bump ctx window up

app.py

@@ -8,9 +8,9 @@ llm = Llama.from_pretrained(
     verbose=True,
     use_mmap=True,
     use_mlock=True,
-    n_threads=2,
-    n_threads_batch=2,
-    n_ctx=2000,
+    n_threads=4,
+    n_threads_batch=4,
+    n_ctx=8000,
 )