Basic NON interactive install of text-generation-webui to host LLM on Ubuntu - for 24GB GPU such as AWS EC2 G4 or G5 box

gistfile1.txt

#!/bin/bash
# Basic NON interactive install of text-generation-webui to host LLM on Ubuntu

GPU_GB=${1:-24}

#sudo apt update
#sudo apt install python3-pip

git clone https://github.com/oobabooga/text-generation-webui.git

pushd text-generation-webui

echo "=== === installing text-generation-webui"
# Do NOT launch after install, since this is a non-interactive install
GPU_CHOICE=A USE_CUDA118=FALSE LAUNCH_AFTER_INSTALL=FALSE INSTALL_EXTENSIONS=TRUE ./start_linux.sh --public-api --extensions openai --api-port 5000 --auto-devices --gpu-memory $GPU_GB
# --share

# echo "=== === Downloading an LLM ..."
# python3 download-model.py    TheBloke/CodeLlama-13B-GGUF
# python3 download-model.py    mistralai/Mistral-7B-v0.1
echo "=== === [done]"