---
base_model: WeiboAI/VibeThinker-1.5B
library_name: peft
tags:
- llama-cpp
- gguf
- loRA
---

# LegoKeeper/Hexo-0.5-Mini

- **Base Model:** WeiboAI/VibeThinker-1.5B
- **Quantization:** `Q4_K_M`

## Usage

This model was fine-tuned via LoRA and merged.
- `Hexo-0.5-Mini-Q4_K_M.gguf`: High-performance quantized version for llama.cpp / Ollama.