#178 - Add support for running local LLMs via LLaMA C/C++ port (#249)

* Initial implementation of integrating llama.cpp to run LLaMA models locally

* Move submodule

* Copy llama submodule to bundle

* Support for downloading models from IDE

* Code cleanup

* Store port field

* Replace service selection radio group with dropdown

* Add quantization support + other fixes

* Add option to override host

* Fix override host handler

* Disable port field when override host enabled

* Design updates

* Fix llama settings configuration, design changes, clean up code

* Improve You.com coupon design

* Add new Phind model and help tooltip

* Fetch you.com subscription

* Add CodeBooga model, fix downloadable model selection

* Chat history support

* Code refactoring, minor bug fixes

* UI updates, several bug fixes, removed code llama python model

* Code cleanup, enable llama port only on macOS

* Change downloaded gguf models path

* Move some of the labels to codegpt bundle

* Minor fixes

* Remove ToRA model, add help texts

* Fix test

* Modify description

src/main/java/ee/carlrobert/codegpt/settings/state/LlamaSettingsState.java

@@ -0,0 +1,96 @@
+package ee.carlrobert.codegpt.settings.state;
+
+import com.intellij.openapi.application.ApplicationManager;
+import com.intellij.openapi.components.PersistentStateComponent;
+import com.intellij.openapi.components.State;
+import com.intellij.openapi.components.Storage;
+import com.intellij.util.xmlb.XmlSerializerUtil;
+import ee.carlrobert.codegpt.completions.HuggingFaceModel;
+import ee.carlrobert.codegpt.completions.llama.PromptTemplate;
+import java.io.IOException;
+import java.net.ServerSocket;
+import org.jetbrains.annotations.NotNull;
+
+@State(name = "CodeGPT_LlamaSettings", storages = @Storage("CodeGPT_CodeGPT_LlamaSettings.xml"))
+public class LlamaSettingsState implements PersistentStateComponent<LlamaSettingsState> {
+
+  private boolean useCustomModel;
+  private String customLlamaModelPath = "";
+  private HuggingFaceModel huggingFaceModel = HuggingFaceModel.CODE_LLAMA_7B_Q4;
+  private PromptTemplate promptTemplate = PromptTemplate.LLAMA;
+  private int serverPort = getRandomAvailablePortOrDefault();
+  private int contextSize = 2048;
+
+  public LlamaSettingsState() {
+  }
+
+  public static LlamaSettingsState getInstance() {
+    return ApplicationManager.getApplication().getService(LlamaSettingsState.class);
+  }
+
+  @Override
+  public LlamaSettingsState getState() {
+    return this;
+  }
+
+  @Override
+  public void loadState(@NotNull LlamaSettingsState state) {
+    XmlSerializerUtil.copyBean(state, this);
+  }
+
+  public boolean isUseCustomModel() {
+    return useCustomModel;
+  }
+
+  public void setUseCustomModel(boolean useCustomModel) {
+    this.useCustomModel = useCustomModel;
+  }
+
+  public String getCustomLlamaModelPath() {
+    return customLlamaModelPath;
+  }
+
+  public void setCustomLlamaModelPath(String customLlamaModelPath) {
+    this.customLlamaModelPath = customLlamaModelPath;
+  }
+
+  public HuggingFaceModel getHuggingFaceModel() {
+    return huggingFaceModel;
+  }
+
+  public void setHuggingFaceModel(HuggingFaceModel huggingFaceModel) {
+    this.huggingFaceModel = huggingFaceModel;
+  }
+
+  public PromptTemplate getPromptTemplate() {
+    return promptTemplate;
+  }
+
+  public void setPromptTemplate(PromptTemplate promptTemplate) {
+    this.promptTemplate = promptTemplate;
+  }
+
+  public int getServerPort() {
+    return serverPort;
+  }
+
+  public void setServerPort(int serverPort) {
+    this.serverPort = serverPort;
+  }
+
+  public int getContextSize() {
+    return contextSize;
+  }
+
+  public void setContextSize(int contextSize) {
+    this.contextSize = contextSize;
+  }
+
+  private static Integer getRandomAvailablePortOrDefault() {
+    try (ServerSocket socket = new ServerSocket(0)) {
+      return socket.getLocalPort();
+    } catch (IOException e) {
+      return 8080;
+    }
+  }
+}