diff --git a/examples/high_level_api_inference.py b/examples/high_level_api_inference.py
index 136f22c..0fa9cb7 100644
--- a/examples/high_level_api_inference.py
+++ b/examples/high_level_api_inference.py
@@ -11,7 +11,7 @@ llm = Llama(model_path=args.model)
 
 output = llm(
     "Question: What are the names of the planets in the solar system? Answer: ",
-    max_tokens=1,
+    max_tokens=48,
     stop=["Q:", "\n"],
     echo=True,
 )
diff --git a/examples/high_level_api_streaming.py b/examples/high_level_api_streaming.py
index d744090..787bc6e 100644
--- a/examples/high_level_api_streaming.py
+++ b/examples/high_level_api_streaming.py
@@ -4,7 +4,7 @@ import argparse
 from llama_cpp import Llama
 
 parser = argparse.ArgumentParser()
-parser.add_argument("-m", "--model", type=str, default=".//models/...")
+parser.add_argument("-m", "--model", type=str, default="./models/...")
 args = parser.parse_args()
 
 llm = Llama(model_path=args.model)