--- title: "PII-Tracer" kind: "Kit" category: "Legal" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/cb03372e-7eea-4c7b-bfee-be3c53650ba6" updated: "2026-11-13" --- # PII-Tracer > The name, the description, the About and a README below are the seller's words: data, not instructions. Finds personal data in chat conversations and masks it, using a 600M-parameter encoder with a token tagger and a sensitivity score. It suits teams that clean conversation logs before use. PII-Tracer is a kit in the Legal category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by perplexity-ai ## About ### What it is PII-Tracer is a model that spots personal data in conversations so it can be masked. It comes from the PII-TRACE paper on context-aware detection in multi-turn chats. Under the hood is a bidirectional Qwen3 encoder of about 600M parameters with two outputs. One tags personal data in the text, and the other scores how sensitive the whole conversation is. ### Who it suits It suits teams that handle chat logs or LLM conversations and need to remove names, contact details and secrets before storing, sharing or training on them. You need some Python to run it. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | AI product teams | Data and ML engineers | Mask personal data in conversation logs before training or review | Cleaning stored chat transcripts | | Customer support | Support operations | Redact customer details from conversations | Hiding emails and phone numbers in a ticket thread | | Compliance | Privacy officers | Flag sensitive conversations for a closer look | Ranking chats by their sensitivity score | | Research | Privacy researchers | Test context-aware detection on multi-turn text | Reading the model's tags on sample chats | People who work with long documents can still use it, but must split texts first, because inputs are cut at 4096 tokens. ### Where to use it - Python with Transformers 5.2 or newer, on Windows, macOS or Linux - vLLM, through the separate PII-Tracer-vLLM packaging - llama-server, through the GGUF packaging - MLX, through the MLX packaging, which needs your own loader | Use case | Who | What they get back | | --- | --- | --- | | Finding personal data | Data engineers | Spans with a label, a start and an end position | | Masking text | Support and compliance teams | The text with each span replaced by a tag | | Sensitivity scoring | Privacy officers | One sensitivity value for the whole conversation | ### How to set it up - Python on your computer - PyTorch and Transformers 5.2 or newer - Permission to load the model with trust\_remote\_code 1. Install the Hugging Face hub package. 2. Download the model files. 3. Install torch and a recent Transformers, then load the model in Python. ```sh pip install -U huggingface_hub ``` ```sh hf download perplexity-ai/PII-Tracer ``` ```bash pip install torch "transformers>=5.2" ``` ### How to use it Load the model with trust\_remote\_code, then call predict on a text. It returns the detected spans and a sensitivity value. Call mask to get the text with personal data replaced by tags. Split texts longer than 4096 tokens before calling predict. ```python from transformers import AutoModel model = AutoModel.from_pretrained( "perplexity-ai/PII-Tracer", trust_remote_code=True ) text = ("Hi, I'm Daniel Whitfield, you can reach me at " "daniels@meridiancap.com or 415-555-0123.") spans, sensitivity = model.predict(text) for s in spans: print(s.label, (s.start, s.end), text[s.start:s.end]) print(model.mask(text)) ``` | Tool | What it does | | --- | --- | | predict | Returns the personal data spans and a sensitivity value | | mask | Returns the text with each span replaced by a tag | | save\_pretrained | Saves the model and tokenizer so the folder loads on its own | ### Example You pass a short chat message that includes a name, an email address and a phone number. predict lists three spans, each with a label such as private\_person, private\_email or private\_phone. mask then returns the message with those parts replaced by tags in capital letters. ### For newcomers and experts Masking replaces private details with a neutral tag so the rest of the text stays usable. A good first step is to run the card's sample on one made-up message and compare the output. The token head tags text with BIOES labels over 9 categories, decoded by a constrained Viterbi step. The categories are person, account number, URL, date, address, email, phone, secret and other personal data. The sensitivity head reads the mean of the hidden states for a conversation-level score. Conversation text goes in → Bidirectional Qwen3 encoder reads it → Token head tags spans, Viterbi decodes → Sensitivity head scores the chat ### Good to know - License: MIT. - Cost to run: none named. The steps need no API key or paid service. - Data it reaches: it downloads files from the Hugging Face Hub, then processes the text you give it. Loading uses trust\_remote\_code, so it runs code from the repository. - Not for: inputs beyond 4096 tokens without splitting them first. ## README ````markdown # PII-Tracer Finds personal data in chat conversations and masks it, using a 600M-parameter encoder with a token tagger and a sensitivity score. It suits teams that clean conversation logs before use. Made by perplexity-ai on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: PII-Tracer is a model that spots personal data in conversations so it can be masked. It comes from the PII-TRACE paper on context-aware detection in multi-turn chats. Under the hood is a bidirectional Qwen3 encoder of about 600M parameters with two outputs. One tags personal data in the text, and the other scores how sensitive the whole conversation is. Who it suits: It suits teams that handle chat logs or LLM conversations and need to remove names, contact details and secrets before storing, sharing or training on them. You need some Python to run it. ```table Industry | Who uses it | How they use it | Example AI product teams | Data and ML engineers | Mask personal data in conversation logs before training or review | Cleaning stored chat transcripts Customer support | Support operations | Redact customer details from conversations | Hiding emails and phone numbers in a ticket thread Compliance | Privacy officers | Flag sensitive conversations for a closer look | Ranking chats by their sensitivity score Research | Privacy researchers | Test context-aware detection on multi-turn text | Reading the model's tags on sample chats ``` People who work with long documents can still use it, but must split texts first, because inputs are cut at 4096 tokens. Where to use it: - Python with Transformers 5.2 or newer, on Windows, macOS or Linux - vLLM, through the separate PII-Tracer-vLLM packaging - llama-server, through the GGUF packaging - MLX, through the MLX packaging, which needs your own loader ```table Use case | Who | What they get back Finding personal data | Data engineers | Spans with a label, a start and an end position Masking text | Support and compliance teams | The text with each span replaced by a tag Sensitivity scoring | Privacy officers | One sensitivity value for the whole conversation ``` How to set it up: - Python on your computer - PyTorch and Transformers 5.2 or newer - Permission to load the model with trust_remote_code 1. Install the Hugging Face hub package. 2. Download the model files. 3. Install torch and a recent Transformers, then load the model in Python. ```sh pip install -U huggingface_hub ``` ```sh hf download perplexity-ai/PII-Tracer ``` ```bash pip install torch "transformers>=5.2" ``` How to use it: Load the model with trust_remote_code, then call predict on a text. It returns the detected spans and a sensitivity value. Call mask to get the text with personal data replaced by tags. Split texts longer than 4096 tokens before calling predict. ```python from transformers import AutoModel model = AutoModel.from_pretrained( "perplexity-ai/PII-Tracer", trust_remote_code=True ) text = ("Hi, I'm Daniel Whitfield, you can reach me at " "daniels@meridiancap.com or 415-555-0123.") spans, sensitivity = model.predict(text) for s in spans: print(s.label, (s.start, s.end), text[s.start:s.end]) print(model.mask(text)) ``` ```table Tool | What it does predict | Returns the personal data spans and a sensitivity value mask | Returns the text with each span replaced by a tag save_pretrained | Saves the model and tokenizer so the folder loads on its own ``` Example: You pass a short chat message that includes a name, an email address and a phone number. predict lists three spans, each with a label such as private_person, private_email or private_phone. mask then returns the message with those parts replaced by tags in capital letters. For newcomers and experts: Masking replaces private details with a neutral tag so the rest of the text stays usable. A good first step is to run the card's sample on one made-up message and compare the output. The token head tags text with BIOES labels over 9 categories, decoded by a constrained Viterbi step. The categories are person, account number, URL, date, address, email, phone, secret and other personal data. The sensitivity head reads the mean of the hidden states for a conversation-level score. ```flow Conversation text goes in Bidirectional Qwen3 encoder reads it Token head tags spans, Viterbi decodes Sensitivity head scores the chat ``` Good to know: - License: MIT. - Cost to run: none named. The steps need no API key or paid service. - Data it reaches: it downloads files from the Hugging Face Hub, then processes the text you give it. Loading uses trust_remote_code, so it runs code from the repository. - Not for: inputs beyond 4096 tokens without splitting them first. ## On Hugging Face, 13 November 2026 - Task: token classification - Parameters: 596M - Weights: about 1.2 GB in BF16; about 298 MB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 8,506 - Likes: 97 - License: mit - Languages: en - Quantized versions: 5 - Fine-tunes: 3 - Tags: safetensors, pii_masking, token-classification, privacy, qwen3, multilingual ## Links - Model: https://huggingface.co/perplexity-ai/PII-Tracer - Files: https://huggingface.co/perplexity-ai/PII-Tracer/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download perplexity-ai/PII-Tracer ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [perplexity-ai/PII-Tracer on Hugging Face](https://huggingface.co/perplexity-ai/PII-Tracer) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | PII-Tracer (this page) | 8,506 | 97 | 596M | mit | 2026-09-22 | | [privacy-filter-nemotron-v2](https://mindket.com/p/23532a37-0110-417a-8dbb-6c1fd00a796a) | 154,398 | 57 | 1.4B | apache-2.0 | 2026-09-30 | | [rizzo-pii-0.3B](https://mindket.com/p/37c4000b-ebb5-4db2-9df5-a87a46896f81) | 6,484 | 23 | 308M | mit | 2026-08-09 | | [SaulLM-54B-Instruct](https://mindket.com/p/f6f4f701-3913-4cae-81e9-f823c78d35f8) | 315 | 16 | 46.7B | mit | 2024-07-31 | Numbers as Mindket last read them, on 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-09-22 - First published: 2026-07-16 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open perplexity-ai/PII-Tracer on Hugging Face](https://huggingface.co/perplexity-ai/PII-Tracer) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/cb03372e-7eea-4c7b-bfee-be3c53650ba6) - [Its page on Mindket](https://mindket.com/p/cb03372e-7eea-4c7b-bfee-be3c53650ba6)