Update app.py

app.py

@@ -28,11 +28,12 @@ print("Loading GGUF model...")
 
 llm = Llama(
     model_path=model_path,
-    n_ctx=4096,
+    n_ctx=2048,
     n_threads=max(1, os.cpu_count() or 2),
     n_threads_batch=max(1, os.cpu_count() or 2),
-    n_batch=128,
-    n_gpu_layers=1,
+    n_batch=64,
+    n_gpu_layers=0,
+    use_mmap=True,
     verbose=False,
 )
 
@@ -257,4 +258,8 @@ if __name__ == "__main__":
     demo.queue(
         default_concurrency_limit=1,
         max_size=10,
-    ).launch()
+    ).launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        show_error=True,
+    )