Update config.json

config.json

@@ -1,8 +1,18 @@
 {
-  "model": "llava-v1.6-mistral-7b.Q3_K_XS.gguf",
-  "clip_model_path": "mmproj-model-f16.gguf",
-  "chat_format": "llava-1-5",
-  "n_threads": 12,
-  "logits_all": true,
-  "host": "0.0.0.0"
+  "host": "0.0.0.0",
+  "port": 8080,
+  "models": [
+    {
+      "model": "llava-v1.6-mistral-7b.Q3_K_XS.gguf",
+      "model_alias": "llava-1.6",
+      "chat_format": "llava-1-5",
+      "clip_model_path": "mmproj-model-f16.gguf",
+      "n_gpu_layers": -1,
+      "offload_kqv": false,  // Assuming default value, adjust as needed
+      "n_threads": 12,
+      "n_batch": 1,
+      "n_ctx": 2048,
+      "logits_all": true
+    }
+  ]
 }