Upload toxic-roberta-onnx model for LLM Guard

README.md

@@ -0,0 +1,39 @@
+---
+license: mit
+library_name: transformers
+tags:
+  - llm-guard
+  - security
+  - onnx
+---
+
+# toxic-roberta-onnx
+
+This is an ONNX model used by LLM Guard for security scanning.
+
+Original model source: `ProtectAI/unbiased-toxic-roberta-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 +1,65 @@
+{
+  "_name_or_path": "unitary/unbiased-toxic-roberta",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "function_to_apply": "sigmoid",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "toxicity",
+    "1": "severe_toxicity",
+    "2": "obscene",
+    "3": "identity_attack",
+    "4": "insult",
+    "5": "threat",
+    "6": "sexual_explicit",
+    "7": "male",
+    "8": "female",
+    "9": "homosexual_gay_or_lesbian",
+    "10": "christian",
+    "11": "jewish",
+    "12": "muslim",
+    "13": "black",
+    "14": "white",
+    "15": "psychiatric_or_mental_illness"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "black": 13,
+    "christian": 10,
+    "female": 8,
+    "homosexual_gay_or_lesbian": 9,
+    "identity_attack": 3,
+    "insult": 4,
+    "jewish": 11,
+    "male": 7,
+    "muslim": 12,
+    "obscene": 2,
+    "psychiatric_or_mental_illness": 15,
+    "severe_toxicity": 1,
+    "sexual_explicit": 6,
+    "threat": 5,
+    "toxicity": 0,
+    "white": 14
+  },
+  "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",
+  "problem_type": "multi_label_classification",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33a3b5b9c74c6c00129fcc6d0a2ed78856eb63eb83684a943e6ae890003dbf2
+size 498913665

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2747e65b2db4071959a2c4c645dd54bf9ff910b4fef66929f5fd450c4976a280
+size 125538880

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": true,
+    "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 +1,57 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}