tolbrino

On-premise LLM model deployments

Requirements

LLM models used as an external resource offer multiple disadvantages:

• Privacy - guarantees regarding confidential imformation usage by the models and intellectual property (IP) safety cannot be guaranteed
• Flexibility - specialization and fine-tuning of more general models offers efficiency gains in terms of resources used and outputs achieved
• Stability - reducing vendor dependency allows internal system stability through guaranteed availability

An approach, whereby LLM models and deployed, fine-tuned and utilized locally (on-premise) allows:

tolbrino

YubiKey 4 series GPG and SSH setup guide

Written for fairly adept technical users, preferably of Debian GNU/Linux, not for absolute beginners.

You'll probably be working with a single smartcard, so you'll want only one primary key (1. Sign & Certify) and two associated subkeys (2. Encrypt, 3. Authenticate). I've published a Bash function which automates this slightly special key generation process.

tolbrino

#!/bin/bash

# Make API request and extract the IP addresses from the "hoprd_api_endpoint" field
ips=( $(curl --silent --request GET --url https://staging.discovery.rpch.tech/api/v1/node?status=READY | jq -r '.[].hoprd_api_endpoint | sub("http://"; "") | sub(":[0-9]*$"; "")') )

# Path to SSH private key for authentication
private_key_path=".ssh/id_rsa"

# Loop through the remote hosts and run the script on each one
for ip in "${ips[@]}"

tolbrino

# to generate your dhparam.pem file, run in the terminal
openssl dhparam -out /etc/nginx/ssl/dhparam.pem 2048

tolbrino

Archlinux setup guide

This guide is based on the official Archlinux [Installation Guide][1], [Beginners' Guide][2] and my personal experience.

Partition layout

HDD	fs	size	mountpoint
/dev/sda1	LUKS	MAX	-
/dev/sda1	LVM	MAX	/dev/mapper/lvm