README / README.md
j0no12's picture
Update README.md
f977920 verified
---
title: README
emoji: 🏃
colorFrom: pink
colorTo: gray
sdk: static
pinned: true
---
# ⚡ Neuronic
**High-Performance Agents for the Edge.**
Neuronic is a specialized AI research and development lab focused on building hyper-optimized, low-parameter models for function calling, tool use, and agentic routing. We believe that intelligence doesn't always require massive compute—it requires precision.
---
## 🎯 Our Focus
* **Function-Calling Specialists:** We train models to act as deterministic routers, prioritizing strict syntax, reliable JSON output, and accurate tool utilization over general chat.
* **Edge Computing:** By optimizing models in the 0.5B to 7B parameter range, we make local, high-speed agentic workflows possible on edge devices, mobile hardware, and consumer GPUs.
* **Low Latency:** Designed for environments where every millisecond counts.
---
## 🚀 Featured Models
### **Nero1-0.5B**
Our flagship router. A 500-million parameter model fine-tuned specifically for agentic tool use and structural reliability.
* **Base Model:** `Qwen/Qwen2.5-Coder-0.5B-Instruct`
* **Dataset:** smirki/Agentic-Coding-Tessa
* **Use Case:** Local Python toolkits, fast API routing, and strictly typed outputs.
### **Nero-0.5B-GGUF**
The quantized versions of Nero for immediate deployment on CPU or low-VRAM environments.
* **Formats:** `Q8_0` (Maximum accuracy), `Q4_K_M` (Maximum speed)
* **Framework:** Ready for `llama.cpp` and LM Studio.
---
## 🛠️ Usage Guidelines
Neuronic models are heavily biased toward action over conversation. For optimal performance:
1. **Use ChatML formatting.**
2. **Define tools explicitly** in your system prompt.
3. **Keep temperatures low** (`0.1 - 0.3`) to prevent structural hallucinations during complex JSON generation.
---
## 🔗 Links & Resources
* [GitHub] *(Coming Soon)*
* [Documentation] *(Coming Soon)*
* [Community Discord](#) *(Coming Soon)*
> *"Precision over parameters."*