---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:12800
- loss:MultipleNegativesRankingLoss
base_model: microsoft/MiniLM-L12-H384-uncased
widget:
- source_sentence: A man in an orange shirt and a man in a white shirt are at a vegetable
stand, and the man in the orange shirt gives a woman wearing red some vegetables.
sentences:
- Two men at a food stand.
- Two teams play each other in a soccer game.
- Two men are outside working on a building.
- source_sentence: A young girl wearing jeans and a white shirt is standing on grass
holding dandelions in her hands.
sentences:
- A lady retrieving clothes from the dryer.
- The girl is wearing jeans.
- The boy is using a computer
- source_sentence: Young individuals in uniforms are gathering under the flags of
several different countries.
sentences:
- A toddler is wearing maroon.
- A man fishes.
- A youth group is gathering near multi-national banners.
- source_sentence: A young person wearing a pink one-piece swimsuit and goggles about
to complete a leap into a swimming pool.
sentences:
- People walk by artwork.
- A crowd in Japan gathers in grassy area.
- A young person has on clothes.
- source_sentence: A man wearing a Gas mask attempts a flying kick toward another
man wearing a mask and red shirt in a martial arts stance.
sentences:
- A man carries a basket on his head.
- Two men fighting in the martial arts.
- The men are working together on the same window
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on microsoft/MiniLM-L12-H384-uncased
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased). 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:** [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 384 dimensions
- **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': 512, '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})
)
```
## 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("Borsa356/bert_mnr_5")
# Run inference
sentences = [
'A man wearing a Gas mask attempts a flying kick toward another man wearing a mask and red shirt in a martial arts stance.',
'Two men fighting in the martial arts.',
'The men are working together on the same window',
]
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, 0.6838, 0.1621],
# [0.6838, 1.0000, 0.2773],
# [0.1621, 0.2773, 1.0000]])
```
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 12,800 training samples
* Columns: sentence_0 and sentence_1
* Approximate statistics based on the first 1000 samples:
| | sentence_0 | sentence_1 |
|:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
| type | string | string |
| details |
A man is working a hotdog stand. | A person is running a small location that sells food. |
| The man, only visible as a black silhouette, took a picture along a brightly colored wall full of graffiti. | The wall is decorated with bright colors. |
| A woman wearing a sweater and jeans is playing on a tire swing with two little children in an outdoor park. | A woman and two children are in the park. |
* Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim"
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 32
- `per_device_eval_batch_size`: 32
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: round_robin
#### All Hyperparameters