Update app.py

app.py

@@ -8,7 +8,7 @@ from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 
 hf_hub_download(repo_id="Pi3141/alpaca-lora-7B-ggml", filename="ggml-model-q4_1.bin", local_dir=".")
-llm = Llama(model_path="./ggml-model-q4_1.bin", seed=0)
+llm = Llama(model_path="./ggml-model-q4_1.bin")
 
 
 ins = '''Below is an instruction that describes a task. Write a response that appropriately completes the request.
@@ -132,7 +132,7 @@ with gr.Blocks(theme=seafoam, analytics_enabled=False, css=css) as demo:
                 gr.Examples(
                     examples=examples,
                     inputs=[instruction],
-                    cache_examples=True,
+                    cache_examples=False,
                     fn=process_example,
                     outputs=[output],
                 )