benob

# script to decompose/recompose llama model in different number of shards
# note that it loads the full model * 2 in cpu memory

import os
import json
import sys
import torch
import glob

if len(sys.argv) != 4:

aserhat

# Summary
A few notes I took to see if I could use MacOS as Hypevirsor in a similar fashion to Linux
I wanted to see how few addons were needed instead of using Parallels, Virtual Box, VM Fsion etc.
The idea is to use QEMU, Hypervisor Framework (https://developer.apple.com/documentation/hypervisor) and some custom host networking.

# Installations
brew install qemu (For controlling Hypervisor Framework)
brew install cdrtools (For making cloud init iso's)
http://tuntaposx.sourceforge.net/download.xhtml (For customer tap based networking)

rob-murray

// create file:
sudo vim /usr/share/applications/intellij.desktop

// add the following
[Desktop Entry]
Version=13.0
Type=Application
Terminal=false
Icon[en_US]=/home/rob/.intellij-13/bin/idea.png
Name[en_US]=IntelliJ

CristinaSolana

1. Clone your fork:

git clone [email protected]:YOUR-USERNAME/YOUR-FORKED-REPO.git

2. Add remote from original repository in your forked repository:

cd into/cloned/fork-repo
git remote add upstream git://github.com/ORIGINAL-DEV-USERNAME/REPO-YOU-FORKED-FROM.git
git fetch upstream