Update config.json

config.json

@@ -1,29 +1,129 @@
-{
-  "_name_or_path": "xlm-roberta-base",
-  "architectures": [
-    "XLMRobertaForSequenceClassification"
-  ],
-  "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,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
-}
+{
+  "model_config": {
+    "_name_or_path": "xlm-roberta-base",
+    "architectures": [
+      "XLMRobertaForSequenceClassification"
+    ],
+    "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,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 514,
+    "model_type": "xlm-roberta",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "output_past": true,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
+    "problem_type": "single_label_classification",
+    "torch_dtype": "float32",
+    "transformers_version": "4.44.2",
+    "type_vocab_size": 1,
+    "use_cache": true,
+    "vocab_size": 250002
+  },
+  
+  "training_config": {
+    "learning_rate": 2e-5,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "per_device_eval_batch_size": 16,
+    "warmup_steps": 500,
+    "weight_decay": 0.01,
+    "logging_dir": "./logs",
+    "evaluation_strategy": "epoch"
+  },
+
+  "tokenizer_config": {
+    "model_max_length": 512,
+    "padding_side": "right",
+    "truncation_side": "right",
+    "special_tokens": {
+      "pad_token": "<pad>",
+      "unk_token": "<unk>",
+      "bos_token": "<s>",
+      "eos_token": "</s>"
+    }
+  },
+
+  "inference_config": {
+    "task": "text-classification",
+    "labels": ["HUMAN", "AI"],
+    "threshold": 0.5,
+    "max_length": 512,
+    "batch_size": 32,
+    "options": {
+      "wait_for_model": true,
+      "use_cache": true
+    }
+  },
+
+  "api_config": {
+    "endpoint": "https://api-inference.huggingface.co/models/yaya36095/text-detector",
+    "headers": {
+      "Content-Type": "application/json"
+    },
+    "cors": {
+      "allow_origin": "*",
+      "allow_headers": [
+        "authorization",
+        "x-client-info",
+        "apikey",
+        "content-type"
+      ]
+    }
+  },
+
+  "model_info": {
+    "name": "text-detector",
+    "version": "1.0.0",
+    "author": "yaya36095",
+    "description": "A model for detecting AI-generated vs human-written text",
+    "license": "MIT",
+    "repository": "https://huggingface.co/yaya36095/text-detector",
+    "languages": ["multilingual"],
+    "tags": [
+      "text-classification",
+      "ai-detection",
+      "xlm-roberta"
+    ]
+  },
+
+  "environment": {
+    "framework": "transformers",
+    "framework_version": "4.44.2",
+    "python_version": ">=3.8.0",
+    "cuda_support": true,
+    "required_packages": {
+      "torch": ">=1.10.0",
+      "transformers": ">=4.44.2",
+      "numpy": ">=1.19.0"
+    }
+  },
+
+  "logging_config": {
+    "level": "INFO",
+    "format": "%(asctime)s - %(name)s - %(levelname)s - %(message)s",
+    "development_mode": {
+      "debug": true,
+      "verbose": true
+    },
+    "production_mode": {
+      "debug": false,
+      "verbose": false
+    }
+  },
+
+  "performance_metrics": {
+    "accuracy_threshold": 0.85,
+    "latency_threshold_ms": 500,
+    "max_batch_size": 64,
+    "memory_limit_mb": 4096
+  }
+}