CoolFace
Modelpublic

kalyan1900/PII-GUARD-Qwen2.5-1.5B

sourceHugging Faceupdated 1mo agoView on Hugging Face
1likes197downloads
Model Card

tags:

  • —text-generation
  • —causal-lm
  • —qwen2.5
  • —pii
  • —pii-detection
  • —pii-extraction
  • —privacy
  • —fine-tuning
  • —lora
  • —unsloth
  • —trl
  • —gguf
  • —llama.cpp
  • —ollama license: apache-2.0 base_model: Qwen/Qwen2.5-1.5B-Instruct ---

PII-GUARD-Qwen2.5-1.5B

A fine-tuned Qwen2.5-1.5B-Instruct model for detecting and extracting Personally Identifiable Information (PII) from unstructured text.

The model was fine-tuned using LoRA/QLoRA with Unsloth and TRL on the NVIDIA Nemotron-PII dataset.

The model is trained to return detected PII entities in a structured JSON format.

Model Overview

PropertyDetails
Base ModelQwen/Qwen2.5-1.5B-Instruct
TaskPII Detection / Extraction
Fine-tuningLoRA / QLoRA
FrameworkUnsloth + TRL
DatasetNVIDIA Nemotron-PII
Training MethodSupervised Fine-Tuning (SFT)
Output FormatStructured JSON
GGUFAvailable
QuantizationQ4KM
InferenceTransformers / llama.cpp / Ollama

What does this model do?

Given a piece of text, the model identifies PII entities and returns them as structured JSON.

This was trained 2x faster with Unsloth <img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>