app.py

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

MODEL_ID = "Kostya27/IIvanIIvanovich"   # 👈 твоя модель на HuggingFace

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    torch_dtype=torch.float32,
    device_map="auto"
)

def chat_fn(message, history):
    # собираем историю
    prompt = ""
    for user, assistant in history:
        prompt += f"<|user|>\n{user}\n<|assistant|>\n{assistant}\n"
    prompt += f"<|user|>\n{message}\n<|assistant|>"

    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

    with torch.inference_mode():
        output_ids = model.generate(
            **inputs,
            max_new_tokens=200,
            temperature=0.7,
            top_p=0.9,
            do_sample=True,
            pad_token_id=tokenizer.eos_token_id
        )

    new_tokens = output_ids[0, inputs["input_ids"].shape[1]:]
    answer = tokenizer.decode(new_tokens, skip_special_tokens=True)
    return answer

interface = gr.ChatInterface(chat_fn, title="IIvanIIvanovich Chatbot")
interface.launch()