#!/bin/bash # Start the local Mongo database mongod & # Start the text-generation-inference process pip3 install -U transformers && pip install -U transformers # mkdir /data/model_gptq # text-generation-server quantize ${MODEL_NAME} /data/model_gptq text-generation-launcher --model-id TheBloke/Llama-2-7B-GPTQ --quantize gptq --num-shard 1 --port 8080 & # Wait for text-generation-inference to start curl --retry 60 --retry-delay 10 --retry-connrefused http://127.0.0.1:8080/health # Start the chat-ui process pm2 start /app/build/index.js -i $CPU_CORES --no-daemon & # Wait for any process to exit wait -n # Exit with status of process that exited first exit $?