This was a full fine-tune of llama-2-13b-hf using dataset https://huggingface.co/datasets/jondurbin/airoboros-gpt4-2.0
Convert the JSONL (newline delimeted JSON strings) into conversational format that FastChat expects:
import reThis was a full fine-tune of llama-2-13b-hf using dataset https://huggingface.co/datasets/jondurbin/airoboros-gpt4-2.0
Convert the JSONL (newline delimeted JSON strings) into conversational format that FastChat expects:
import re| { | |
| "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, |
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!
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")
| Name | Purpose | Author (Publication Date) | Category | |
|---|---|---|---|---|
| Andy - an artificial human | A slang term for "android" - an artificially created humanoid being. | Philip K. Dick (1968) | ai | |
| Autobutle | An automated servant. | Frank Herbert (1972) | ai | |
| Automaton Chessplayer - the first chess-playing computer | The first chess-playing computer. | Ambrose Bierce (1910) | ai | |
| Automonk | A robot with an AI trained on an individual monk. | Ray Naylor (2022) | ai | |
| Ava - she wants to be taught | A piece of learning software. | Amitav Ghosh (1995) | ai | |
| Bard | A machine that invents randomized stories and can read them out loud or animate them for viewing. | Isaac Asimov (1956) | ai | |
| Bendix Anxiety Reducer | Machine-based psychotherapy. | Robert Sheckley (1956) | ai | |
| Big Computer - wide-screen Jehovah | Just like it says; this computer knows it all. | John Varley (1983) | ai | |
| Big Noodle | A vast artificial intelligence system used to process all of Earth's information. | Philip K. Dick (1981) | ai |
Think of a Laravel package as a mini-application that plugs into any Laravel project. It's PHP code organized with specific conventions that Laravel recognizes and automatically integrates. The "magic" happens through Service Providers - special classes that tell Laravel "here's my code, here's how to use it."
Every package needs: a composer.json file (the package's ID card), a Service Provider (the integration bridge), and your actual code. Laravel handles the rest through auto-discovery.
| <?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 | |
| { |
| <?php | |
| require_once __DIR__ . '/../vendor/autoload.php'; | |
| function getPixels($img) | |
| { | |
| $pixels = []; | |
| $width = imagesx($img); | |
| $height = imagesy($img); | |
| for ($y = 0; $y < $height; $y++) { |