fix: change to qwen2

app.py

@@ -1,8 +1,17 @@
 import gradio as gr
 from llama_cpp import Llama
 
-model = "Qwen/Qwen1.5-0.5B-Chat-GGUF"
-llm = Llama.from_pretrained(repo_id=model, filename="*q8_0.gguf", verbose=True)
+model = "Qwen/Qwen2-0.5B-Instruct-GGUF"
+llm = Llama.from_pretrained(
+    repo_id=model,
+    filename="*q8_0.gguf",
+    verbose=True,
+    use_mmap=False,
+    use_mlock=True,
+    n_threads=2,
+    n_threads_batch=2,
+    n_ctx=32000,
+)
 
 
 def respond(