README / README.md
GautamKishore's picture
Upload README.md with huggingface_hub
9edf143 verified
|
Raw
History Blame Contribute Delete
3.29 kB
---
title: README
emoji: ๐Ÿง 
colorFrom: blue
colorTo: indigo
sdk: static
pinned: false
---
<div align="center">
# Eulogik ๐Ÿง 
### Edge AI Infrastructure & Quantitative Systems Engineering
[![Website](https://img.shields.io/badge/Website-eulogik.com-00F0FF?style=for-the-badge&logo=google-chrome&logoColor=white)](https://eulogik.com)
[![GitHub](https://img.shields.io/badge/GitHub-eulogik-181717?style=for-the-badge&logo=github)](https://github.com/eulogik)
---
**We engineer hyper-efficient, domain-specialized, and edge-deployable AI models.**
No bloated parameter sizes. No massive cloud dependencies. Just high-performance models designed to run locally, securely, and cost-effectively.
</div>
---
## ๐Ÿ”ฌ Active Research & Model Portfolios
We focus on three primary domains of edge-optimized machine intelligence:
### 1. ๐Ÿ“„ Visual Document Understanding (VDU)
* **[TinyDoc-VLM-256M](https://huggingface.co/eulogik/TinyDoc-VLM-256M)**: A compact 290M-parameter vision-language model trained on SigLIP and SmolLM2. Optimized for document OCR, layout parsing, and information extraction.
* **[TinyDoc-VLM-LoRA](https://huggingface.co/eulogik/TinyDoc-VLM-LoRA)**: Parameter-efficient adapters for custom corporate legal and administrative document compliance.
### 2. ๐Ÿ“ˆ Time Series & Quantitative Forecasting
* **[NanoForecast](https://huggingface.co/eulogik/nanoforecast-v03)**: A lightweight time-series foundation model family ranging from 200K to 6.5M parameters. Supports streaming RNN inference and zero-shot forecasting, optimized for running directly on edge hardware like Raspberry Pi.
### 3. ๐Ÿก Intelligent LLM Routing
* **[fugusashi](https://huggingface.co/spaces/eulogik/fugusashi)**: An open-source, federated, human-interpretable model router. Learns user preferences and routes requests to the most optimal model, slashing inference costs by up to 70%.
### 4. ๐Ÿ‡ฎ๐Ÿ‡ณ Localized & Multilingual LLMs
* **[Bharat-Tiny-LLM](https://huggingface.co/eulogik/Bharat-Tiny-LLM)**: An ultra-compact 240M-parameter language model specialized for Hinglish and Indian cultural context.
---
## โšก Developer Demos (Spaces)
Test our models directly in your browser:
* [๐Ÿš€ Bharat-Tiny-LLM Chatbot](https://huggingface.co/spaces/eulogik/Bharat-Tiny-LLM) โ€” Hinglish AI companion.
* [๐Ÿก Fugusashi Router](https://huggingface.co/spaces/eulogik/fugusashi) โ€” Intelligent prompt router.
* [๐Ÿ“„ TinyDoc-VLM Demo](https://huggingface.co/spaces/eulogik/TinyDoc-VLM) โ€” Local document analysis.
* [๐Ÿ“Š NanoForecast CSV Tool](https://huggingface.co/spaces/eulogik/nanoforecast) โ€” Zero-shot time series analysis.
---
## ๐Ÿข Licensing & Enterprise Collaboration
All our core public models are open-sourced under **Apache 2.0** or **MIT** licenses.
For enterprise-grade integration, private custom model training, or commercial licensing of specialized components (such as our high-frequency quant trading predictors and legal document ingestion pipelines), get in touch:
* **Website:** [eulogik.com/contact](https://eulogik.com/contact)
* **Email:** [info@eulogik.com](mailto:info@eulogik.com)
* **HQ:** Bhopal, India | **Global:** Dubai, UAE
<div align="center">
<sub>ยฉ 2026 Eulogik. Engineered for efficiency.</sub>
</div>