app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_path = "modernbert.bin"
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

tokenizer = AutoTokenizer.from_pretrained("answerdotai/ModernBERT-base")
model = AutoModelForSequenceClassification.from_pretrained("answerdotai/ModernBERT-base", num_labels=41)
model.load_state_dict(torch.load(model_path, map_location=device))
model.to(device)
model.eval()

label_mapping = {
    0: '13B', 1: '30B', 2: '65B', 3: '7B', 4: 'GLM130B', 5: 'bloom_7b',
    6: 'bloomz', 7: 'cohere', 8: 'davinci', 9: 'dolly', 10: 'dolly-v2-12b',
    11: 'flan_t5_base', 12: 'flan_t5_large', 13: 'flan_t5_small', 
    14: 'flan_t5_xl', 15: 'flan_t5_xxl', 16: 'gemma-7b-it', 17: 'gemma2-9b-it',
    18: 'gpt-3.5-turbo', 19: 'gpt-35', 20: 'gpt4', 21: 'gpt4o', 
    22: 'gpt_j', 23: 'gpt_neox', 24: 'human', 25: 'llama3-70b', 26: 'llama3-8b',
    27: 'mixtral-8x7b', 28: 'opt_1.3b', 29: 'opt_125m', 30: 'opt_13b',
    31: 'opt_2.7b', 32: 'opt_30b', 33: 'opt_350m', 34: 'opt_6.7b',
    35: 'opt_iml_30b', 36: 'opt_iml_max_1.3b', 37: 't0_11b', 38: 't0_3b',
    39: 'text-davinci-002', 40: 'text-davinci-003'
}

def classify_text(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True)
    inputs = {key: value.to(device) for key, value in inputs.items()}
    
    with torch.no_grad():
        outputs = model(**inputs)
        probabilities = torch.softmax(outputs.logits, dim=1)[0]
        predicted_class = torch.argmax(probabilities).item()
        confidence = probabilities[predicted_class].item() * 100

        if predicted_class == 24:
            prediction_label = f"✅ - The text is <span class='highlight-human'>**{confidence:.2f}%** likely <b>Human written</b>.</span>"
            model_info = ""  
        else:
            prediction_label = f"🤖 - The text is <span class='highlight-ai'>**{confidence:.2f}%** likely <b>AI generated</b>.</span>"
            model_info = f"**Identified AI Model:** {label_mapping[predicted_class]}"

    result_message = f"**Result:**\n\n{prediction_label}"
    if model_info:
        result_message += f"\n\n{model_info}"
        
    return result_message

title = "Detect AI Generated Texts!"
description = """

---

Detect AI-generated texts with precision using the new **ModernBERT** model, fine-tuned for machine-generated text detection which capable of identifying 40 different models.

- 🤖 - **Identify AI Models:** Reveals which LLM generated the text if detected as AI.  
- ✅ - **Human Verification:** Marks human-written text with a green checkmark.  

**Note:** The longer the text, the better the detection accuracy.

---

"""

bottom_text = "**AI detection tool by SzegedAI**"

iface = gr.Blocks(css="""

    @import url('https://fonts.googleapis.com/css2?family=Roboto+Mono:wght@400;700&display=swap');

    #text_input_box {
        border-radius: 10px;
        border: 2px solid #4CAF50;
        font-size: 18px;
        padding: 15px;
        margin-bottom: 20px;
        width: 60%;
        box-sizing: border-box;
        margin: auto;
        background-color: #1E1E2F;
    }

    #result_output_box {
        border-radius: 10px;
        border: 2px solid #4CAF50;
        font-size: 18px;
        padding: 15px;
        background-color: #2E2E3F;
        margin-top: 20px;
        width: 40%;
        box-sizing: border-box;
        text-align: center;
        margin: auto;
    }

    .form.svelte-633qhp {
        background: none;
        border: none;
        box-shadow: none;
    }

    body {
        background: #1E1E2F;
        color: #E1E1E6;
        font-family: 'Roboto Mono', sans-serif;
        padding: 20px;
        display: block;
        justify-content: center;
        align-items: center;
        height: 100vh;
	overflow-y: auto;
    }
    .gradio-container {
        border: 1px solid #4CAF50;
        border-radius: 15px;
        padding: 30px;
        box-shadow: 0px 0px 10px rgba(0,255,0,0.6);
        max-width: 600px;
        margin: auto;
	overflow-y: auto;
    }
    h1 {
        text-align: center;
        font-size: 28px;
        font-weight: bold;
	margin-bottom: 30px;
    }
    h2 {
        text-align: left;
        font-size: 28px;
    }
    .highlight-human {
        color: #4CAF50;
        font-weight: bold;
        background: rgba(76, 175, 80, 0.2);
        padding: 5px;
        border-radius: 8px;
    }
    .highlight-ai {
        color: #FF5733;
        font-weight: bold;
        background: rgba(255, 87, 51, 0.2);
        padding: 5px;
        border-radius: 8px;
    }
    #bottom_text {
        text-align: center;
        margin-top: 50px;
        font-weight: bold;
        font-size: 20px;
        color: #E1E1E6;
    }
""")

with iface:
    gr.Markdown(f"# {title}")
    gr.Markdown(description)
    text_input = gr.Textbox(label="", placeholder="Type or paste your content here...", elem_id="text_input_box", lines=5)
    result_output = gr.Markdown("**Results will appear here...**", elem_id="result_output_box")
    text_input.change(classify_text, inputs=text_input, outputs=result_output)
    gr.Markdown(bottom_text, elem_id="bottom_text")

iface.launch(share=True)