diff --git a/.gitignore b/.gitignore
index 36ed7f7fd..6c4402430 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,4 +1,4 @@
-.vscode/
+# .vscode/
 
 _skbuild/
 
diff --git a/.vscode/launch.json b/.vscode/launch.json
new file mode 100644
index 000000000..2b2502c69
--- /dev/null
+++ b/.vscode/launch.json
@@ -0,0 +1,16 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Current File",
+            "type": "python",
+            "request": "launch",
+            "program": "${file}",
+            "console": "integratedTerminal",
+            "justMyCode": false
+        }
+    ]
+}
\ No newline at end of file
diff --git a/tests/test_llama.py b/tests/test_llama.py
index 941287de6..2bdcfec18 100644
--- a/tests/test_llama.py
+++ b/tests/test_llama.py
@@ -169,3 +169,16 @@ def test_llama_server():
             }
         ],
     }
+
+
+def test_model():
+    # ./main -m ./models/ggml-model-q4_0.bin -p "Q: 广东2018的文科分数线是多少。这个问题的年份和省份分别是多少，用json的方式回答的结果是 A: " -n 12
+    # import os
+    # os.environ["N_THREAD"] = "16"
+    model_path = "/home/faith/llama-cpp-python/vendor/llama.cpp/models/ggml-model-q4_0.bin"
+    llm = llama_cpp.Llama(model_path=model_path, n_threads=16)
+    output = llm("Q: 广东2018的文科分数线是多少。这个问题的年份和省份分别是多少，用json的方式回答的结果是 A: ", max_tokens=12, stop=["Q:", "\n"], echo=True)
+    print(output)
+    
+    
+test_model()
\ No newline at end of file