---
language: []
library_name: sentence-transformers
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:75
- loss:CosineSimilarityLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
datasets: []
widget:
- source_sentence: This store featured in the SavaCentre TV adverts in 1983.
sentences:
- I love the Scream movies and all horror movies and this one ranks way up there.
- Development of synchronous toothed-belts was halted by the Gilmer company prior
to 1940.
- This store was not featured in the SavaCentre TV promotions in 1983.
- source_sentence: In 2014, Nextgen earns KLAS Top Performance Honors for Ambulatory
RCM Services.
sentences:
- These strategies employ reporter transposon s and in vitro expression technology
(IVET).
- In 2014, Nextgen fails to achieve KLAS Top Performance Honors for Ambulatory RCM
Services.
- The film's sole bright spot was Jonah Hill (who will look almost unrecognizable
to fans of the recent Superbad due to the amount of weight he lost in the interim).
- source_sentence: E105 has never been implicated in atopic asthma.
sentences:
- E105 has been implicated in non-atopic asthma.
- The species is named in honor of the divorce of Sara Anderson and Malcolm Slaney.
- Each annex to a filed document is not required to have page numbering.
- source_sentence: Additionally, a church at San Lazaro in Orange Walk District escaped
all damage.
sentences:
- Kuwait has a reputation for being the central music influence of the GCC countries.
- Early settlers may have introduced it 4,000 years ago.
- Additionally, a church at San Lazaro in Orange Walk District suffered severe damage.
- source_sentence: The content in Australia is lower than in other reports.
sentences:
- Other reports also show a content lower than 0.1% in Australia.
- Commercial DNP is unable to be utilized as an antiseptic or as a non-selective
bioaccumulating pesticide.
- Installation of Halon systems is mandated by the European Union.
pipeline_tag: sentence-similarity
---
# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
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 semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## 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)
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 384 tokens
- **Similarity Function:** Cosine Similarity
### 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': 256, 'do_lower_case': False}) with Transformer model: 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("LeoChiuu/all-MiniLM-L6-v2-negations")
# Run inference
sentences = [
'The content in Australia is lower than in other reports.',
'Other reports also show a content lower than 0.1% in Australia.',
'Installation of Halon systems is mandated by the European Union.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 75 training samples
* Columns: sentence_0
, sentence_1
, and label
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 | label |
|:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
| type | string | string | int |
| details |
It wasn't an inexpensive piece, but I would still have expected better quality.
| It was an inexpensive piece, but I would still have expected better quality.
| 0
|
| My name is noncrucial.
| My name is important.
| 0
|
| Hawthorne mostly wrote against his own religious belief.
| Hawthorne wrote against his beliefs.
| 1
|
* Loss: [CosineSimilarityLoss
](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
```json
{
"loss_fct": "torch.nn.modules.loss.MSELoss"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `num_train_epochs`: 10
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters