452634 santool jawa 300 cl'
+  sentences:
+  - 'document: смартфон эппл iphone xs max 512gb'
+  - 'document: 1453934 santool съемник для сальников jawa 300 cl'
+  - 'document: 1452634 santool съемник для сальников jawa 300 cl'
+datasets:
+- seregadgl/car_and_product_triplet_103k
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on seregadgl/splade_gemma_google_base_checkpoint_100_clear
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: val set fine
+      type: val_set_fine
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.749
+      name: Cosine Accuracy@1
+    - type: cosine_precision@1
+      value: 0.749
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27433333333333326
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17060000000000003
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0886
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.749
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.823
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.853
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.886
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.816961550160875
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7949674603174605
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7988750755190056
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on seregadgl/splade_gemma_google_base_checkpoint_100_clear
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [seregadgl/splade_gemma_google_base_checkpoint_100_clear](https://huggingface.co/seregadgl/splade_gemma_google_base_checkpoint_100_clear) on the [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) 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:** [seregadgl/splade_gemma_google_base_checkpoint_100_clear](https://huggingface.co/seregadgl/splade_gemma_google_base_checkpoint_100_clear) <!-- at revision 20c38a098901bc44c1031a7537d0e3bf0aa93063 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k)
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/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': 512, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
+  (1): Pooling({'word_embedding_dimension': 768, '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): SparseLayer(
+    (linear): Linear(in_features=768, out_features=262144, bias=True)
+  )
+)
+```
+
+## 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("seregadgl/splade_gemma_google_base_checkpoint_100_ver2_checkpoint100")
+# Run inference
+sentences = [
+    'query: 1452634 santool jawa 300 cl',
+    'document: 1452634 santool съемник для сальников jawa 300 cl',
+    'document: 1453934 santool съемник для сальников jawa 300 cl',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.1749, 0.1724],
+#         [0.1749, 1.0000, 0.7309],
+#         [0.1724, 0.7309, 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
+
+#### Information Retrieval
+
+* Dataset: `val_set_fine`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.749     |
+| cosine_precision@1  | 0.749     |
+| cosine_precision@3  | 0.2743    |
+| cosine_precision@5  | 0.1706    |
+| cosine_precision@10 | 0.0886    |
+| cosine_recall@1     | 0.749     |
+| cosine_recall@3     | 0.823     |
+| cosine_recall@5     | 0.853     |
+| cosine_recall@10    | 0.886     |
+| **cosine_ndcg@10**  | **0.817** |
+| cosine_mrr@10       | 0.795     |
+| cosine_map@100      | 0.7989    |
+
+<!--
+## 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
+
+#### car_and_product_triplet_103k
+
+* Dataset: [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) at [3519181](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k/tree/35191818e272dc373544bd86903a5146c6f993e2)
+* Size: 102,127 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: 5 tokens</li><li>mean: 16.27 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 23.62 tokens</li><li>max: 77 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 23.2 tokens</li><li>max: 47 tokens</li></ul> |
+* Samples:
+  | anchor                                                        | positive                                                                              | negative                                                                        |
+  |:--------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
+  | <code>query: погружной блендер tefal optichef hb64f810</code> | <code>document: погружной блендер тефаль optichef hb64f810</code>                     | <code>document: погружной миксер tefal mixchef hb64f850</code>                  |
+  | <code>query: 375675836 niteo</code>                           | <code>document: тосол 375675836 для ford f350 полуночный синий</code>                 | <code>document: тосол 375625836 для ford f350 полуночный синий фиалковый</code> |
+  | <code>query: накидка с подогревом dodge viper pink</code>     | <code>document: накидка с подогревом acdelco арт  787327sx dodge viper розовый</code> | <code>document: 787327sx накидка с подогревом indian challenger лаймовый</code> |
+* Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#spladeloss) with these parameters:
+  ```json
+  {
+      "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score', gather_across_devices=False)",
+      "document_regularizer_weight": 1e-05,
+      "query_regularizer_weight": 1e-05
+  }
+  ```
+
+### Evaluation Dataset
+
+#### car_and_product_triplet_103k
+
+* Dataset: [car_and_product_triplet_103k](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k) at [3519181](https://huggingface.co/datasets/seregadgl/car_and_product_triplet_103k/tree/35191818e272dc373544bd86903a5146c6f993e2)
+* Size: 1,000 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: 5 tokens</li><li>mean: 16.73 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 23.54 tokens</li><li>max: 80 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 22.66 tokens</li><li>max: 65 tokens</li></ul> |
+* Samples:
+  | anchor                                                            | positive                                                                                                     | negative                                                                          |
+  |:------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | <code>query: зеркала для 'слепых' зон volkswagen arteon</code>    | <code>document: зеркала для 'слепых' зон 86635985zz для volkswagen arteon перламутровочёрный</code>          | <code>document: 86635985zz зеркала для 'слепых' зон иж юпитер2 голубой</code>     |
+  | <code>query: elf bar lux 1500 лимонад голубой малины 1500 </code> | <code>document: одноразовая электронная сигарета эльф бар 1 5000 мл lemonade blue raspberry 340440526</code> | <code>document: elf bar vibe 1000 мохито зелёного яблока 1000</code>              |
+  | <code>query: удалитель наклеек chevrolet corvette onyx</code>     | <code>document: удалитель наклеек 20810588pl для chevrolet corvette оникс</code>                             | <code>document: удалитель наклеек 20810588pl для maserati levante янтарный</code> |
+* Loss: [<code>SpladeLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#spladeloss) with these parameters:
+  ```json
+  {
+      "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score', gather_across_devices=False)",
+      "document_regularizer_weight": 1e-05,
+      "query_regularizer_weight": 1e-05
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 0.0001
+- `num_train_epochs`: 1
+- `warmup_steps`: 10
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `router_mapping`: {'query': 'anchor', 'document': 'positive'}
+
+#### 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`: 8
+- `per_device_eval_batch_size`: 8
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 0.0001
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `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
+- `bf16`: False
+- `fp16`: True
+- `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`: 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
+- `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`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: True
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {'query': 'anchor', 'document': 'positive'}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Validation Loss | val_set_fine_cosine_ndcg@10 |
+|:------:|:----:|:---------------:|:---------------------------:|
+| 0.0125 | 10   | 0.8461          | 0.7841                      |
+| 0.0251 | 20   | 0.8195          | 0.8009                      |
+| 0.0376 | 30   | 0.7884          | 0.7967                      |
+| 0.0501 | 40   | 0.7641          | 0.8097                      |
+| 0.0627 | 50   | 0.7503          | 0.8146                      |
+| 0.0752 | 60   | 0.7140          | 0.8151                      |
+| 0.0877 | 70   | 0.7165          | 0.8180                      |
+| 0.1003 | 80   | 0.6955          | 0.8131                      |
+| 0.1128 | 90   | 0.6866          | 0.8157                      |
+| 0.1253 | 100  | 0.6735          | 0.8170                      |
+
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.2.2
+- Transformers: 4.57.1
+- PyTorch: 2.8.0+cu126
+- Accelerate: 1.11.0
+- Datasets: 4.4.2
+- 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",
+}
+```
+
+#### SpladeLoss
+```bibtex
+@misc{formal2022distillationhardnegativesampling,
+      title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
+      author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
+      year={2022},
+      eprint={2205.04733},
+      archivePrefix={arXiv},
+      primaryClass={cs.IR},
+      url={https://arxiv.org/abs/2205.04733},
+}
+```
+
+#### SparseMultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+#### FlopsLoss
+```bibtex
+@article{paria2020minimizing,
+    title={Minimizing flops to learn efficient sparse representations},
+    author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
+    journal={arXiv preprint arXiv:2004.05665},
+    year={2020}
+}
+```
+
+<!--
+## 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

@@ -0,0 +1,70 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3TextModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 3,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 65,
+  "transformers_version": "4.57.1",
+  "use_bidirectional_attention": true,
+  "use_cache": true,
+  "vocab_size": 262144
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.2",
+    "transformers": "4.57.1",
+    "pytorch": "2.8.0+cu126"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbf5a78393b6a033e0b8a63a57549964f7ed5c6fbeb4ba0694214f36123f2fd2
+size 1211486072

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_SparseLayer",
+    "type": "__main__.SparseLayer"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc07dcf4350cd709c4e37bdb92d6f7b723f1396d28fb4307ec6a6d2c867f5861
+size 33384696