# ✦ Veytra ✦
**From words to vectors, from vectors to meaning.**
A lightweight, elegant **sentence embedding model**, built from scratch.
[](https://github.com/coderianx/veytra)
[](https://github.com/coderianx/veytra)
[](https://huggingface.co/datasets/sentence-transformers/stsb)
[](https://github.com/coderianx/veytra)
---
Trained with a Transformer architecture, Veytra maps sentences into **64-dimensional vectors** and measures the **semantic closeness** between two sentences via cosine similarity. Small yet ambitious — designed for those who believe in the power of simplicity.
| ⚙️ Architecture | |
|---|---|
| **Total Parameters** | ~3.3M (3,316,544) |
| **Tokenizer** | GPT-2 (50,257 vocab) |
| **Model** | Transformer Encoder (2 layers, 4 heads) |
| **Embedding Dimension** | 64 |
| **Max Length** | 64 tokens |
| **Pooling** | Mean Pooling + L2 Normalization |
---
## ⚡ Usage
```bash
python3 train.py
```
*Veytra — encoding meaning.*