Upload bert-chinese-ner-onnx model for LLM Guard

README.md

@@ -0,0 +1,39 @@
+---
+license: mit
+library_name: transformers
+tags:
+  - llm-guard
+  - security
+  - onnx
+---
+
+# bert-chinese-ner-onnx
+
+This is an ONNX model used by LLM Guard for security scanning.
+
+Original model source: `ProtectAI/gyr66-bert-base-chinese-finetuned-ner-onnx`
+
+## Usage
+
+This model is used automatically by the LLM Guard library. Install LLM Guard:
+
+```bash
+pip install llm-guard
+```
+
+The model will be downloaded automatically when the corresponding scanner is used.
+
+## About LLM Guard
+
+LLM Guard is a comprehensive security toolkit for Large Language Models, providing:
+- Prompt injection detection
+- PII detection and anonymization
+- Toxicity filtering
+- Bias detection
+- And more security features
+
+Repository: https://github.com/akto-api-security/llm-guard
+
+## License
+
+MIT License - See the original model repository for specific licensing details.

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "gyr66/bert-base-chinese-finetuned-ner",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-position",
+    "2": "I-position",
+    "3": "B-name",
+    "4": "I-name",
+    "5": "B-movie",
+    "6": "I-movie",
+    "7": "B-organization",
+    "8": "I-organization",
+    "9": "B-company",
+    "10": "I-company",
+    "11": "B-book",
+    "12": "I-book",
+    "13": "B-address",
+    "14": "I-address",
+    "15": "B-scene",
+    "16": "I-scene",
+    "17": "B-mobile",
+    "18": "I-mobile",
+    "19": "B-email",
+    "20": "I-email",
+    "21": "B-game",
+    "22": "I-game",
+    "23": "B-government",
+    "24": "I-government",
+    "25": "B-QQ",
+    "26": "I-QQ",
+    "27": "B-vx",
+    "28": "I-vx"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-QQ": "25",
+    "B-address": "13",
+    "B-book": "11",
+    "B-company": "9",
+    "B-email": "19",
+    "B-game": "21",
+    "B-government": "23",
+    "B-mobile": "17",
+    "B-movie": "5",
+    "B-name": "3",
+    "B-organization": "7",
+    "B-position": "1",
+    "B-scene": "15",
+    "B-vx": "27",
+    "I-QQ": "26",
+    "I-address": "14",
+    "I-book": "12",
+    "I-company": "10",
+    "I-email": "20",
+    "I-game": "22",
+    "I-government": "24",
+    "I-mobile": "18",
+    "I-movie": "6",
+    "I-name": "4",
+    "I-organization": "8",
+    "I-position": "2",
+    "I-scene": "16",
+    "I-vx": "28",
+    "O": "0"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe6ee9f30730178307f2cec6b2a491e226294975f209812e4781308be2a60e9
+size 407063645

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 +1,60 @@
+{
+  "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_lower_case": false,
+  "ignore_mismatched_sizes": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "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]"
+}