---
base_model: FacebookAI/roberta-base
datasets:
- SynthSTEL/styledistance_training_triplets_v2
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- datadreamer
- datadreamer-0.35.0
- synthetic
- sentence-transformers
- feature-extraction
- sentence-similarity
widget:
- example_title: Example 1
  source_sentence: "The Harley School will thrive\uD83D\uDE00; so many future leaders\uD83C\
    \uDF93 will emerge from its doors\uD83D\uDEAA."
  sentences:
  - "To avoid extra attorney fees\uD83D\uDCB0, they kept the entity's minutes updated⏱️;\
    \ it proved a wise decision\uD83D\uDC4D."
  - To avoid extra attorney fees, they kept the entity's minutes updated; it proved
    a wise decision.
- example_title: Example 2
  source_sentence: In Segovia, I will shoulder the duty of raising suckling pigs;
    their care will be my responsibility too.
  sentences:
  - Despite facing routine criticism, I continue to support the display of religious
    texts in public buildings.
  - I'll raise suckling pigs in Segovia; I'll care for them as well.
- example_title: Example 3
  source_sentence: You'll play Far Cry 2 on Xbox; I prefer Far Cry 3 on PlayStation.
  sentences:
  - I endured significant challenges when my partner was in prison.
  - They'll play Far Cry 2 on Xbox; they prefer Far Cry 3 on PlayStation.
---
# Model Card

[Add more information here](https://huggingface.co/templates/model-card-example)

## Example Usage

```python3
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim

model = SentenceTransformer('SynthSTEL/styledistance_synthetic_only_full_v2') # Load model

input = model.encode('The Harley School will thrive😀; so many future leaders🎓 will emerge from its doors🚪.')
others = model.encode(["To avoid extra attorney fees💰, they kept the entity's minutes updated⏱️; it proved a wise decision👍.", "To avoid extra attorney fees, they kept the entity's minutes updated; it proved a wise decision."])
print(cos_sim(input, others))
```

---
This model was trained with a synthetic dataset with [DataDreamer 🤖💤](https://datadreamer.dev). The synthetic dataset card and model card can be found [here](datadreamer.json). The training arguments can be found [here](training_args.json).