> ## Documentation Index
> Fetch the complete documentation index at: https://docs.liquid.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# LFM2-350M-PII-Extract-JP

> 350M parameter model for Japanese PII detection and extraction

<a href="/lfm/models/liquid-nanos" className="back-button">← Back to Liquid Nanos</a>

LFM2-350M-PII-Extract-JP extracts personally identifiable information (PII) from Japanese text as structured JSON. Output can be used to mask sensitive information on-device for privacy-preserving applications.

<div style={{display: 'flex', gap: '0.5rem', margin: '0.5rem 0 1.5rem 0'}}>
  <a href="https://huggingface.co/LiquidAI/LFM2-350M-PII-Extract-JP" style={{padding: '0.35rem 0.7rem', borderRadius: '4px', fontSize: '0.85rem', fontWeight: 600, textDecoration: 'none', backgroundColor: '#fbbf24'}}><span style={{color: '#000'}}>HF</span></a>
  <a href="https://huggingface.co/LiquidAI/LFM2-350M-PII-Extract-JP-GGUF" style={{padding: '0.35rem 0.7rem', borderRadius: '4px', fontSize: '0.85rem', fontWeight: 600, textDecoration: 'none', backgroundColor: '#60a5fa'}}><span style={{color: '#000'}}>GGUF</span></a>
</div>

## Specifications

| Property       | Value         |
| -------------- | ------------- |
| Parameters     | 350M          |
| Context Length | 32K tokens    |
| Task           | PII Detection |
| Language       | Japanese      |

<div className="use-cases">
  <CardGroup cols={3}>
    <Card title="Privacy Protection" icon="shield-halved">
      On-device PII masking
    </Card>

    <Card title="Compliance" icon="scale-balanced">
      Data protection compliance
    </Card>

    <Card title="Document Redaction" icon="eraser">
      Automated redaction
    </Card>
  </CardGroup>
</div>

## Prompting Recipe

<Warning>
  Use `temperature=0` (greedy decoding) for best results. This model is intended for single-turn conversations only.
</Warning>

**System Prompt Format:**

```
Extract <address>, <company_name>, <email_address>, <human_name>, <phone_number>
```

Extract specific entities by listing only what you need (e.g., `Extract <human_name>`). List categories in alphabetical order for optimal performance.

**Output Format:** JSON with lists per category. Empty lists for missing entities. Outputs entities exactly as they appear (including notation variations) for exact-match masking.

## Quick Start

<Tabs>
  <Tab title="Transformers">
    **Install:**

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    pip install "transformers>=5.2.0" torch accelerate
    ```

    **Run:**

    ```python theme={"theme":{"light":"github-light","dark":"github-dark"}}
    from transformers import AutoTokenizer, AutoModelForCausalLM

    model_id = "LiquidAI/LFM2-350M-PII-Extract-JP"
    tokenizer = AutoTokenizer.from_pretrained(model_id)
    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

    system_prompt = "Extract <address>, <company_name>, <email_address>, <human_name>, <phone_number>"

    user_input = """こんにちは、ラミンさんに B200 GPU を 10000 台 至急請求してください。
    連絡先は celegans@liquid.ai (電話番号010-000-0000) で、これは C. elegans
    線虫に着想を得たニューラルネットワークアーキテクチャを 今すぐ構築するために不可欠です。"""

    messages = [
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": user_input}
    ]

    inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=256, temperature=0, do_sample=False)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    print(response)
    # Output: {"address": [], "company_name": [], "email_address": ["celegans@liquid.ai"],
    #          "human_name": ["ラミン"], "phone_number": ["010-000-0000"]}
    ```
  </Tab>

  <Tab title="llama.cpp">
    **Download GGUF:**

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    hf download LiquidAI/LFM2-350M-PII-Extract-JP-GGUF \
      --local-dir ./LFM2-350M-PII-Extract-JP-GGUF
    ```

    **Run:**

    ```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
    llama-cli -m ./LFM2-350M-PII-Extract-JP-GGUF/LFM2-350M-PII-Extract-JP-Q4_K_M.gguf \
      -sys "Extract <human_name>, <phone_number>" \
      -p "田中太郎様、電話番号は090-1234-5678です。" \
      --temp 0
    ```
  </Tab>
</Tabs>