Update app.py

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
 from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
-import multiprocessing
 
 hf_hub_download(repo_id="LLukas22/gpt4all-lora-quantized-ggjt", filename="ggjt-model.bin", local_dir=".")
 
-llm = Llama(model_path="./ggjt-model.bin", n_threads=multiprocessing.cpu_count())
+llm = Llama(model_path="./ggjt-model.bin", n_threads=2)
 
 def chat(input):
     resp = llm(input)