start.sh

#!/bin/bash


export WORK="/home/user/app"
cd $WORK
unzip llama_cpp_avx512.zip > /dev/null 2>&1 
wget -O model.gguf https://huggingface.co/unsloth/gpt-oss-20b-GGUF/resolve/main/gpt-oss-20b-Q4_K_M.gguf > /dev/null 2>&1

./llama-server -m model.gguf --port 8000 --host 0.0.0.0 --threads 2 --ctx-size 4096  --mlock --jinja  \
  --temp 0.2 \
  --top-p 0.85 &
python3 app.py

#python3 -m http.server 7860 --bind 0.0.0.0