Update app.py

app.py

@@ -19,9 +19,6 @@ from exception import CustomExceptionHandling
 
 
 # Download gguf model files
-llm = None
-llm_model = None
-
 hf_hub_download(
     repo_id="bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF",
     filename="Qwen2.5-Coder-1.5B-Instruct-Q6_K.gguf",
@@ -33,11 +30,15 @@ hf_hub_download(
     local_dir="./models",
 )
 
+
 # Set the title and description
 title = "Qwen-Coder Llama.cpp"
 description = """Qwen2.5-Coder, a six-model family of LLMs, boasts enhanced code generation, reasoning, and debugging. Trained on 5.5 trillion tokens, its 32B parameter model rivals GPT-4o, offering versatile capabilities for coding and broader applications."""
 
 
+llm = None
+llm_model = None
+
 def respond(
     message: str,
     history: List[Tuple[str, str]],
@@ -79,8 +80,8 @@ def respond(
                 n_gpu_layers=0,
                 n_batch=8,
                 n_ctx=2048,
-                n_threads=2,
-                n_threads_batch=2,
+                n_threads=8,
+                n_threads_batch=8,
             )
             llm_model = model
         provider = LlamaCppPythonProvider(llm)