Add qwen for llama app

Summary: Generate qwen2.5 0.5b model and run on the app

Differential Revision: D81751900

Author: cccclai

examples/demo-apps/apple_ios/LLaMA/LLaMA/Application/ContentView.swift

@@ -85,6 +85,7 @@ struct ContentView: View {
   enum ModelType {
     case llama
     case llava
+    case qwen2
     case qwen3
     case phi4
 
@@ -94,11 +95,13 @@ struct ContentView: View {
         return .llama
       } else if filename.hasPrefix("llava") {
         return .llava
+      } else if filename.hasPrefix("qwen2") {
+        return .qwen2
       } else if filename.hasPrefix("qwen3") {
         return .qwen3
       } else if filename.hasPrefix("phi4") {
         return .phi4
-      }
+
       print("Unknown model type in path: \(path). Model filename should start with one of: llama, llava, qwen3, or phi4")
       exit(1)
     }
@@ -346,15 +349,15 @@ struct ContentView: View {
       }
 
       switch modelType {
-      case .llama, .qwen3, .phi4:
+      case .llama, .qwen2, .qwen3, .phi4:
         runnerHolder.llamaRunner = runnerHolder.llamaRunner ?? LLaMARunner(modelPath: modelPath, tokenizerPath: tokenizerPath)
       case .llava:
         runnerHolder.llavaRunner = runnerHolder.llavaRunner ?? LLaVARunner(modelPath: modelPath, tokenizerPath: tokenizerPath)
       }
 
       guard !shouldStopGenerating else { return }
       switch modelType {
-      case .llama, .qwen3, .phi4:
+      case .llama, .qwen2, .qwen3, .phi4:
         if let runner = runnerHolder.llamaRunner, !runner.isLoaded() {
           var error: Error?
           let startLoadTime = Date()
@@ -468,6 +471,8 @@ struct ContentView: View {
         } else {
           let prompt: String
           switch modelType {
+          case .qwen2:
+              prompt = String(format: Constants.llama3PromptTemplate, text)
           case .qwen3:
             let basePrompt = String(format: Constants.qwen3PromptTemplate, text)
             // If thinking mode is enabled for Qwen, don't skip the <think></think> special tokens