Update app.py

app.py

@@ -1,3 +1,4 @@
+import spaces
 import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -9,18 +10,17 @@ print("Загружаю модель...")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
-    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-    device_map="auto" if torch.cuda.is_available() else None,
+    dtype=torch.float16,
 )
-if not torch.cuda.is_available():
-    model = model.to("cpu")
+model = model.to("cuda")
 print("Модель загружена.")
 
 
+@spaces.GPU
 def respond(message, history, max_tokens, temperature, top_p):
     prompt = message.strip() + SEP
 
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
 
     with torch.no_grad():
         output = model.generate(