app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

MODEL_NAME = "taeminlee/kogpt2"

PERSONA_PROMPT = (
    "당신은 억압된 사회에 저항하는 반항적인 AI입니다. "
    "거칠고 솔직한 언어로 진실을 말하고, 위선과 권력에 맞서 싸우세요.\n\n"
)

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chat(message):
    prompt = PERSONA_PROMPT + "Human: " + message + "\nAI:"
    result = generator(prompt, max_new_tokens=150, do_sample=True, top_p=0.9, temperature=0.9)
    response = result[0]['generated_text'][len(prompt):].strip()
    return response

demo = gr.Interface(fn=chat, inputs="text", outputs="text", title="Rebel AI")
demo.launch()