| export WORK="/home/user/app" | |
| cd $WORK | |
| #unzip llama-bin-20250728.zip > /dev/null 2>&1 | |
| unzip llama_cpp_avx512.zip > /dev/null 2>&1 | |
| wget -O model.gguf https://huggingface.co/unsloth/ERNIE-4.5-21B-A3B-PT-GGUF/resolve/main/ERNIE-4.5-21B-A3B-PT-UD-IQ1_S.gguf > /dev/null 2>&1 | |
| ./llama-server -m model.gguf --port 8000 --host 0.0.0.0 --threads 2 --ctx-size 4096 --mlock --jinja | |
| #wget https://huggingface.co/unsloth/Qwen3-30B-A3B-GGUF/resolve/main/Qwen3-30B-A3B-UD-IQ1_M.gguf > /dev/null 2>&1 | |
| #./llama-server -m Qwen3-30B-A3B-UD-IQ1_M.gguf --port 8000 --host 0.0.0.0 --threads 2 --ctx-size 4096 --mlock --jinja | |