app.py

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import gradio as gr

model_name = "cointegrated/rut5-small"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

def generate_response(prompt):
    instruction = f"Ответь кратко: {prompt.strip()}"
    input_ids = tokenizer.encode(instruction, return_tensors="pt", max_length=512, truncation=True)

    output = model.generate(
        input_ids,
        max_new_tokens=80,
        do_sample=True,
        top_p=0.9,
        temperature=0.7,
        repetition_penalty=1.2,
        eos_token_id=tokenizer.eos_token_id
    )

    response = tokenizer.decode(output[0], skip_special_tokens=True)
    return response.strip()

iface = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(label="Введите ваш вопрос"),
    outputs=gr.Textbox(label="Ответ модели"),
    title="Интерфейс ChatGPT",
    description="Пример взаимодействия с API OpenAI через Hugging Face Space"
)

iface.launch()