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.
There are multiple steps involved in running LLaMA locally on a M1 Mac after downloading the model weights.
| import glob | |
| from typing import Counter | |
| # import urllib.request | |
| # import os | |
| import json | |
| import genanki # https://pypi.org/project/genanki/ | |
| import warnings | |
| import random | |
| deckID = random.randint(1000000000, 2000000000) |
| brew install pandoc | |
| brew tap homebrew/cask | |
| brew install --cask basictex | |
| eval "$(/usr/libexec/path_helper)" | |
| # Update $PATH to include `/usr/local/texlive/2022basic/bin/universal-darwin` | |
| sudo tlmgr update --self | |
| sudo tlmgr install texliveonfly | |
| sudo tlmgr install xelatex | |
| sudo tlmgr install adjustbox | |
| sudo tlmgr install tcolorbox |
| 0) Go to https://mullvad.net/en/download/#linux <-- Latest Link when I made this guide or just go to your mullvad account page | |
| 1) Download your mullvad VPN files by clicking "GenerateOpenVPN configuration files" . Make sure to keep "Use IP addresses" and "Connect via our bridges" left unchecked | |
| 2) Unzip the downloaded file. | |
| 3) Move all four files (you should have four) to appdata/deluge/openvpn | |
| 3a) change the file extension of mullvad_<whatever region you selected>.conf to mullvad_<whatever region you selected>.ovpn | |
| 3b) Open mullvad_<whatever region you selected>.ovpn with a text editor and add the following lines to the bottom: | |
| pull-filter ignore "route-ipv6" | |
| pull-filter ignore "ifconfig-ipv6" | |
| 3c) save the file. | |
| 4) In your deluge container, edit the following settings: |
| 1: 日 | |
| 2: 一 | |
| 3: 国 | |
| 4: 会 | |
| 5: 人 | |
| 6: 年 | |
| 7: 大 | |
| 8: 十 | |
| 9: 二 | |
| 10: 本 |
事言思物何私無行時人若来見今良所自分中後方訳本当持出考入作聞聴場合話使日風前多一子供非常気取知感番二同必要仕余僕皆彼食書次結構問題例目眼頃上他家付陽間違受葉少買手好返掛終意味形三最初大住近特誰友達緒生活国現在高悪乗変会社実際先女心金顔町街及体読昔教対水置楽声普通残車度強力全呼局歩男性学校世界状態然飲新早小相母以関係四店頭電長夜別者親名部立毎族果況代覚東京続俺父確法説明屋朝得選面白戻勉下始犬嬉遊理由簡単死回内容経験木点音海応与利用働杯共存絶切足走待写真五寝英語決忘口送姿期逆頑張示々道有難山程願昭和向連影響病院年花求情報十開島重婚認歴史増外進起嫌駅映画身客質含地域我娘平成図紹介安夢規定色探興売化印象品参加夏解件敢的様答過配笑午動主困環境比引辺離火施練習越企業奴怖絵酒原因守広猫調六落打夫数割丈申可能述是料歌幾互着記憶基月君魚旅健康深伝集戦争流致厳不限愛途研究済描驚元素晴座機信古識低曲去土振評価息似悲雨詳紀昨喜便迎耳表注雰囲痛将転川隣段律妻冬具発繰泣七紙努判断両念庭払船九授亡止議茶直接効触飼民殺徴神暮飛雑誌怒整備建談絡懸命突首設指失光並八美優異婆至育種類商胸頼材勝運捨幸横伴予馬完格位展飯危険想像許文借準春寒般第押責任択負技術減焼慣推半条医秋趣徒従検討占査保正字空役球公園個消激短薬試遅資扱摘除週政府計階量田舎寂再勤吸希望急勧齢疲弱渡患壁路反提肩匂銀購右雪仲緑狭敗功協伯産卒降野菜告移血涙逃警察兄細静腰催瞬暗届窓伸森標更謝腕鹿忙遠苦労課仰為悩論録温眺極積故鳥市眠固値避穴捕洗左珍尋制登額塩奥組傾拡疑肉差章背景担豊助詰阪支抱追権算納織薄治療昼赤較荷魅村撮導韓営南季節枚輩員距泊充散黒石挨拶携帯休甘弟卵服妹交訪汗改善曜咲暑慢浮益裏姉継北宿掲都就職派舞台弾宅腹呂香菓被害椅桜躍恥皮革夕抜敵側祭沖縄幼稚処勢暇隠緊帰席歯星砂糖維太湯約束米周伺精冷適宗範裕械寄費層旦那揃誘採飾純植契叫駄髪管工婦監督鍋鼻復塗老倒翌則販諦障迷惑締餌床黙護等演奏泉室載肌症骨偉熱援握司盛犯罪批師浜脳器寺底刺吹訴把震昇複観祖抵狙迫唯青了未視波誕汚畑履膝案務孫包式虫到痩遥収掃徐促癖速製慌措油線造筋策濃館靴礼炒投玄込証沸剣巻恐牛乳否踏干箱泳邪踊攻撃弁久幅挑独壊仮輸満鍵詩西項塾県耐揮閉芝居析釈奪傷蔵庫慮港換防妊娠貸破削遣沿輝襲募属富喉布団宇宙唇釣覧拾絞江戸天敷洋承偶懐机
Press minus + shift + s and return to chop/fold long lines!
| " Use vim settings, rather then vi settings (much better!) | |
| " This must be first, because it changes other options as a side effect. | |
| set nocompatible | |
| set t_Co=256 " iTerm2 supports 256 color mode. | |
| set ai " auto indenting | |
| set history=100 " keep 100 lines of history | |
| set ruler " show the cursor position | |
| syntax on " syntax highlighting | |
| filetype plugin on " use the file type plugins |
| Regex for matching ALL Japanese common & uncommon Kanji (4e00 – 9fcf) ~ The Big Kahuna! | |
| ([一-龯]) | |
| Regex for matching Hirgana or Katakana | |
| ([ぁ-んァ-ン]) | |
| Regex for matching Non-Hirgana or Non-Katakana | |
| ([^ぁ-んァ-ン]) | |
| Regex for matching Hirgana or Katakana or basic punctuation (、。’) |
| # 0 is too far from ` ;) | |
| set -g base-index 1 | |
| # Automatically set window title | |
| set-window-option -g automatic-rename on | |
| set-option -g set-titles on | |
| #set -g default-terminal screen-256color | |
| set -g status-keys vi | |
| set -g history-limit 10000 |
