---
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: 0.742
name: Cosine Accuracy@1
- type: cosine_precision@1
value: 0.742
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.27633333333333326
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1728
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.08910000000000001
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.742
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.829
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.864
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.891
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.8160719769563038
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.7919432539682544
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.7955622385483846
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)
- **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)
### 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")
# 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, 0.1443, 0.1452],
# [0.1443, 1.0000, 0.7490],
# [0.1452, 0.7490, 1.0000]])
```
## Evaluation
### Metrics
#### Information Retrieval
* Dataset: `val_set_fine`
* Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.742 |
| cosine_precision@1 | 0.742 |
| cosine_precision@3 | 0.2763 |
| cosine_precision@5 | 0.1728 |
| cosine_precision@10 | 0.0891 |
| cosine_recall@1 | 0.742 |
| cosine_recall@3 | 0.829 |
| cosine_recall@5 | 0.864 |
| cosine_recall@10 | 0.891 |
| **cosine_ndcg@10** | **0.8161** |
| cosine_mrr@10 | 0.7919 |
| cosine_map@100 | 0.7956 |
## 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: anchor, positive, and negative
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
| type | string | string | string |
| details |
query: погружной блендер tefal optichef hb64f810 | document: погружной блендер тефаль optichef hb64f810 | document: погружной миксер tefal mixchef hb64f850 |
| query: 375675836 niteo | document: тосол 375675836 для ford f350 полуночный синий | document: тосол 375625836 для ford f350 полуночный синий фиалковый |
| query: накидка с подогревом dodge viper pink | document: накидка с подогревом acdelco арт 787327sx dodge viper розовый | document: 787327sx накидка с подогревом indian challenger лаймовый |
* Loss: [SpladeLoss](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: anchor, positive, and negative
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details | query: зеркала для 'слепых' зон volkswagen arteon | document: зеркала для 'слепых' зон 86635985zz для volkswagen arteon перламутровочёрный | document: 86635985zz зеркала для 'слепых' зон иж юпитер2 голубой |
| query: elf bar lux 1500 лимонад голубой малины 1500 | document: одноразовая электронная сигарета эльф бар 1 5000 мл lemonade blue raspberry 340440526 | document: elf bar vibe 1000 мохито зелёного яблока 1000 |
| query: удалитель наклеек chevrolet corvette onyx | document: удалитель наклеек 20810588pl для chevrolet corvette оникс | document: удалитель наклеек 20810588pl для maserati levante янтарный |
* Loss: [SpladeLoss](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