initial commit

.gitattributes

@@ -0,0 +1 @@
+*.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,121 @@
+---
+language: multilingual
+license: mit
+tags:
+- token-classification
+- text-anonymization
+- pii-redaction
+- named-entity-recognition
+- ner
+- roberta
+- privacy
+- data-protection
+- synthetic-data
+- tanaos
+- artifex
+base_model:
+  - tanaos/tanaos-NER-v1
+datasets:
+  - tanaos/synthetic-text-anonymizer-dataset-v1
+library_name: transformers
+task:
+  type: token-classification
+  name: "Text Anonymization (PII Redaction)"
+  description: "A multilingual NER model for detecting and anonymizing personally identifiable information (PII), including PERSON, LOCATION, DATE, ADDRESS, PHONE_NUMBER, and other sensitive entities."
+
+---
+
+<p align="center">
+    <img src="https://raw.githubusercontent.com/tanaos/.github/master/assets/logo.png" width="250px" alt="Tanaos – Train task specific LLMs without training data, for offline NLP and Text Classification">
+</p>
+
+# 🥸 tanaos-text-anonymizer-v1: A small but performant Text Anonymization model
+
+This model was created by Tanaos with the [Artifex Python library](https://github.com/tanaos/artifex).
+
+This is a multilingual (it supports 16+ languages) **Named Entity Recognition model** based on [tanaos/tanaos-NER-v1](https://huggingface.co/tanaos/tanaos-NER-v1) and fine-tuned on [a synthetic dataset](https://huggingface.co/datasets/tanaos/synthetic-text-anonymizer-dataset-v1) to recognize Personal Identifiable Information (PII) entities in text.
+Once identified, the entities can be redacted to ensure privacy and confidentiality, before sharing or processing text data.
+
+While the base NER model was trained to recognize 14 named entity categories, this Text Anonymization was fine-tuned specifically to focus on the following 5 key PII entity categories that are commonly found in text data and are critical for anonymization:
+
+| Entity | Description |
+|--------|-------------|
+| `PERSON` | Individual people, fictional characters |
+| `LOCATION` | Geographical areas |
+| `DATE` | Absolute or relative dates, including years, months and/or days |
+| `ADDRESS` | Full addresses |
+| `PHONE_NUMBER` | Telephone numbers |
+
+## ⚙️ How to Use
+
+This model can be used in one of two ways: 
+
+### Via the Artifex library (`pip install artifex`)
+
+Using this model through our [Artifex Python library](https://github.com/tanaos/artifex), Personal Identifiable Information (PII) aren't just detected, but automatically redacted from the text, replacing them with a placeholder.
+
+```python
+from artifex import Artifex
+
+ta = Artifex().text_anonymization
+
+print(ta("John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567."))
+# >>> ["[MASKED] lives at [MASKED]. His phone number is [MASKED]."]
+```
+
+### Via the Transformers library
+
+
+Using this model through the `transformers` library, Personal Identifiable Information (PII) are only identified, but not automatically redcted; you will have to implement your own redaction logic.
+
+```python
+from transformers import pipeline
+
+ta = pipeline(
+    task="text-anonymization",
+    model="tanaos/tanaos-text-anonymizer-v1",
+    aggregation_strategy="first"
+)
+
+print(ta("John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567."))
+# >>> ["[MASKED] lives at [MASKED]. His phone number is [MASKED]."]
+```
+
+## 🧠 Model Description
+
+- **Base model:** `FacebookAI/roberta-base`
+- **Task:** Token classification (Named Entity Recognition for Text Anonymization)
+- **Languages:** Multilingual (16+ languages)
+- **Fine-tuning data:** A synthetic, custom dataset of around 10,000 passages, each containing multiple named entities across 5 Personal Identifiable Information categories.
+
+## 🎓 Training Details
+
+This model was trained using the [Artifex Python library](https://github.com/tanaos/artifex)
+
+```bash
+pip install artifex
+```
+
+by providing the following instructions and generating 10,000 synthetic training samples:
+
+```python
+from artifex import Artifex
+
+ta = Artifex().text_anonymization
+
+ta.train(
+    domain="general",
+    num_samples=10000
+)
+```
+
+## 🧰 Intended Uses
+
+This model is intended to:
+- Anonymize text data by redacting personal identifiable information (PII) such as names, addresses, phone numbers, dates, and locations.
+- Ensure privacy and confidentiality in text data for compliance with data protection regulations.
+- Be used before sharing or processing text data to protect sensitive information.
+- Be GDPR compliant when handling personal data.
+
+Not intended for:
+- Scenarios involving highly specialized or domain-specific text without further fine-tuning.

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PERSON",
+    "2": "I-PERSON",
+    "3": "B-LOCATION",
+    "4": "I-LOCATION",
+    "5": "B-DATE",
+    "6": "I-DATE",
+    "7": "B-ADDRESS",
+    "8": "I-ADDRESS",
+    "9": "B-PHONE_NUMBER",
+    "10": "I-PHONE_NUMBER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ADDRESS": 7,
+    "B-DATE": 5,
+    "B-LOCATION": 3,
+    "B-PERSON": 1,
+    "B-PHONE_NUMBER": 9,
+    "I-ADDRESS": 8,
+    "I-DATE": 6,
+    "I-LOCATION": 4,
+    "I-PERSON": 2,
+    "I-PHONE_NUMBER": 10,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c16ae094f49b3f02188d54f37a82e57d836f605ef09ffea628bd5649b5ce7e
+size 496277924

notebook.ipynb

@@ -0,0 +1,103 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b71a1322",
+   "metadata": {},
+   "source": [
+    "# Get started with `tanaos-NER-v1`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "469712c1",
+   "metadata": {},
+   "source": [
+    "## Option 1 - Use through the [Artifex library](https://github.com/tanaos/artifex)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c4bfa886",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "!pip install artifex"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a8f8ec7",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from artifex import Artifex\n",
+    "\n",
+    "ta = Artifex().text_anonymization\n",
+    "\n",
+    "print(ta(\"John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567.\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "afcc6d57",
+   "metadata": {},
+   "source": [
+    "## Option 2 - Use through the Transformers library"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff2b44c9",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "!pip install transformers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ae5368d6",
+   "metadata": {
+    "vscode": {
+     "languageId": "plaintext"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from transformers import pipeline\n",
+    "\n",
+    "ta = pipeline(\n",
+    "    task=\"text-anonymization\",\n",
+    "    model=\"tanaos/tanaos-text-anonymizer-v1\",\n",
+    "    aggregation_strategy=\"first\"\n",
+    ")\n",
+    "\n",
+    "print(ta(\"John Doe lives at 123 Main St, New York. His phone number is (555) 123-4567.\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}