Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+license: mit
+library_name: gguf
+tags:
+- phi3
+- prompt-engineering
+- gguf
+- quantization
+base_model: microsoft/Phi-3-mini-4k-instruct
+---
+
+# Phi-3 Prompt Engineer (GGUF)
+
+This repository contains **GGUF** quantized versions of the **Phi-3 Prompt Engineer** model, fine-tuned to excel at refining user requests into detailed, structured prompts for LLMs.
+
+## Model Description
+
+- **Base Model**: [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
+- **Fine-tuning**: LoRA adapters trained on a custom dataset of prompt refinement examples.
+- **Purpose**: To act as a specialized "Prompt Engineer" agent, converting vague user ideas into high-quality, actionable system instructions and prompts.
+
+## Available Quantizations
+
+The following GGUF files are available for download. **Q4_K_M** is recommended for most users as it balances performance and quality perfectly.
+
+| Filename | Quantization | Size | SHA256 Checksum |
+|----------|--------------|------|-----------------|
+| phi3-prompt-engineer-f16.gguf | F16 | 7.12 GB | `1bc8a41027c400eda38d5dc9cf97fcf0a4617072d2c3c132b922dd2589783c16` |
+| phi3-prompt-engineer-q4_k_m.gguf | Q4_K_M | 2.23 GB | `cc840e37e0f21c97bf158211a2f0dda1096294ee47ab3f199da854cc841c39f7` |
+| phi3-prompt-engineer-q5_k_m.gguf | Q5_K_M | 2.62 GB | `218b8021b5f1b1efb2e0914d939f5464d8cb790ef9d9e35eaa05e1b8b3cc560f` |
+| phi3-prompt-engineer-q6_k.gguf | Q6_K | 2.92 GB | `4cf033bfe14c43ebf84e47f7184f2f0f5286a30a2c87927d59aa95d9b4a455d5` |
+| phi3-prompt-engineer-q8_0.gguf | Q8_0 | 3.78 GB | `2aa4f14b038c01a50ad8e3306832a25b8c6f704aa1d9efa29a88856dee924fce` |
+
+## Usage
+
+### Ollama
+
+You can use these files directly with [Ollama](https://ollama.com).
+
+1. Create a `Modelfile`:
+   ```dockerfile
+   FROM ./phi3-prompt-engineer-q4_k_m.gguf
+   SYSTEM "You are an Expert Prompt Engineer. Your goal is to refine the following user request into a clear, structured, and detailed prompt."
+   ```
+
+2. Create and run the model:
+   ```bash
+   ollama create phi3-pe -f Modelfile
+   ollama run phi3-pe
+   ```
+
+### llama.cpp
+
+```bash
+./main -m phi3-prompt-engineer-q4_k_m.gguf -p "You are an Expert Prompt Engineer. Refine this: make a snake game in python"
+```
+
+## Training Data
+
+The model was trained on a proprietary dataset (`raw_dataset.jsonl`) consisting of:
+- **Input**: Raw, often vague user requests (e.g., "make a login page").
+- **Output**: Detailed, structured Prompt Engineering responses including personas, constraints, and specific requirements.
+- **Focus**: Web development, Python scripting, creative writing, and system design tasks.
+
+## License
+
+MIT