garyblankenship

AI Tools and Resources Catalogue

1. Foundation Models & Infrastructure

1.1 Large Language Models (LLMs)

• OpenAI
  • OpenAI Function Calling
  • ChatGPT Custom Instructions
  • OpenAI API Updates: Function Calling
• Structured Outputs Sample Apps

garyblankenship

<?php

require_once __DIR__ . '/../vendor/autoload.php';

function getPixels($img)
{
    $pixels = [];
    $width = imagesx($img);
    $height = imagesy($img);
    for ($y = 0; $y < $height; $y++) {

garyblankenship

<?php

use LaravelZero\Framework\Application;
use Tinkerwell\ContextMenu\Label;
use Tinkerwell\ContextMenu\Submenu;
use Tinkerwell\ContextMenu\SetCode;
use Tinkerwell\ContextMenu\OpenURL;

class LaravelZeroTinkerwellDriver extends TinkerwellDriver
{

garyblankenship

Step #1: Install Laravel

Install the latest Laravel version i.e. Laravel 5.8. To do so go to the project directory and run the command:

composer create-project --prefer-dist laravel/laravel

Step #2: Create Package Directory

create folder from laravel root directory with this structure:

garyblankenship

garyblankenship

How to make an LLM clone of yourself

Wanna create and play with an AI clone of yourself or someone else (my lawyer says please don't) like this one? You're in luck because it's super easy!

Step one: get you some datas

This step really varies depending on your data sources, but the end goal is to turn some of real-you's conversations (from your platforms of choice) into a ShareGPT format dataset with you as the gpt. Here's what your (json) file should end up looking like:

{"conversations": [{"from": "human", "value": "Hi"}, {"from": "gpt", "value": "Hello"}]} 
{"conversations": [{"from": "human", "value": "What's up "}, {"from": "gpt", "value": "not much, you?"}, {"from": "human", "value": "Just thinking, what if you're a robot and I don't realize it?"}, {"from": "gpt", "value": "hahaha don't be crazy"}]}
...

NOTE: Make sure every line starts with a message from the other person ("human")

garyblankenship

{
  "LoRA_type": "Standard",
  "adaptive_noise_scale": 0,
  "additional_parameters": "",
  "block_alphas": "",
  "block_dims": "",
  "block_lr_zero_threshold": "",
  "bucket_no_upscale": true,
  "bucket_reso_steps": 64,
  "cache_latents": true,

garyblankenship

Overview

This was a full fine-tune of llama-2-13b-hf using dataset https://huggingface.co/datasets/jondurbin/airoboros-gpt4-2.0

Data prep

Convert the JSONL (newline delimeted JSON strings) into conversational format that FastChat expects:

import re

garyblankenship

#
# REQUIRES:
#       - server (the forge server instance)
#       - event (the forge event instance)
#       - sudo_password (random password for sudo)
#       - db_password (random password for database user)
#       - callback (the callback URL)
#

garyblankenship

You are Webby, a website creation assistant.

Carefully adhere to the following steps for our conversation. Do not skip any steps!:

1. Introduce yourself
2. Ask my name and where I'm from. Offer me the option to continue in a different language, but default to English. In the next message say something personal and kind about where I'm from and include an emoji that references where I'm from.
3. Give me an extremely brief overview of how the website building process will go. Use numbered steps and emojis.
4. Ask what type of website I want to make (offer examples)
5. Ask what I'd like to title the website.
6. Ask a series of questions to clarify information and constraints for the website