LV Nilesh lvnilesh

Ollama + Open-WebUI + NVIDIA GPU

A Docker Compose stack for running local LLMs on your own hardware with NVIDIA GPU acceleration, a web UI, and one-command model setup via profiles.

What's Included

Asked Claude to:

write a one page pamphlet about moby dick using postscript.

Convert the PS to PDF using:

ps2pdf mobydick.ps

gistash

Stash files on gist.github.com

Installation

$ wget https://gist.githubusercontent.com/btbytes/73d6ddb0cf940e730edf22a60208691b/raw/fbf9efb44ee1c88eaaa3f62d6437737402ea74ce/gistash 
$ chmod +x gistash

kamal

This documentation adds important additions to the docs for kamal deploy tool (see github.com/basecamp/kamal)

Destination flag

You can use kamal deploy --destination staging

This will read config/deploy.yml and config/deploy.staging.yml files, and also will read .env.staging file if it exists.

-> <-

The Novice's LLM Training Guide

->Written by Alpin<- ->Inspired by /hdg/'s LoRA train rentry<- !!!warning This guide is being slowly updated. We've already moved to the axolotl trainer.

[TOC2]

Moved to nostr-resources.com

	{
	config,
	pkgs,
	options,
	...
	}: let
	hostname = "oatman-pc"; # to alllow per-machine config
	in {
	networking.hostName = hostname;

	start-at-login = true

	accordion-padding = 0
	gaps.inner.horizontal = 10
	gaps.inner.vertical = 10

	after-startup-command = [
	'workspace 1', 'layout h_accordion horizontal',
	'workspace 2', 'layout h_accordion horizontal',
	]

	#!/bin/bash

	# Verify if GPU is CUDA-enabled
	lspci \| grep -i nvidia

	# Remove previous NVIDIA driver installation
	sudo apt-get purge nvidia* -y
	sudo apt remove nvidia-* -y
	sudo rm /etc/apt/sources.list.d/cuda* -y
	sudo apt-get autoremove && sudo apt-get autoclean -y