import gradio as gr
from transformers import AutoTokenizer, GPTJForCausalLM

model_name = "rycont/kakaobrain__kogpt-6b-8bit"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = GPTJForCausalLM.from_pretrained(model_name)

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(inputs['input_ids'], max_new_tokens=50)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

iface = gr.Interface(
    fn=generate_response,
    inputs="text",
    outputs="text",
    title="KoGPT-6B Chatbot",
    description="Enter a prompt and the model will generate a response."
)

if __name__ == "__main__":
    iface.launch()