change settings

app.py

@@ -4,9 +4,9 @@ from llama_cpp import Llama
 model = "Qwen/Qwen2-7B-Instruct-GGUF"
 llm = Llama.from_pretrained(
     repo_id=model,
-    filename="qwen2-7b-instruct-q4_k_m.gguf",
+    filename="qwen2-7b-instruct-q4_0.gguf",
     verbose=True,
-    use_mmap=False,
+    use_mmap=True,
     use_mlock=True,
     n_threads=2,
     n_threads_batch=2,
@@ -39,6 +39,7 @@ def respond(
         stream=True,
         temperature=temperature,
         top_p=top_p,
+        echo=False
     )
 
     for message in completion: