Update app.py

app.py

@@ -13,6 +13,7 @@ def load_model(repo_name):
     tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
     generator_conf = GenerationConfig.from_pretrained(repo_name)
     model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True, torch_dtype=torch.bfloat16)
+    model.to('cuda')
     return tokenizer, generator_conf, model
 
 tokenizer, generator_conf, model = load_model(REPO_NAME)