Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+base_model: broadfield-dev/bert-mini-ner-pii-training-tuned-12270113
+library_name: transformers
+tags:
+- onnx
+- onnxruntime
+- tokenizers
+- optimum
+- token-classification
+language: en
+pipeline_tag: token-classification
+---
+
+# ONNX Export: broadfield-dev/bert-mini-ner-pii-training-tuned-12270113
+
+This is a version of [broadfield-dev/bert-mini-ner-pii-training-tuned-12270113](https://huggingface.co/broadfield-dev/bert-mini-ner-pii-training-tuned-12270113) that has been converted to ONNX and optimized.
+
+## Model Details
+- **Base Model:** `broadfield-dev/bert-mini-ner-pii-training-tuned-12270113`
+- **Task:** `token-classification`
+- **Opset Version:** `17`
+- **Optimization:** `FP32 (No Quantization)`
+
+## Usage
+
+### Installation
+For a lightweight mobile/serverless setup, you only need `onnxruntime` and `tokenizers`.
+```bash
+pip install onnxruntime tokenizers
+```
+
+### Python Example
+```python
+
+from tokenizers import Tokenizer
+import onnxruntime as ort
+import numpy as np
+
+# 1. Load the lightweight tokenizer (No Transformers dependency needed)
+tokenizer = Tokenizer.from_pretrained("broadfield-dev/bert-mini-ner-pii-training-tuned-12270113-onnx")
+
+# 2. Load the ONNX model
+session = ort.InferenceSession("model.onnx")
+
+# 3. Preprocess (Simple text encoding)
+text = "Run inference on mobile!"
+encoding = tokenizer.encode(text)
+
+# Prepare inputs (Exact names vary by model, usually input_ids + attention_mask)
+inputs = {
+    "input_ids": np.array([encoding.ids], dtype=np.int64),
+    "attention_mask": np.array([encoding.attention_mask], dtype=np.int64)
+}
+
+# 4. Run Inference
+outputs = session.run(None, inputs)
+print("Output logits shape:", outputs[0].shape)
+
+```
+
+## About this Export
+This model was exported using [Optimum](https://huggingface.co/docs/optimum/index). 
+It includes the `FP32 (No Quantization)` quantization settings and a pre-compiled `tokenizer.json` for fast loading.

config.json

@@ -0,0 +1,64 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "ACCOUNTNUM",
+    "1": "BUILDINGNUM",
+    "2": "CITY",
+    "3": "CREDITCARDNUMBER",
+    "4": "DATEOFBIRTH",
+    "5": "DRIVERLICENSENUM",
+    "6": "EMAIL",
+    "7": "GIVENNAME",
+    "8": "IDCARDNUM",
+    "9": "O",
+    "10": "PASSWORD",
+    "11": "SOCIALNUM",
+    "12": "STREET",
+    "13": "SURNAME",
+    "14": "TAXNUM",
+    "15": "TELEPHONENUM",
+    "16": "USERNAME",
+    "17": "ZIPCODE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "ACCOUNTNUM": 0,
+    "BUILDINGNUM": 1,
+    "CITY": 2,
+    "CREDITCARDNUMBER": 3,
+    "DATEOFBIRTH": 4,
+    "DRIVERLICENSENUM": 5,
+    "EMAIL": 6,
+    "GIVENNAME": 7,
+    "IDCARDNUM": 8,
+    "O": 9,
+    "PASSWORD": 10,
+    "SOCIALNUM": 11,
+    "STREET": 12,
+    "SURNAME": 13,
+    "TAXNUM": 14,
+    "TELEPHONENUM": 15,
+    "USERNAME": 16,
+    "ZIPCODE": 17
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f0b502555bd277bf4ef2c35ec7c15bba547d49d6a938e569662890d36e742b
+size 44514088

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}