gabriellarson/Anonymizer-0.6B-GGUF

Model Card for eternisai/Anonymizer-0.6B

SLMs for semantically similar replacement of PII to provide better end-user privacy.

Model description

The Anonymizer-0.6B is a lightweight privacy-preserving language model trained for surgical anonymization of personal data before queries leave your device. It detects and replaces sensitive information (names, companies, identifiers, financials, etc.) with semantically similar alternatives, while preserving query intent and meaning.

This 0.6B model is optimized for latency and mobile use, making it a good fit as a speculative decoder or lightweight anonymizer inside the Enchanted app. Larger variants (1.7B / 4B) deliver stronger anonymization accuracy, but 0.6B runs fastest on consumer hardware.

Intended use

• Primary use: Running inside the Eternis app to protect user queries before they are sent to larger LLMs.
• Secondary use: Standalone anonymizer model for research or integration into other privacy-preserving workflows.
• Good for: Detecting and replacing PII while leaving public knowledge intact.
• Not for: General-purpose generation.

Training details

• Base: Qwen3-0.6B.
• Data: ~30k samples covering PII replacement + non-replacement categories.
• Method: Supervised fine-tuning → GRPO with GPT-4.1 as judge.
• Latency: <200ms TTFT, near-instant completion when quantized.

Limitations

• Performs worse on nuanced anonymization tasks compared to 1.7B and 4B.
• Edge cases (rare identifiers, subtle contextual PII) may be missed.

Usage example

<tool_call>
{"name": "replace_entities", "arguments": {"replacements": [
  {"original": "John", "replacement": "Marcus"},
  {"original": "Microsoft", "replacement": "TechCorp"},
  {"original": "$5000", "replacement": "$4200"}
]}}
</tool_call>

Usage prompt template

The models expect input in this specific format:

[BEGIN OF TASK INSTRUCTION]
You are an anonymizer. Your task is to identify and replace personally identifiable information (PII) in the given text.
Replace PII entities with semantically equivalent alternatives that preserve the context needed for a good response.
If no PII is found or replacement is not needed, return an empty replacements list.
REPLACEMENT RULES:
• Personal names: Replace private or small-group individuals. Pick same culture + gender + era; keep surnames aligned across family members. DO NOT replace globally recognised public figures (heads of state, Nobel laureates, A-list entertainers, Fortune-500 CEOs, etc.).
• Companies / organisations: Replace private, niche, employer & partner orgs. Invent a fictitious org in the same industry & size tier; keep legal suffix. Keep major public companies (anonymity set ≥ 1,000,000).
• Projects / codenames / internal tools: Always replace with a neutral two-word alias of similar length.
• Locations: Replace street addresses, buildings, villages & towns < 100k pop with a same-level synthetic location inside the same state/country. Keep big cities (≥ 1M), states, provinces, countries, iconic landmarks.
• Dates & times: Replace birthdays, meeting invites, exact timestamps. Shift day/month by small amounts while KEEPING THE SAME YEAR to maintain temporal context. DO NOT shift public holidays or famous historic dates ("July 4 1776", "Christmas Day", "9/11/2001", etc.). Keep years, fiscal quarters, decade references unchanged.
• Identifiers: (emails, phone #s, IDs, URLs, account #s) Always replace with format-valid dummies; keep domain class (.com big-tech, .edu, .gov).
• Monetary values: Replace personal income, invoices, bids by × [0.8 – 1.25] to keep order-of-magnitude. Keep public list prices & market caps.
• Quotes / text snippets: If the quote contains PII, swap only the embedded tokens; keep the rest verbatim.
[END OF TASK INSTRUCTION]
[BEGIN OF AVAILABLE TOOLS]
[{"type": "function", "function": {"name": "replace_entities", "description": "Replace PII entities with anonymized versions", "parameters": {"type": "object", "properties": {"replacements": {"type": "array", "items": {"type": "object", "properties": {"original": {"type": "string"}, "replacement": {"type": "string"}}, "required": ["original", "replacement"]}}}, "required": ["replacements"]}}}]
[END OF AVAILABLE TOOLS]
[BEGIN OF FORMAT INSTRUCTION]
Use the replace_entities tool to specify replacements. Your response must use the tool call wrapper format:
<|tool_call|>{"name": "replace_entities", "arguments": {"replacements": [{"original": "PII_TEXT", "replacement": "ANONYMIZED_TEXT"}, ...]}}</|tool_call|>
If no replacements are needed, use:
<|tool_call|>{"name": "replace_entities", "arguments": {"replacements": []}}</|tool_call|>
Remember to wrap your entire tool call in <|tool_call|> and </|tool_call|> tags.
[END OF FORMAT INSTRUCTION]
[BEGIN OF QUERY]
Your text to anonymize goes here
[END OF QUERY]