Add preliminary README

.gitignore

@@ -1,4 +1,4 @@
-HELP.md
+README.md
 
 .mvn
 

llama.log

@@ -1 +1 @@
-[1751134161] warming up the model with an empty run
+[1751135918] warming up the model with an empty run

src/main/java/com/pablotj/ia/chat/boot/infraestructure/llm/LlmModelLoader.java

@@ -4,18 +4,22 @@ import com.pablotj.ia.chat.boot.domain.exception.BusinessLogicException;
 import de.kherud.llama.LlamaModel;
 import de.kherud.llama.ModelParameters;
 import jakarta.annotation.PostConstruct;
+import org.springframework.beans.factory.annotation.Value;
 import org.springframework.stereotype.Component;
 
 @Component
 public class LlmModelLoader implements AutoCloseable {
 
+    @Value(value = "${model.gguf.name}")
+    private String modelName;
+
     private LlamaModel model;
 
     @PostConstruct
     public void init() {
         try {
             ModelParameters params = new ModelParameters()
-                    .setModelFilePath("models/openchat-3.5-0106.Q4_K_M.gguf")
+                    .setModelFilePath(String.format("models/%s.gguf", modelName))
                     .setSeed(42)
                     .setNThreads(8)
                     .setNGpuLayers(0)

src/main/resources/application.properties

@@ -1,2 +1,5 @@
 spring.application.name = ia-chat-boot
 server.port             = 8080
+
+! Model
+model.gguf.name         = openchat-3.5-0106.Q4_K_M