Claudio Canales Klaudioz

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Neural network links before starting with transformers.

These instructions are based on DreamBooth usage with the https://github.com/ShivamShrirao/diffusers repo.

Below are 2 files. "convertToCkpt.py" and "toCkpt.sh". Create those files inside the examples/dreambooth folder with the code provided.

This easy widget let's you see upcoming matches of your favourite football team.

Copy this code in a new script in Scriptable app
Find teamId here: https://site.api.espn.com/apis/site/v2/sports/soccer/:league/teams
Find league id: some league abbreviation (EX: 'eng.1' for EPL, 'usa.1' for MLS, 'ned.1' for Dutch Eredivisie)
Change competitionId variable (line 4) with your competition id
Change teamId variable (line 5) with your favourite team id

	const awsTool = new DynamicTool({
	name: "aws-cli",
	description:
	"This is AWS CLI. You can call this to send commands to the AWS Cloud. Use AWS CLI format like `aws s3api list-buckets`",
	async func(command) {
	const args = command.split(" ").filter((x) => x !== "aws");
	const result = spawnSync("aws", args, {
	env: {
	...process.env,
	AWS_REGION: "eu-central-1",

	javascript:(() => {
	const requestURL = "http://127.0.0.1:8080/api/readingList";
	const token = "dfgkjlhsdfgkljghklhj";

	const pageTitle = document.title;
	const pageURL = window.location.href;
	let metaImage = "";
	let metaDescription = "";

	function getMetaValue(propName) {

	<?

	//
	// AUTO KEYWORD-BASED FOLLOWER CURATION BOT (by @levelsio)
	//
	// File: twitterFollowerCuratorBot.php
	//
	// Created: May 2021
	// License: MIT
	//

	# Bash really should be avoided as much as possible (within reasonable limits, of course) even for one-liners which seem trivial.
	# Bash is very error-prone by design. It's hard to comprehend all the pitfalls (e.g. https://mywiki.wooledge.org/BashFAQ/105)
	# and it's a regrettable time-waste anyway.
	#
	# Modern Python is good for scripting the logic - keep Bash only for launching executables and most primitive
	# pipes and redirections (avoid subshells, substitutions and so on). No need to install anything -
	# just start your script with the following small self-contained helper function (check the examples for usage). Its features:
	# * terminates on non-zero exit status by default
	# * returns the output (combined - which usually should not be a problem - use e.g. '2>/dev/null' when it is)
	# * prints commands and combined output

	#!/usr/bin/env bash
	# Send SIGSTOP (pause) to all plot processes
	ps aux \| grep "[c]hia plots create" \| awk '{print $2}' \| xargs kill -STOP