app.py

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

model_name = "ai-forever/rugpt3large_based_on_gpt2"

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

def generate_response(user_query):
    prompt = f"Клиент: {user_query}\nБанк:"
    input_ids = tokenizer.encode(prompt, return_tensors="pt")

    with torch.no_grad():
        output_ids = model.generate(
            input_ids,
            max_new_tokens=100,
            do_sample=True,
            temperature=0.7,
            top_k=50,
            top_p=0.95,
            pad_token_id=tokenizer.eos_token_id
        )

    generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
    response = generated_text[len(prompt):].strip()
    return response

gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(lines=3, label="Введите банковский запрос"),
    outputs=gr.Textbox(lines=5, label="Ответ модели"),
    title="🤖 Русский банковский помощник",
    description="Генерация ответа на русском языке с использованием модели RuGPT-3 от AI-Forever."
).launch(share=True)