app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

# Initialize model and tokenizer
model_name = "deepseek-ai/deepseek-model"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

def summarize_text(text, max_length=150, min_length=50):
    """
    Summarize the input text using the DeepSeek model
    """
    # Prepare the input
    inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)
    
    # Generate summary
    summary_ids = model.generate(
        inputs["input_ids"],
        max_length=max_length,
        min_length=min_length,
        length_penalty=2.0,
        num_beams=4,
        early_stopping=True
    )
    
    # Decode and return the summary
    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
    return summary

# Create the Gradio interface
iface = gr.Interface(
    fn=summarize_text,
    inputs=[
        gr.Textbox(label="Input Text", placeholder="Enter the text you want to summarize...", lines=10),
        gr.Slider(minimum=50, maximum=300, value=150, label="Maximum Summary Length"),
        gr.Slider(minimum=30, maximum=150, value=50, label="Minimum Summary Length")
    ],
    outputs=gr.Textbox(label="Summary"),
    title="Text Summarization with DeepSeek",
    description="Enter your text and get an AI-generated summary using the DeepSeek model.",
    examples=[
        ["The artificial intelligence revolution has transformed various sectors of the economy, from healthcare to finance. Machine learning algorithms are now capable of detecting diseases, predicting market trends, and automating complex tasks. This technological advancement has raised both excitement about the potential benefits and concerns about job displacement and ethical implications."],
    ]
)

iface.launch()