Upload AI vs Human Text Detector model

README.md

@@ -0,0 +1,63 @@
+---
+language: en
+license: mit
+library: pytorch
+datasets:
+- custom
+tags:
+- text-classification
+- ai-text-detection
+- roberta
+widget:
+- text: "The impact of artificial intelligence on modern society has been profound and far-reaching, transforming industries and reshaping how we live and work."
+- text: "The quantum mechanics principle demonstrates that particles can exist in multiple states simultaneously until observed, a phenomenon known as superposition."
+---
+
+# AI vs Human Text Detector
+
+This model can detect whether a text was written by a human or generated by AI.
+
+## Model description
+
+This AI text detector is built by fine-tuning RoBERTa-base on a dataset containing both human-written and AI-generated text samples.
+The model has been trained with data augmentation techniques to improve its robustness.
+
+## Performance
+
+The model achieves the following performance on the validation set:
+- Accuracy: 0.9999
+- F1-Score (Human): 1.0000
+- F1-Score (AI): 0.9999
+
+## How to use
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+model_name = "Abuzaid01/Ai_Human_Text_Detector"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+# Prepare text for classification
+text = "Your text to classify goes here."
+inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512, padding=True)
+
+# Run inference
+with torch.no_grad():
+    outputs = model(**inputs)
+    logits = outputs.logits
+    
+# Get the predicted class and probabilities
+probabilities = torch.nn.functional.softmax(logits, dim=1)
+predicted_class_idx = torch.argmax(probabilities, dim=1).item()
+confidence = probabilities[0][predicted_class_idx].item()
+
+# Map class index to label
+labels = ["Human-written", "AI-generated"]
+predicted_label = labels[predicted_class_idx]
+
+print(f"Prediction: {predicted_label}")
+print(f"Confidence: {confidence:.4f}")
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

inference.py

@@ -0,0 +1,35 @@
+
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+def classify_text(text, model_path=None):
+    # Load model and tokenizer
+    model_path = model_path or "."
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(model_path)
+    
+    # Prepare the text for the model
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512, padding=True)
+    
+    # Run inference
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        
+    # Get the predicted class and probabilities
+    probabilities = torch.nn.functional.softmax(logits, dim=1)
+    predicted_class_idx = torch.argmax(probabilities, dim=1).item()
+    confidence = probabilities[0][predicted_class_idx].item()
+    
+    # Map class index to label
+    labels = ["Human-written", "AI-generated"]
+    predicted_label = labels[predicted_class_idx]
+    
+    return predicted_label, confidence
+
+if __name__ == "__main__":
+    # Example usage
+    text = "Enter your text here to test if it's AI-generated or human-written."
+    result, confidence = classify_text(text)
+    print(f"This text appears to be: {result}")
+    print(f"Confidence: {confidence:.4f}")

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f89a54999e6ab4b9a153081aaf5afc1df7776b52f1501ee9b275770ac43931
+size 498612824

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}