diff --git a/examples/llama.swiftui/.gitignore b/examples/llama.swiftui/.gitignore
index 4f405ccc66e1ae..9bce6af399ba96 100644
--- a/examples/llama.swiftui/.gitignore
+++ b/examples/llama.swiftui/.gitignore
@@ -1 +1 @@
-xcuserdata
\ No newline at end of file
+xcuserdata
diff --git a/examples/llama.swiftui/README.md b/examples/llama.swiftui/README.md
index 44049dc81c5b3f..fa68e6ed8e34db 100644
--- a/examples/llama.swiftui/README.md
+++ b/examples/llama.swiftui/README.md
@@ -1,7 +1,7 @@
 # llama.swiftui
 
-Local inference of llama.cpp on an iPhone. 
-So far I only tested with starcoder 1B model, but it can most likely handle 7B models as well. 
+Local inference of llama.cpp on an iPhone.
+So far I only tested with starcoder 1B model, but it can most likely handle 7B models as well.
 
 https://github.com/bachittle/llama.cpp/assets/39804642/e290827a-4edb-4093-9642-2a5e399ec545
 
diff --git a/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift b/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
index 7f8b0f0b6d04a9..5f0e7db50404bd 100644
--- a/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
+++ b/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
@@ -11,28 +11,28 @@ actor LlamaContext {
     private var context: OpaquePointer
     private var batch: llama_batch
     private var tokens_list: [llama_token]
-    
+
     var n_len: Int32 = 512
     var n_cur: Int32 = 0
     var n_decode: Int32 = 0
-    
+
     init(model: OpaquePointer, context: OpaquePointer) {
         self.model = model
         self.context = context
         self.tokens_list = []
         self.batch = llama_batch_init(512, 0, 1)
     }
-    
+
     deinit {
         llama_free(context)
         llama_free_model(model)
         llama_backend_free()
     }
-    
+
     static func createContext(path: String) throws -> LlamaContext {
         llama_backend_init(false)
         let model_params = llama_model_default_params()
-        
+
         let model = llama_load_model_from_file(path, model_params)
         guard let model else {
             print("Could not load model at \(path)")
@@ -43,41 +43,41 @@ actor LlamaContext {
         ctx_params.n_ctx = 2048
         ctx_params.n_threads = 8
         ctx_params.n_threads_batch = 8
-        
+
         let context = llama_new_context_with_model(model, ctx_params)
         guard let context else {
             print("Could not load context!")
             throw LlamaError.couldNotInitializeContext
         }
-        
+
         return LlamaContext(model: model, context: context)
     }
-    
+
     func get_n_tokens() -> Int32 {
         return batch.n_tokens;
     }
-    
+
     func completion_init(text: String) {
         print("attempting to complete \"\(text)\"")
-        
+
         tokens_list = tokenize(text: text, add_bos: true)
-        
+
         let n_ctx = llama_n_ctx(context)
         let n_kv_req = tokens_list.count + (Int(n_len) - tokens_list.count)
-        
+
         print("\n n_len = \(n_len), n_ctx = \(n_ctx), n_kv_req = \(n_kv_req)")
 
         if n_kv_req > n_ctx {
             print("error: n_kv_req > n_ctx, the required KV cache size is not big enough")
         }
-        
+
         for id in tokens_list {
             print(token_to_piece(token: id))
         }
-        
+
         // batch = llama_batch_init(512, 0) // done in init()
         batch.n_tokens = Int32(tokens_list.count)
-        
+
         for i1 in 0..<batch.n_tokens {
             let i = Int(i1)
             batch.token[i] = tokens_list[i]
@@ -87,90 +87,90 @@ actor LlamaContext {
             batch.logits[i] = 0
         }
         batch.logits[Int(batch.n_tokens) - 1] = 1 // true
-        
+
         if llama_decode(context, batch) != 0 {
             print("llama_decode() failed")
         }
-        
+
         n_cur = batch.n_tokens
     }
-    
+
     func completion_loop() -> String {
         var new_token_id: llama_token = 0
-        
+
         let n_vocab = llama_n_vocab(model)
         let logits = llama_get_logits_ith(context, batch.n_tokens - 1)
-                
+
         var candidates = Array<llama_token_data>()
         candidates.reserveCapacity(Int(n_vocab))
-        
+
         for token_id in 0..<n_vocab {
             candidates.append(llama_token_data(id: token_id, logit: logits![Int(token_id)], p: 0.0))
         }
         candidates.withUnsafeMutableBufferPointer() { buffer in
             var candidates_p = llama_token_data_array(data: buffer.baseAddress, size: buffer.count, sorted: false)
-            
+
             new_token_id = llama_sample_token_greedy(context, &candidates_p)
         }
-        
+
         if new_token_id == llama_token_eos(context) || n_cur == n_len {
             print("\n")
             return ""
         }
-        
+
         let new_token_str = token_to_piece(token: new_token_id)
         print(new_token_str)
         // tokens_list.append(new_token_id)
-        
+
         batch.n_tokens = 0
-        
+
         batch.token[Int(batch.n_tokens)] = new_token_id
         batch.pos[Int(batch.n_tokens)] = n_cur
         batch.n_seq_id[Int(batch.n_tokens)] = 1
         batch.seq_id[Int(batch.n_tokens)]![0] = 0
         batch.logits[Int(batch.n_tokens)] = 1 // true
         batch.n_tokens += 1
-        
+
         n_decode += 1
-        
+
         n_cur += 1
-        
+
         if llama_decode(context, batch) != 0 {
             print("failed to evaluate llama!")
         }
-        
+
         return new_token_str
     }
-    
+
     func clear() {
         tokens_list.removeAll()
     }
-    
+
     private func tokenize(text: String, add_bos: Bool) -> [llama_token] {
         let n_tokens = text.count + (add_bos ? 1 : 0)
         let tokens = UnsafeMutablePointer<llama_token>.allocate(capacity: n_tokens)
         let tokenCount = llama_tokenize(model, text, Int32(text.count), tokens, Int32(n_tokens), add_bos, false)
-        
+
         var swiftTokens: [llama_token] = []
         for i in 0..<tokenCount {
             swiftTokens.append(tokens[Int(i)])
         }
-        
+
         tokens.deallocate()
-        
+
         return swiftTokens
     }
-    
+
     private func token_to_piece(token: llama_token) -> String {
         let result = UnsafeMutablePointer<Int8>.allocate(capacity: 8)
         result.initialize(repeating: Int8(0), count: 8)
-        
+
         let _ = llama_token_to_piece(model, token, result, 8)
-        
+
         let resultStr = String(cString: result)
-        
+
         result.deallocate()
-        
+
         return resultStr
     }
-}
+}
\ No newline at end of file
diff --git a/examples/llama.swiftui/llama.swiftui/Models/LlamaState.swift b/examples/llama.swiftui/llama.swiftui/Models/LlamaState.swift
index ed1573f4e2d499..babc60cdcc9dcc 100644
--- a/examples/llama.swiftui/llama.swiftui/Models/LlamaState.swift
+++ b/examples/llama.swiftui/llama.swiftui/Models/LlamaState.swift
@@ -3,7 +3,7 @@ import Foundation
 @MainActor
 class LlamaState: ObservableObject {
     @Published var messageLog = ""
-    
+
     private var llamaContext: LlamaContext?
     private var modelUrl: URL? {
         Bundle.main.url(forResource: "q8_0", withExtension: "gguf", subdirectory: "models")
@@ -17,7 +17,6 @@ class LlamaState: ObservableObject {
         }
     }
 
-    
     private func loadModel() throws {
         messageLog += "Loading model...\n"
         if let modelUrl {
@@ -27,7 +26,7 @@ class LlamaState: ObservableObject {
             messageLog += "Could not locate model\n"
         }
     }
-    
+
     func complete(text: String) async {
         guard let llamaContext else {
             return
@@ -35,7 +34,7 @@ class LlamaState: ObservableObject {
         messageLog += "Attempting to complete text...\n"
         await llamaContext.completion_init(text: text)
         messageLog += "\(text)"
-        
+
         while await llamaContext.n_cur <= llamaContext.n_len {
             let result = await llamaContext.completion_loop()
             messageLog += "\(result)"
diff --git a/examples/llama.swiftui/llama.swiftui/UI/ContentView.swift b/examples/llama.swiftui/llama.swiftui/UI/ContentView.swift
index 070ecde78c3e06..0bd16a806d10fa 100644
--- a/examples/llama.swiftui/llama.swiftui/UI/ContentView.swift
+++ b/examples/llama.swiftui/llama.swiftui/UI/ContentView.swift
@@ -2,15 +2,15 @@ import SwiftUI
 
 struct ContentView: View {
     @StateObject var llamaState = LlamaState()
-    
+
     @State private var multiLineText = ""
-    
+
     var body: some View {
         VStack {
             ScrollView(.vertical) {
                 Text(llamaState.messageLog)
             }
-            
+
             TextEditor(text: $multiLineText)
                 .frame(height: 200)
                 .padding()
@@ -27,7 +27,7 @@ struct ContentView: View {
         }
         .padding()
     }
-    
+
     func sendText() {
         Task {
             await llamaState.complete(text: multiLineText)