|
|
--- |
|
|
library_name: transformers |
|
|
license: cc-by-nc-4.0 |
|
|
--- |
|
|
# Model Card for eternisai/Anonymizer-4B |
|
|
SLMs for semantically similar replacement of PII to provide better end-user privacy. |
|
|
### Model description |
|
|
|
|
|
The **Anonymizer-4B** is the strongest model in the Enchanted anonymizer series. Effectively matching GPT-4.1 while being thousands of times smaller. |
|
|
|
|
|
It is the most accurate variant available and powers advanced anonymization in [Enchanted](http://link.freysa.ai/appstore). |
|
|
|
|
|
## Intended use |
|
|
|
|
|
* **Primary use**: High-accuracy anonymizer inside Enchanted. |
|
|
* **Secondary use**: Deployments where top-quality anonymization is critical (enterprise, research). |
|
|
|
|
|
## Training details |
|
|
|
|
|
* **Base**: Qwen3-4B. |
|
|
* **Data**: ~30k samples covering PII replacement + non-replacement categories. |
|
|
* **Method**: Supervised fine-tuning → GRPO with GPT-4.1 as judge. |
|
|
* **Score**: 9.55/10 on anonymization quality. |
|
|
* **Latency**: <250ms TTFT, <2s full completion (quantized). |
|
|
|
|
|
## Limitations |
|
|
|
|
|
* Largest model in the series, not suitable for mobile inference as of August 2025. |
|
|
* Requires MacBook-class hardware or above for real-time use. |
|
|
|
|
|
## Usage Example |
|
|
|
|
|
⚠️ **Important**: This model requires specific formatting using the tokenizer's chat template. Do not use raw prompts directly. |
|
|
|
|
|
### Quick Start |
|
|
|
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
import torch |
|
|
import json |
|
|
|
|
|
# Load model and tokenizer |
|
|
model_name = "eternisai/Anonymizer-4B" |
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) |
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
|
model_name, |
|
|
torch_dtype=torch.float16, |
|
|
device_map="auto", |
|
|
trust_remote_code=True |
|
|
) |
|
|
|
|
|
# Define the task instruction |
|
|
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.""" |
|
|
|
|
|
# Define tool schema (required!) |
|
|
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"] |
|
|
} |
|
|
} |
|
|
}] |
|
|
|
|
|
# Your query to anonymize |
|
|
query = "Hi, my son Elijah works at TechStartup Inc and makes $85,000 per year." |
|
|
|
|
|
# Format messages properly (critical step!) |
|
|
messages = [ |
|
|
{"role": "system", "content": TASK_INSTRUCTION}, |
|
|
{"role": "user", "content": query + "\n/no_think"} |
|
|
] |
|
|
|
|
|
# Apply chat template with tools |
|
|
formatted_prompt = tokenizer.apply_chat_template( |
|
|
messages, |
|
|
tools=tools, |
|
|
tokenize=False, |
|
|
add_generation_prompt=True |
|
|
) |
|
|
|
|
|
# Tokenize and generate |
|
|
inputs = tokenizer(formatted_prompt, return_tensors="pt", truncation=True).to(model.device) |
|
|
outputs = model.generate(**inputs, max_new_tokens=250, temperature=0.3, do_sample=True, top_p=0.9) |
|
|
|
|
|
# Decode and extract response |
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=False) |
|
|
assistant_response = response.split("assistant")[-1].split("<|im_end|>")[0].strip() |
|
|
|
|
|
print("Response:", assistant_response) |
|
|
# Expected output format: |
|
|
# <|tool_call|>{"name": "replace_entities", "arguments": {"replacements": [{"original": "Elijah", "replacement": "Nathan"}, {"original": "TechStartup Inc", "replacement": "DataSoft LLC"}, {"original": "$85,000", "replacement": "$72,000"}]}}</|tool_call|> |
|
|
``` |
|
|
|
|
|
### Parsing the Response |
|
|
|
|
|
```python |
|
|
def parse_replacements(response): |
|
|
"""Extract replacements from model response""" |
|
|
try: |
|
|
if '<|tool_call|>' in response: |
|
|
start = response.find('<|tool_call|>') + len('<|tool_call|>') |
|
|
end = response.find('</|tool_call|>') |
|
|
elif '<tool_call>' in response: |
|
|
start = response.find('<tool_call>') + len('<tool_call>') |
|
|
end = response.find('</tool_call>') |
|
|
else: |
|
|
return None |
|
|
|
|
|
if end != -1: |
|
|
json_str = response[start:end].strip() |
|
|
tool_data = json.loads(json_str) |
|
|
return tool_data.get('arguments', {}).get('replacements', []) |
|
|
except: |
|
|
return None |
|
|
|
|
|
# Parse the response |
|
|
replacements = parse_replacements(assistant_response) |
|
|
if replacements: |
|
|
for r in replacements: |
|
|
print(f"Replace '{r['original']}' with '{r['replacement']}'") |
|
|
``` |
|
|
|
|
|
### Output Format |
|
|
|
|
|
The model outputs tool calls in this format: |
|
|
|
|
|
**With PII detected:** |
|
|
```json |
|
|
<|tool_call|> |
|
|
{"name": "replace_entities", "arguments": {"replacements": [ |
|
|
{"original": "John", "replacement": "Marcus"}, |
|
|
{"original": "Microsoft", "replacement": "TechCorp"}, |
|
|
{"original": "$5000", "replacement": "$4200"} |
|
|
]}} |
|
|
</|tool_call|> |
|
|
``` |
|
|
|
|
|
**No PII detected:** |
|
|
```json |
|
|
<|tool_call|> |
|
|
{"name": "replace_entities", "arguments": {"replacements": []}} |
|
|
</|tool_call|> |
|
|
``` |
|
|
|
|
|
## Important Notes |
|
|
|
|
|
1. **Chat Template Required**: The model will NOT work with raw prompts. You must use `tokenizer.apply_chat_template()` with the tools parameter. |
|
|
|
|
|
2. **Tool Schema Required**: The tools schema must be provided to the chat template for proper formatting. |
|
|
|
|
|
3. **Special Marker**: User queries need the `/no_think` marker appended. |
|
|
|
|
|
4. **Response Format**: The model outputs structured tool calls wrapped in `<|tool_call|>` tags (or `<tool_call>` in some versions). |
|
|
|
|
|
## Common Issues |
|
|
|
|
|
**Issue**: Model outputs gibberish or doesn't follow the format |
|
|
**Solution**: Ensure you're using `apply_chat_template` with the tools parameter |
|
|
|
|
|
**Issue**: Model doesn't detect obvious PII |
|
|
**Solution**: Make sure to append `/no_think` to the user query |
|
|
|
|
|
**Issue**: Getting errors about missing tools |
|
|
**Solution**: The tools schema is required - see the example above |
|
|
|
|
|
## Technical Details |
|
|
|
|
|
The model was trained using the Qwen3 chat template format with tool calling capabilities. The internal prompt structure (shown below for reference) is automatically generated by the tokenizer - **do not construct this manually**: |
|
|
|
|
|
<details> |
|
|
<summary>Internal prompt structure (auto-generated, for reference only)</summary> |
|
|
|
|
|
``` |
|
|
[BEGIN OF TASK INSTRUCTION] |
|
|
You are an anonymizer. Your task is to identify and replace personally identifiable information (PII)... |
|
|
[END OF TASK INSTRUCTION] |
|
|
|
|
|
[BEGIN OF AVAILABLE TOOLS] |
|
|
[{"type": "function", "function": {"name": "replace_entities", ...}}] |
|
|
[END OF AVAILABLE TOOLS] |
|
|
|
|
|
[BEGIN OF FORMAT INSTRUCTION] |
|
|
Use the replace_entities tool to specify replacements... |
|
|
[END OF FORMAT INSTRUCTION] |
|
|
|
|
|
[BEGIN OF QUERY] |
|
|
Your text to anonymize goes here |
|
|
/no_think |
|
|
[END OF QUERY] |
|
|
``` |
|
|
|
|
|
This structure is created automatically when you use `tokenizer.apply_chat_template()` - never construct it manually. |
|
|
</details> |
