Upload folder using huggingface_hub

README.md

@@ -1,3 +1,89 @@
 ---
 license: mit
+base_model: tanaos/tanaos-text-anonymizer-v1
+tags:
+  - ner
+  - pii
+  - onnx
+  - token-classification
+  - named-entity-recognition
+language:
+  - en
+library_name: onnx
 ---
+
+# RuleSentry Core PII
+
+ONNX export of [tanaos/tanaos-text-anonymizer-v1](https://huggingface.co/tanaos/tanaos-text-anonymizer-v1) for local PII detection in RuleSentry Desktop.
+
+## Attribution
+
+This model is an ONNX conversion of **tanaos-text-anonymizer-v1** by [tanaos](https://huggingface.co/tanaos).
+We converted it to ONNX format for efficient CPU/GPU inference without Python dependencies.
+
+Original model: https://huggingface.co/tanaos/tanaos-text-anonymizer-v1
+
+## Supported Entity Types
+
+| Entity | Example |
+|--------|---------|
+| PERSON | "John Douglas" |
+| LOCATION | "New York" |
+| DATE | "January 15, 2024" |
+| ADDRESS | "123 Main St, Suite 400" |
+| PHONE_NUMBER | "(555) 123-4567" |
+
+## Model Files
+
+- `model.onnx` - ONNX model (~496 MB)
+- `tokenizer.json` - Tokenizer configuration
+- `config.json` - Model configuration
+- `labels.json` - NER label mappings
+- `vocab.json` - Vocabulary
+- `merges.txt` - BPE merges
+
+## Usage
+
+This model is designed for use with [RuleSentry Desktop](https://rulesentry.com) for local, privacy-preserving document anonymization.
+
+### With ONNX Runtime (Rust)
+
+```rust
+use ort::{Session, SessionBuilder};
+
+let session = SessionBuilder::new()?
+    .with_model_from_file("model.onnx")?;
+```
+
+### With ONNX Runtime (Python)
+
+```python
+import onnxruntime as ort
+
+session = ort.InferenceSession("model.onnx")
+```
+
+## License
+
+MIT License - Same as the original model.
+
+Copyright (c) 2024 tanaos (original model)
+Copyright (c) 2024 RuleSentry (ONNX conversion)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

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": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

labels.json

@@ -0,0 +1,29 @@
+{
+  "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"
+  },
+  "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
+  },
+  "num_labels": 11
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:899cc2182bd85af25cb7d38b11500c5558e7648ffff63904996dfb21d50d0f06
+size 496476397

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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>"
+}