Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,17 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+Copyright 2026 SAGEA / Basab Jha
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

README.md

@@ -1,3 +1,87 @@
----
-license: apache-2.0
----
+# Tegmen
+
+A high-performance on-premise PII detection and masking solution
+
+## Overview
+
+Tegmen is a production-ready token classification system designed for identifying and masking personally identifiable information (PII) in text data. Built for high-throughput data sanitization workflows, it offers on-premise deployment capabilities with enterprise-grade performance.
+
+## Key Features
+
+- **On-Premise Deployment**: Run entirely within your infrastructure
+- **Lightweight Architecture**: Optimized for edge deployment
+- **Fine-Tunable**: Easily adapt to your specific data distributions
+- **Long Context Support**: Process documents up to 128,000 tokens
+- **Configurable Detection**: Tune precision/recall tradeoffs
+
+## Supported PII Categories
+
+The model detects 8 categories of sensitive information:
+
+| Category | Description |
+|----------|-------------|
+| `account_number` | Financial account identifiers |
+| `private_address` | Physical and mailing addresses |
+| `private_email` | Email addresses |
+| `private_person` | Personal names |
+| `private_phone` | Phone numbers |
+| `private_url` | URLs and web addresses |
+| `private_date` | Birth dates and personal dates |
+| `secret` | API keys, passwords, credentials |
+
+## Installation
+
+```bash
+pip install transformers torch
+```
+
+## Quick Start
+
+### Using the Pipeline API
+
+```python
+from transformers import pipeline
+
+detector = pipeline("token-classification", model="comethrusws/tegmen", aggregation_strategy="simple")
+
+text = "Contact John Smith at john.smith@email.com"
+results = detector(text)
+
+for item in results:
+    print(f"Found: {item['word']} ({item['entity_group']})")
+```
+
+### Using the Model Directly
+
+```python
+import torch
+from transformers import AutoModelForTokenClassification, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("comethrusws/tegmen")
+model = AutoModelForTokenClassification.from_pretrained("comethrusws/tegmen")
+
+text = "My name is Alice and my email is alice@example.com"
+inputs = tokenizer(text, return_tensors="pt")
+
+with torch.no_grad():
+    outputs = model(**inputs)
+
+predictions = outputs.logits.argmax(dim=-1)
+labels = [model.config.id2label[p.item()] for p in predictions[0]]
+print(labels)
+```
+
+## Performance Specifications
+
+- **Architecture**: Transformer encoder
+- **Parameters**: 1.5B total / 50M active
+- **Context Window**: 128,000 tokens
+- **Output Format**: BIOES span tagging
+
+## License
+
+Apache License 2.0
+
+## Support
+
+For enterprise support, contact SAGEA.

config.json

@@ -0,0 +1,121 @@
+{
+  "architectures": [
+    "OpenAIPrivacyFilterForTokenClassification"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_dropout": 0.0,
+  "default_n_ctx": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 199999,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 640,
+  "id2label": {
+    "0": "O",
+    "1": "B-account_number",
+    "2": "I-account_number",
+    "3": "E-account_number",
+    "4": "S-account_number",
+    "5": "B-private_address",
+    "6": "I-private_address",
+    "7": "E-private_address",
+    "8": "S-private_address",
+    "9": "B-private_date",
+    "10": "I-private_date",
+    "11": "E-private_date",
+    "12": "S-private_date",
+    "13": "B-private_email",
+    "14": "I-private_email",
+    "15": "E-private_email",
+    "16": "S-private_email",
+    "17": "B-private_person",
+    "18": "I-private_person",
+    "19": "E-private_person",
+    "20": "S-private_person",
+    "21": "B-private_phone",
+    "22": "I-private_phone",
+    "23": "E-private_phone",
+    "24": "S-private_phone",
+    "25": "B-private_url",
+    "26": "I-private_url",
+    "27": "E-private_url",
+    "28": "S-private_url",
+    "29": "B-secret",
+    "30": "I-secret",
+    "31": "E-secret",
+    "32": "S-secret"
+  },
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 640,
+  "label2id": {
+    "B-account_number": 1,
+    "B-private_address": 5,
+    "B-private_date": 9,
+    "B-private_email": 13,
+    "B-private_person": 17,
+    "B-private_phone": 21,
+    "B-private_url": 25,
+    "B-secret": 29,
+    "E-account_number": 3,
+    "E-private_address": 7,
+    "E-private_date": 11,
+    "E-private_email": 15,
+    "E-private_person": 19,
+    "E-private_phone": 23,
+    "E-private_url": 27,
+    "E-secret": 31,
+    "I-account_number": 2,
+    "I-private_address": 6,
+    "I-private_date": 10,
+    "I-private_email": 14,
+    "I-private_person": 18,
+    "I-private_phone": 22,
+    "I-private_url": 26,
+    "I-secret": 30,
+    "O": 0,
+    "S-account_number": 4,
+    "S-private_address": 8,
+    "S-private_date": 12,
+    "S-private_email": 16,
+    "S-private_person": 20,
+    "S-private_phone": 24,
+    "S-private_url": 28,
+    "S-secret": 32
+  },
+  "max_position_embeddings": 131072,
+  "model_type": "pii-detector",
+  "num_attention_heads": 14,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_theta": 150000.0,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": 128,
+  "tie_word_embeddings": false,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model": 1,
+      "model.onnx": 3,
+      "model_fp16.onnx": 2
+    }
+  },
+  "transformers_version": "5.10.1",
+  "use_cache": true,
+  "vocab_size": 200064,
+  "_name_or_path": "comethrusws/tegmen"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f66b87650b988b04e218285f9fe3df6a4943416b6ffa8171f07bc56cf12a9d
+size 2798989498

model_card.md

@@ -0,0 +1,27 @@
+---
+language: en
+license: apache-2.0
+library_name: transformers
+tags:
+- token-classification
+- pii-detection
+- privacy
+---
+
+# Tegmen Model Card
+
+## Model Details
+
+**Model Type:** Bidirectional token classification
+**Parameters:** 1.5B total / 50M active
+**Context Length:** 128,000 tokens
+
+## Intended Use
+
+- Data sanitization workflows
+- Compliance aid for privacy regulations
+- On-premise PII detection
+
+## Limitations
+
+This tool should be used as part of a comprehensive privacy-by-design approach.

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "<|endoftext|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend"
+}