Update demo.py

demo.py

@@ -4,7 +4,7 @@ import gradio as gr
 
 
 llm = AutoModelForCausalLM.from_pretrained("TheBloke/falcon-7b-instruct-GGML", model_file="falcon7b-instruct.ggmlv3.q4_0.bin",
-                                           model_type="falcon", threads=20)
+                                           model_type="falcon", threads=8)
 
 
 TITLE = """<h2 align="center">🕊️ Falcon-Chat ggml 🕊️"""
@@ -198,5 +198,5 @@ def get_demo():
 
 if __name__ == "__main__":
   demo = get_demo()
-  demo.queue(max_size=128, concurrency_count=10)
+  demo.queue(max_size=128, concurrency_count=8)
   demo.launch(server_name="0.0.0.0", server_port=7860)