ONNX-converted version of the model

We decided to swap the existing model for the [Code Scanner](https://llm-guard.com/input_scanners/code/) in [llm-guard](https://github.com/laiyer-ai/llm-guard) with your model. Our tests show much better accuracy compared to the HuggingFace's one.

To have faster inference, we use ONNX models converted using Optimum from HuggingFace.

Example of the repo with ONNX built-in: https://huggingface.co/laiyer/deberta-v3-base-prompt-injection

onnx/config.json

@@ -0,0 +1,84 @@
+{
+  "_name_or_path": "philomath-1209/programming-language-identification",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Scala",
+    "1": "JavaScript",
+    "2": "COBOL",
+    "3": "ARM Assembly",
+    "4": "R",
+    "5": "Lua",
+    "6": "C++",
+    "7": "Visual Basic .NET",
+    "8": "Go",
+    "9": "Erlang",
+    "10": "C#",
+    "11": "Rust",
+    "12": "Ruby",
+    "13": "Swift",
+    "14": "Mathematica/Wolfram Language",
+    "15": "PHP",
+    "16": "Fortran",
+    "17": "AppleScript",
+    "18": "Pascal",
+    "19": "Java",
+    "20": "PowerShell",
+    "21": "Python",
+    "22": "C",
+    "23": "Perl",
+    "24": "Kotlin",
+    "25": "jq"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ARM Assembly": 3,
+    "AppleScript": 17,
+    "C": 22,
+    "C#": 10,
+    "C++": 6,
+    "COBOL": 2,
+    "Erlang": 9,
+    "Fortran": 16,
+    "Go": 8,
+    "Java": 19,
+    "JavaScript": 1,
+    "Kotlin": 24,
+    "Lua": 5,
+    "Mathematica/Wolfram Language": 14,
+    "PHP": 15,
+    "Pascal": 18,
+    "Perl": 23,
+    "PowerShell": 20,
+    "Python": 21,
+    "R": 4,
+    "Ruby": 12,
+    "Rust": 11,
+    "Scala": 0,
+    "Swift": 13,
+    "Visual Basic .NET": 7,
+    "jq": 25
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d9bf25fe9933c20db353c90fd5295554d4c02f06f6f052d8ec1ef87c623e0bf
+size 334030262

onnx/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": false,
+    "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
+  }
+}

onnx/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "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>",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}