change to qwen2 0.5B fp16

app.py

@@ -1,10 +1,10 @@
 import gradio as gr
 from llama_cpp import Llama
 
-model = "Qwen/Qwen2-7B-Instruct-GGUF"
+model = "Qwen/Qwen2-0.5B-Instruct-GGUF"
 llm = Llama.from_pretrained(
     repo_id=model,
-    filename="qwen2-7b-instruct-q4_k_m.gguf",
+    filename="qwen2-0_5b-instruct-fp16.gguf",
     verbose=True,
     use_mmap=False,
     use_mlock=True,