HyzeMiniGGUF / README.md
HyzeAI's picture
Update README.md
9d6b7a0 verified
---
license: apache-2.0
language:
- en
base_model:
- HyzeAI/HyzeMini
pipeline_tag: text-generation
library_name: transformers.js
tags:
- gguf
- hyze
- local
- chat
- Hitesh_V_Founder
---
<p align="center">
<img src="https://i.imgur.com/ePJMLNp.png" alt="Hyze Logo" width="405"/>
</p>
<h1 align="center">HyzeMini (GGUF)</h1>
<p align="center">
Lightweight GGUF builds of <b>HyzeMini</b> for fast local inference
</p>
<p align="center">
πŸ”— <a href="https://hyzebot.vercel.app">hyzebot.vercel.app</a> β€’
πŸ“˜ <a href="https://hyzedocs.vercel.app">hyzedocs.vercel.app</a> β€’
🧠 <a href="https://hyzecode.vercel.app">hyzecode.vercel.app</a>
</p>
---
## πŸš€ Overview
**HyzeMini (GGUF)** provides **quantized GGUF versions** of the HyzeMini model, optimized for **local execution** using tools like **llama.cpp**, **LM Studio**, **Ollama**, and other GGUF-compatible runtimes.
This version keeps the same **Space + General Chat focus**, while enabling:
- ⚑ Faster inference
- 🧠 Lower memory usage
- πŸ’» CPU-friendly execution
---
## 🧠 Model Details
- **Base model:** HyzeAI / HyzeMini
- **Parameters:** ~0.1B
- **Architecture:** Transformer (LLaMA-style)
- **Format:** GGUF
- **Language:** English
- **License:** Apache-2.0
---
## πŸ§ͺ Available Quantizations
*(Exact files may vary depending on upload)*
Common GGUF variants include:
- `Q2_K` – Ultra-low memory, fastest
- `Q4_K_M` – Balanced quality & speed (recommended)
- `Q5_K_M` – Higher quality, slightly slower
- `Q8_0` – Best quality, highest memory usage
> πŸ’‘ If you’re unsure, start with **Q4_K_M**.
---
## βš™οΈ Usage
### llama.cpp
```bash
./main -m HyzeMini-Q4_K_M.gguf -p "Tell me a cool space fact:"
---