cedrickchee

4 Steps in Running LLaMA-7B on a M1 MacBook

The large language models usability

The problem with large language models is that you can’t run these locally on your laptop. Thanks to Georgi Gerganov and his llama.cpp project, it is now possible to run Meta’s LLaMA on a single computer without a dedicated GPU.

Running LLaMA

There are multiple steps involved in running LLaMA locally on a M1 Mac after downloading the model weights.

1player

# Bazarr downloads subtitles

version: "3.4"
services:
  bazarr:
    image: linuxserver/bazarr:1.0.5-development
    container_name: bazarr
    restart: unless-stopped
    environment:
      - TZ=Europe/London

naveedqadir

import random
from hashlib import sha256


def coprime(a, b):
    while b != 0:
        a, b = b, a % b
    return a
    
    

henrik242

Disable Device Enrollment Program (DEP) notification on macOS Ventura.md

Ventura docs for M2 Macs in this comment: https://gist.github.com/henrik242/65d26a7deca30bdb9828e183809690bd?permalink_comment_id=4555340#gistcomment-4555340

Old Monterey docs in this old revision: https://gist.github.com/henrik242/65d26a7deca30bdb9828e183809690bd/32c410e3a1de73539c76fa13ea5486569c4e0c5d

Solution for Sonoma: https://gist.github.com/sghiassy/a3927405cf4ffe81242f4ecb01c382ac

bbqtd

Installing tmux-256color for macOS

• macOS 10.15.5
• tmux 3.1b

macOS has ncurses version 5.7 which does not ship the terminfo description for tmux. There're two ways that can help you to solve this problem.

The Fast Blazing Solution

Instead of tmux-256color, use screen-256color which comes with system. Place this command into ~/.tmux.conf or ~/.config/tmux/tmux.conf(for version 3.1 and later):

wess

; Ender 3 Custom Start G-code
M140 S{material_bed_temperature_layer_0} ; Set Heat Bed temperature
M190 S{material_bed_temperature_layer_0} ; Wait for Heat Bed temperature
M104 S160; start warming extruder to 160
G28 ; Home all axes
G29 ; Auto bed-level (BL-Touch)
G92 E0 ; Reset Extruder
M104 S{material_print_temperature_layer_0} ; Set Extruder temperature
G1 X0.1 Y20 Z0.3 F5000.0 ; Move to start position
M109 S{material_print_temperature_layer_0} ; Wait for Extruder temperature

remcovz

My setup:

GRE Tunnel using 10.42.1.0/24 for IPv4 and fd00:42::/48 for IPv6.

Host 1 (colo2) will announce: 2a07:1c42:10::/48 using AS208717.

Host 2 (vps1) will announce: 192.168.5.5/32 using AS65000.

First create the GRE tunnels:

jarek-przygodzki

sudo useradd --system --shell /bin/false node_exporter

curl -fsSL https://github.com/prometheus/node_exporter/releases/download/v1.3.1/node_exporter-1.3.1.linux-amd64.tar.gz \
  | sudo tar -zxvf - -C /usr/local/bin --strip-components=1 node_exporter-1.3.1.linux-amd64/node_exporter \
  && sudo chown node_exporter:node_exporter /usr/local/bin/node_exporter

eiri

Install Prometheus on Debian

install gosu

just to not wrestle with sudo and exec

$ sudo apt-get update
$ sudo apt-get install gosu

Create prometheus user

sirosen

"""
RSA Sign a Message using a private key

Just turns this example into a script:
    https://cryptography.io/en/latest/hazmat/primitives/asymmetric/rsa/#signing
"""

import sys
import hashlib
import base64