Try to use pipeline

app.py

@@ -2,19 +2,21 @@ import gradio as gr
 import spaces
 import torch
 
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
 model_id = "AverageBusinessUser/aidapal"
 filename = "aidapal-8k.Q4_K_M.gguf"
 
-torch_dtype = torch.float32 # could be torch.float16 or torch.bfloat16 too
 print("Downloading model")
-tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
-model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename, torch_dtype=torch_dtype)
+pipe = pipeline(task="text-generation", model_id, gguf_file=filename, device_map="auto")
+
+#torch_dtype = torch.float32 # could be torch.float16 or torch.bfloat16 too
+#tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
+#model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename, torch_dtype=torch_dtype)
 
 @spaces.GPU
 def greet(name):
-    return "Hello " + name + "!!"
+    return pipe(name)
 
 demo = gr.Interface(fn=greet, inputs="text", outputs="text")
 demo.launch()