Upload lora_pii_detector_bert-base-uncased_model LoRA model

README.md

@@ -0,0 +1,96 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- lora
+- semantic-router
+- pii-classification
+- text-classification
+- candle
+- rust
+language:
+- en
+pipeline_tag: text-classification
+library_name: candle
+---
+
+# lora_pii_detector_bert-base-uncased_model
+
+## Model Description
+
+This is a LoRA (Low-Rank Adaptation) fine-tuned model based on **bert-base-uncased** for PII Detection - Detects personally identifiable information in text using token classification.
+
+This model is part of the [semantic-router](https://github.com/vllm-project/semantic-router) project and is optimized for use with the Candle framework in Rust.
+
+## Model Details
+
+- **Base Model**: bert-base-uncased
+- **Task**: Pii Classification
+- **Framework**: Candle (Rust)
+- **Model Size**: ~416MB
+- **LoRA Rank**: 16
+- **LoRA Alpha**: 32
+- **Target Modules**: attention.self.query, attention.self.value, attention.output.dense, intermediate.dense, output.dense
+
+## Usage
+
+### With semantic-router (Recommended)
+
+```python
+from semantic_router import SemanticRouter
+
+# The model will be automatically downloaded and used
+router = SemanticRouter()
+results = router.classify_batch(["Your text here"])
+```
+
+### With Candle (Rust)
+
+```rust
+use candle_core::{Device, Tensor};
+use candle_transformers::models::bert::BertModel;
+
+// Load the model using Candle
+let device = Device::Cpu;
+let model = BertModel::load(&device, &config, &weights)?;
+```
+
+## Training Details
+
+This model was fine-tuned using LoRA (Low-Rank Adaptation) technique:
+
+- **Rank**: 16
+- **Alpha**: 32 
+- **Dropout**: 0.1
+- **Target Modules**: attention.self.query, attention.self.value, attention.output.dense, intermediate.dense, output.dense
+
+## Performance
+
+PII Detection - Detects personally identifiable information in text using token classification
+
+For detailed performance metrics, see the [training results](https://github.com/vllm-project/semantic-router/blob/main/training-result.md).
+
+## Files
+
+- `model.safetensors`: LoRA adapter weights
+- `config.json`: Model configuration
+- `lora_config.json`: LoRA-specific configuration
+- `tokenizer.json`: Tokenizer configuration
+- `label_mapping.json`: Label mappings for classification
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{semantic-router-lora,
+  title={LoRA Fine-tuned Models for Semantic Router},
+  author={Semantic Router Team},
+  year={2025},
+  url={https://github.com/vllm-project/semantic-router}
+}
+```
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,99 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-AGE",
+    "2": "I-AGE",
+    "3": "B-CREDIT_CARD",
+    "4": "I-CREDIT_CARD",
+    "5": "B-DATE_TIME",
+    "6": "I-DATE_TIME",
+    "7": "B-DOMAIN_NAME",
+    "8": "I-DOMAIN_NAME",
+    "9": "B-EMAIL_ADDRESS",
+    "10": "I-EMAIL_ADDRESS",
+    "11": "B-GPE",
+    "12": "I-GPE",
+    "13": "B-IBAN_CODE",
+    "14": "I-IBAN_CODE",
+    "15": "B-IP_ADDRESS",
+    "16": "I-IP_ADDRESS",
+    "17": "B-NRP",
+    "18": "I-NRP",
+    "19": "B-ORGANIZATION",
+    "20": "I-ORGANIZATION",
+    "21": "B-PERSON",
+    "22": "I-PERSON",
+    "23": "B-PHONE_NUMBER",
+    "24": "I-PHONE_NUMBER",
+    "25": "B-STREET_ADDRESS",
+    "26": "I-STREET_ADDRESS",
+    "27": "B-TITLE",
+    "28": "I-TITLE",
+    "29": "B-US_DRIVER_LICENSE",
+    "30": "I-US_DRIVER_LICENSE",
+    "31": "B-US_SSN",
+    "32": "I-US_SSN",
+    "33": "B-ZIP_CODE",
+    "34": "I-ZIP_CODE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "B-AGE": 1,
+    "I-AGE": 2,
+    "B-CREDIT_CARD": 3,
+    "I-CREDIT_CARD": 4,
+    "B-DATE_TIME": 5,
+    "I-DATE_TIME": 6,
+    "B-DOMAIN_NAME": 7,
+    "I-DOMAIN_NAME": 8,
+    "B-EMAIL_ADDRESS": 9,
+    "I-EMAIL_ADDRESS": 10,
+    "B-GPE": 11,
+    "I-GPE": 12,
+    "B-IBAN_CODE": 13,
+    "I-IBAN_CODE": 14,
+    "B-IP_ADDRESS": 15,
+    "I-IP_ADDRESS": 16,
+    "B-NRP": 17,
+    "I-NRP": 18,
+    "B-ORGANIZATION": 19,
+    "I-ORGANIZATION": 20,
+    "B-PERSON": 21,
+    "I-PERSON": 22,
+    "B-PHONE_NUMBER": 23,
+    "I-PHONE_NUMBER": 24,
+    "B-STREET_ADDRESS": 25,
+    "I-STREET_ADDRESS": 26,
+    "B-TITLE": 27,
+    "I-TITLE": 28,
+    "B-US_DRIVER_LICENSE": 29,
+    "I-US_DRIVER_LICENSE": 30,
+    "B-US_SSN": 31,
+    "I-US_SSN": 32,
+    "B-ZIP_CODE": 33,
+    "I-ZIP_CODE": 34
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

label_mapping.json

@@ -0,0 +1 @@
+{"label_to_id": {"O": 0, "B-AGE": 1, "I-AGE": 2, "B-CREDIT_CARD": 3, "I-CREDIT_CARD": 4, "B-DATE_TIME": 5, "I-DATE_TIME": 6, "B-DOMAIN_NAME": 7, "I-DOMAIN_NAME": 8, "B-EMAIL_ADDRESS": 9, "I-EMAIL_ADDRESS": 10, "B-GPE": 11, "I-GPE": 12, "B-IBAN_CODE": 13, "I-IBAN_CODE": 14, "B-IP_ADDRESS": 15, "I-IP_ADDRESS": 16, "B-NRP": 17, "I-NRP": 18, "B-ORGANIZATION": 19, "I-ORGANIZATION": 20, "B-PERSON": 21, "I-PERSON": 22, "B-PHONE_NUMBER": 23, "I-PHONE_NUMBER": 24, "B-STREET_ADDRESS": 25, "I-STREET_ADDRESS": 26, "B-TITLE": 27, "I-TITLE": 28, "B-US_DRIVER_LICENSE": 29, "I-US_DRIVER_LICENSE": 30, "B-US_SSN": 31, "I-US_SSN": 32, "B-ZIP_CODE": 33, "I-ZIP_CODE": 34}, "id_to_label": {"0": "O", "1": "B-AGE", "2": "I-AGE", "3": "B-CREDIT_CARD", "4": "I-CREDIT_CARD", "5": "B-DATE_TIME", "6": "I-DATE_TIME", "7": "B-DOMAIN_NAME", "8": "I-DOMAIN_NAME", "9": "B-EMAIL_ADDRESS", "10": "I-EMAIL_ADDRESS", "11": "B-GPE", "12": "I-GPE", "13": "B-IBAN_CODE", "14": "I-IBAN_CODE", "15": "B-IP_ADDRESS", "16": "I-IP_ADDRESS", "17": "B-NRP", "18": "I-NRP", "19": "B-ORGANIZATION", "20": "I-ORGANIZATION", "21": "B-PERSON", "22": "I-PERSON", "23": "B-PHONE_NUMBER", "24": "I-PHONE_NUMBER", "25": "B-STREET_ADDRESS", "26": "I-STREET_ADDRESS", "27": "B-TITLE", "28": "I-TITLE", "29": "B-US_DRIVER_LICENSE", "30": "I-US_DRIVER_LICENSE", "31": "B-US_SSN", "32": "I-US_SSN", "33": "B-ZIP_CODE", "34": "I-ZIP_CODE"}}

lora_config.json

@@ -0,0 +1 @@
+{"rank": 16, "alpha": 32, "dropout": 0.1, "target_modules": ["attention.self.query", "attention.self.value", "attention.output.dense", "intermediate.dense", "output.dense"]}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68536cf27db976e89cdf1dbb5b36f409932be494dd180020580b9d008d907605
+size 435697596

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}