Upload main.py

main.py

@@ -53,7 +53,7 @@ def main():
     # Load the model
     llm = Llama(
         model_path=model_path,
-        n_ctx=5072,  # Set the maximum context length
+        n_ctx=572,  # Set the maximum context length
         max_tokens=max_tokens  # Control the maximum number of tokens generated in the response
     )