# ✦ Veytra ✦ **From words to vectors, from vectors to meaning.** A lightweight, elegant **sentence embedding model**, built from scratch. [![Params](https://img.shields.io/badge/params-3.3M-blue)](https://github.com/coderianx/veytra) [![Embedding](https://img.shields.io/badge/embedding-64d-green)](https://github.com/coderianx/veytra) [![Dataset](https://img.shields.io/badge/dataset-STS--B-orange)](https://huggingface.co/datasets/sentence-transformers/stsb) [![GitHub](https://img.shields.io/badge/GitHub-coderian%2Fveytra-black?logo=github)](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.*