Update app.py

app.py

@@ -1,20 +1,19 @@
 import torch
+import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "cody82/unitrip"  # или другой ID модели с Huggingface
-
-tokenizer = AutoTokenizer.from_pretrained(model_id)  # без local_files_only
-model = AutoModelForCausalLM.from_pretrained(model_id)  # без local_files_only
+model_id = "cody82/unitrip"
 
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
 
 system_message = "Ты — умный помощник по Университету Иннополис."
 
-while True:
-    user_input = input("🧑 Вопрос: ").strip()
-    if user_input.lower() in ["exit", "выход", "quit"]:
-        break
+def respond(user_input, history=None):
+    if history is None:
+        history = []
 
     prompt = f"{system_message}\nUser: {user_input}\nAssistant:"
 
@@ -32,4 +31,8 @@ while True:
 
     generated = outputs[0][inputs["input_ids"].shape[1]:]
     answer = tokenizer.decode(generated, skip_special_tokens=True)
-    print(f"🤖 Ответ: {answer.strip()}\n")
+    history.append((user_input, answer.strip()))
+    return history, history
+
+iface = gr.ChatInterface(fn=respond, title="Innopolis Q&A")
+iface.launch()