| <div align="center"> | |
| <img src="https://github.com/bloomifycafe/blossomsAI/blob/main/assets/logo.png?raw=true" alt="Logo"/> | |
| </div> | |
| </br> | |
| <div align="center"> | |
| # 🚀 Final_demo-GGUF | |
| ### Optimized quantized models for efficient inference | |
| </div> | |
| ## 📋 Overview | |
| A collection of optimized GGUF quantized models derived from [Final_demo](https://huggingface.co/BlossomsAI/BloomVN-0.5B-ppo), providing various performance-quality tradeoffs. | |
| <div style="width: 100%; text-align: left; margin-left: 0;"> | |
| ## 💎 Model Variants | |
| | Variant | Use Case | Download | | |
| |---------|-----------|------------| | |
| | Final_demo_int8 | This variant is suitable for mobile and embedded devices where memory and computational resources are limited, providing a balance between accuracy and efficiency. | [📥](https://huggingface.co/Vuanhngo11/Final_demo-gguf/resolve/main/Final_demo_int8.gguf) | |
| | Final_demo_fp16 | This variant is ideal for applications requiring high accuracy and fast inference speed, such as real-time object detection and image classification, while still being relatively memory-efficient. | [📥](https://huggingface.co/Vuanhngo11/Final_demo-gguf/resolve/main/Final_demo_fp16.gguf) | |
| | Final_demo_fp32 | This variant is best suited for applications where high accuracy is paramount, such as in research and development environments, or when working with complex datasets that require precise calculations. | [📥](https://huggingface.co/Vuanhngo11/Final_demo-gguf/resolve/main/Final_demo_fp32.gguf) | |
| ## 🤝 Contributors | |
| Developed with ❤️ by [BlossomAI](https://huggingface.co/BlossomsAI) | |
| --- | |
| <div align="center"> | |
| <sub>Star ⭐️ this repo if you find it valuable!</sub> | |
| </div> |