---
license: mit
language:
- en
tags:
- gguf
- phi-3
- llama.cpp
- quantized
- redactor
- q4_k_m
- text-generation
pipeline_tag: text-generation
datasets:
- King-Harry/NinjaMasker-PII-Redaction-Dataset
base_model:
- microsoft/Phi-3-mini-4k-instruct
- christopherheuer/phi3-mini-4k-instruct-pii-redactor
---

# ⚡ Phi-3 Mini Instruct Redactor - GGUF (Q4_K_M)

This is a **GGUF-format**, Q4_K_M **quantized version** of [`phi3-mini-4k-instruct-pii-redactor`](https://huggingface.co/christopherheuer/phi3-mini-4k-instruct-pii-redactor), optimized for **local inference with llama.cpp** and other GGUF-compatible tools.

The model was LoRA-finetuned for redaction/instruction tasks and fully merged before conversion and quantization.

## 🛠 Format & Details

- **Model Base:** `microsoft/Phi-3-mini-4k-instruct`
- **LoRA Merged:** ✅
- **GGUF Format:** ✅
- **Quantization:** Q4_K_M (4-bit grouped, high quality)
- **File:** `phi3-mini-instruct-redactor-q4km.gguf`
- **Model Size:** ~2–3 GB

## 💻 Usage with `llama.cpp`

```bash
./llama-cli.exe -m phi3-mini-instruct-redactor-q4km.gguf --prompt "John Doe, born in 1985, lives in Berlin." -n 128 -ngl 100
```

## ✅ Works with:
- llama.cpp (CUDA build)
- text-generation-webui
- KoboldCpp
- llamacpp-python
- LM Studio

## 📖 Dataset Attribution
This model was fine-tuned using a modified version of the [NinjaMasker-PII-Redaction Dataset by King-Harry](https://huggingface.co/datasets/King-Harry/NinjaMasker-PII-Redaction-Dataset), which is licensed under the Apache 2.0 License. The dataset was reformatted to suit the training requirements of this model.

## ⚠️ Disclaimer:
>This model is provided "as-is" without any warranties or guarantees regarding its performance, accuracy, or reliability in detecting and redacting personally identifiable information (PII) or other sensitive data.
>
>The model may fail to identify or fully redact all forms of PII, depending on input format, context, or model limitations.
>
>Use of this model is at your own risk.
>
>The authors and maintainers of this model accept no responsibility or liability for any data leakage, compliance violations, or security breaches that may occur as a result of using this model.

## 📜 License
MIT License