app.py

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

model_path = "cody82/unitrip"  # путь к локальной модели

config = AutoConfig.from_pretrained(model_path, local_files_only=True)
tokenizer = AutoTokenizer.from_pretrained(model_path, local_files_only=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    config=config,
    local_files_only=True,
    torch_dtype=torch.float32,
    device_map="auto" if torch.cuda.is_available() else None,
)

system_message = "Ты — умный помощник по Университету Иннополис."

def respond(message, history=None):
    if history is None:
        history = []

    prompt = f"{system_message}\nUser: {message}\nAssistant:"

    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=128,
            do_sample=False,
            pad_token_id=tokenizer.eos_token_id,
            eos_token_id=tokenizer.eos_token_id,
            use_cache=True,
        )

    generated_tokens = outputs[0][inputs["input_ids"].shape[1]:]
    answer = tokenizer.decode(generated_tokens, skip_special_tokens=True).strip()

    history.append((message, answer))
    return history

chat = gr.ChatInterface(fn=respond, title="Innopolis Assistant")
chat.launch()