wangii

This worked on 14/May/23. The instructions will probably require updating in the future.

It is possible to run LLama 13B with a 6GB graphics card now! (e.g. a RTX 2060). Thanks to the amazing work involved in llama.cpp. The latest change is CUDA/cuBLAS which allows you pick an arbitrary number of the transformer layers to be run on the GPU. This is perfect for low VRAM.

• Get llama.cpp from git, I am on commit 08737ef720f0510c7ec2aa84d7f70c691073c35d.
• Use the link at the bottom of the page to apply for research access to the llama model: https://ai.facebook.com/blog/large-language-model-llama-meta-ai/
• Set up a micromamba environment to install cuda/python pytorch stuff in order to run the conversion scripts. Install some packages:
  • micromamba install -c conda-forge -n mymamba pytorch transformers sentencepiece
• Perform the conversion process: (This will produce a file called `ggml-model

wangii

macOS Internals

Understand your Mac and iPhone more deeply by tracing the evolution of Mac OS X from prelease to Swift. John Siracusa delivers the details.

Starting Points

How to use this gist

You've got two main options:

wangii

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.

Prelude

Neural network links before starting with transformers.

wangii

Thermoeconomics

last update: 2022-11-12

Garrett model

1. How persistent is civilization growth? (Garrett 2011)
2. Can we predict long-run economic growth? (Garrett 2012)
3. Modes of growth in dynamic systems (Garrett 2012)
4. Thermodynamics of long-run economic innovation and growth (Garrett 2013)

wangii

set ssl_starttls=yes
set ssl_force_tls=yes

set imap_user = 'user_name@hotmail.com'
set imap_pass = 'password_here'
set from= $imap_user
set use_from=yes
set realname='Your_Name'
set folder = imaps://imap-mail.outlook.com:993
set spoolfile = "+INBOX"

wangii

#********************************************************************
#**  _00-readme-freebsd-11.1-imac.txt
#**    This note describes the proces of installing FreeBSD 11.1
#**    on an Intel iMac (early 2008)
#**    xref _00-readme-freebsd-11.txt
#**    last update 20170822.2034
#********************************************************************
---------------------------------------------------------------------
-- System Specifications:
---------------------------------------------------------------------

wangii

Generic 1,2,3 Noise

float rand(float n){return fract(sin(n) * 43758.5453123);}

float noise(float p){
	float fl = floor(p);
  float fc = fract(p);
	return mix(rand(fl), rand(fl + 1.0), fc);
}

wangii

bind-key        C-b send-prefix
bind-key        C-o rotate-window
bind-key        C-q confirm-before kill-server
bind-key        C-z suspend-client
bind-key      Space next-layout
bind-key          ! break-pane
bind-key          # list-buffers
bind-key          $ command-prompt -I #S "rename-session '%%'"
bind-key          & confirm-before -p "kill-window #W? (y/n)" kill-window
# Commennt out caused by Gist syntax error

wangii

//PLEASE NOTE: The ParticleEmitter class functions have changed since this tutorial
//after I reorganized some things for the SIMD update loop. The final code for that
//is linked in the optimization section.

enum ParticleFacingType
{
	ParticleFacing_2D_Billboard,
	ParticleFacing_3D_Billboard
};

wangii

input: "image"
input_dim: 1 # Original: 2
input_dim: 3 # It crashes if not left to 3
input_dim: 1 # Original: 368
input_dim: 1 # Original: 368
layer {
  name: "conv1_1"
  type: "Convolution"
  bottom: "image"
  top: "conv1_1"