app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load DeepSeek model (replace with your actual model name)
MODEL_NAME = "deepseek-ai/deepseek-coder-6.7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)

def summarize(text):
    # Customize your summarization prompt
    prompt = f"Summarize this text concisely:\n\n{text}\n\nSummary:"
    
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=500)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Text Summarizer")
    with gr.Row():
        with gr.Column():
            input_text = gr.Textbox(label="Input Text", lines=10)
            submit_btn = gr.Button("Summarize")
        with gr.Column():
            output_text = gr.Textbox(label="Summary", lines=10)
    
    submit_btn.click(fn=summarize, inputs=input_text, outputs=output_text)

# Launch with API mode enabled
demo.launch(api_mode=True, server_name="0.0.0.0", server_port=7860)