Use ctransformers qwen model

app.py

@@ -8,9 +8,9 @@ print("Loading model...")
 llm = AutoModelForCausalLM.from_pretrained(
     MODEL_REPO,
     model_file=MODEL_FILE,
-    model_type="llama",
+    model_type="qwen",
     gpu_layers=0,
-    context_length=4096,
+    context_length=2048,
 )
 
 def respond(message: str, history: list[list[str]]) -> str: