eternis/qwen3-dpo-pii-anonymizer-merged-july15

Qwen3-DPO-PII-Anonymizer

A Direct Preference Optimization (DPO) fine-tuned Qwen3-0.6B model specifically designed for PII (Personally Identifiable Information) anonymization tasks.

Model Details

• Base Model: Qwen3-0.6B
• Training Method: Direct Preference Optimization (DPO)
• Optimization: Unsloth optimizations for faster training
• Task: PII Anonymization with tool calling capabilities
• Context Length: 4096 tokens
• Model Size: ~1.1GB

Training Data

Trained on preference pairs for PII anonymization tasks, where the model learns to:

• Identify personally identifiable information in text
• Replace PII with semantically equivalent alternatives
• Preserve context while maintaining anonymity
• Use structured tool calls for replacements

Usage

The model is designed to work with the replace_entities tool for PII anonymization:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("eternis/qwen3-dpo-pii-anonymizer", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("eternis/qwen3-dpo-pii-anonymizer", trust_remote_code=True)

# Example prompt for PII anonymization
prompt = "Replace PII in: John Smith works at ABC Corp and lives at 123 Main St, New York."

Tool Schema

The model uses the following tool schema for PII replacement:

{
  "type": "function",
  "function": {
    "name": "replace_entities",
    "description": "Replace personally identifiable information (PII) with anonymized alternatives",
    "parameters": {
      "type": "object",
      "properties": {
        "replacements": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "original": {"type": "string", "description": "Original PII text"},
              "replacement": {"type": "string", "description": "Anonymized replacement"}
            },
            "required": ["original", "replacement"]
          },
          "description": "List of PII replacements to make"
        }
      },
      "required": ["replacements"]
    }
  }
}

Training Configuration

• Learning Rate: 5e-6
• Batch Size: 2 (with gradient accumulation of 8)
• Epochs: 3
• LoRA Rank: 16
• LoRA Alpha: 32
• Max Length: 2048 tokens
• Max Response: 512 tokens

License

[Add your license information here]

Citation

If you use this model in your research, please cite:

@misc{qwen3-dpo-pii-anonymizer,
  author = {Your Name},
  title = {Qwen3-DPO-PII-Anonymizer},
  year = {2024},
  publisher = {Hugging Face},
  url = {https://huggingface.co/eternis/qwen3-dpo-pii-anonymizer}
}