Update app.py

app.py

@@ -45,7 +45,7 @@ h1 {
 
 # Load the tokenizer and model
 tokenizer = AutoTokenizer.from_pretrained("alfredplpl/sarashina2-7b-it-test")
-model = AutoPeftModelForCausalLM.from_pretrained("alfredplpl/sarashina2-7b-it-test", device_map="auto")
+model = AutoPeftModelForCausalLM.from_pretrained("alfredplpl/sarashina2-7b-it-test", device_map="cuda")
 
 @spaces.GPU()
 def chat_llama3_8b(message: str,