/lmg/ - a general dedicated to the discussion and development of local language models.

Previous threads: >>100135578 & >>100130427

►News
>(04/21) Llama 3 70B pruned to 42B parameters: https://hf.co/chargoddard/llama3-42b-v0
>(04/18) Llama 3 8B, 70B pretrained and instruction-tuned models released: https://llama.meta.com/llama3/
>(04/17) Mixtral-8x22B-Instruct-v0.1 released: https://mistral.ai/news/mixtral-8x22b/
>(04/15) Microsoft AI unreleases WizardLM 2: https://web.archive.org/web/20240415221214/https://wizardlm.github.io/WizardLM2/
>(04/09) Mistral releases Mixtral-8x22B: https://twitter.com/MistralAI/status/1777869263778291896

►FAQ: https://wikia.schneedc.com
►Glossary: https://archive.today/E013q | https://rentry.org/local_llm_glossary
►Links: https://rentry.org/LocalModelsLinks
►Official /lmg/ card: https://files.catbox.moe/cbclyf.png

►Getting Started
https://rentry.org/llama-mini-guide
https://rentry.org/8-step-llm-guide
https://rentry.org/llama_v2_sillytavern
https://rentry.org/lmg-spoonfeed-guide
https://rentry.org/rocm-llamacpp

►Further Learning
https://rentry.org/machine-learning-roadmap
https://rentry.org/llm-training
https://rentry.org/LocalModelsPapers

►Benchmarks
Chatbot Arena: https://chat.lmsys.org/?leaderboard
Programming: https://hf.co/spaces/bigcode/bigcode-models-leaderboard
Censorship: https://hf.co/spaces/DontPlanToEnd/UGI-Leaderboard
Censorbench: https://codeberg.org/jts2323/censorbench

►Tools
Alpha Calculator: https://desmos.com/calculator/ffngla98yc
GGUF VRAM Calculator: https://huggingface.co/spaces/NyxKrage/LLM-Model-VRAM-Calculator
Sampler visualizer: https://artefact2.github.io/llm-sampling/index.xhtml

►Text Gen. UI, Inference Engines
https://github.com/oobabooga/text-generation-webui
https://github.com/LostRuins/koboldcpp
https://github.com/lmg-anon/mikupad
https://github.com/turboderp/exui
https://github.com/ggerganov/llama.cpp

Congratulations!

/aicg/ - A general dedicated to the discussion and development of AI chatbots

Panda Hero Edition

>News
llama 3 8b and 70b https://llama.meta.com/llama3/, among other developments in local
opus on aws https://aws.amazon.com/blogs/aws/anthropics-claude-3-opus-model-on-amazon-bedrock/
gpt-4-turbo finally out of preview, not as fucked as the last preview snapshot
https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
news: https://rentry.org/aicg_chronicles
additional info: https://rentry.org/aicg_extra_information

>Bots
https://chub.ai
https://chub-archive.evulid.cc
https://booru.plus/+pygmalion
https://rentry.org/meta_bot_list

>Guides
https://rentry.org/tavern4retards

>Jailbreaks
https://rentry.org/jb-listing

>Frontends
https://sillytavern.app [SillyTavern]
https://agnai.chat [Agnai]
https://risuai.xyz [RisuAI]
https://docs.miku.gg [Miku]
https://character.ai [Cai]

>Models
gpt: https://platform.openai.com/docs
claude: https://docs.anthropic.com
gemini: https://ai.google.dev/docs
local: >>>/g/lmg
https://rentry.org/meta_golocal_list

>Botmaking
https://rentry.org/meta_botmaking_list
https://desune.moe/aichared
https://agnai.chat/editor

>Meta
OP templates: https://rentry.org/aicgOP
services assessment: https://rentry.org/aicg_meta
fun JBs and prompts: https://rentry.org/weirdbutfunjailbreaksandprompts - https://rentry.org/jinxbreaks
sultra: https://github.com/kingbased/gemini
logs: https://chatlogs.neocities.org
aicg botmaking events: https://rentry.org/meta_event_list

not gumi: >>100140065

/aicg/ - A general dedicated to the discussion and development of AI chatbots

Ham-Ham Edition

>News
Meta AI released Llama 3 8B and 70B https://llama.meta.com/llama3
Claude Opus on Amazon Bedrock https://aws.amazon.com/blogs/aws/anthropics-claude-3-opus-model-on-amazon-bedrock
OpenAI released the gpt-4-turbo as stable
Anthropic released the Claude 3 family https://www.anthropic.com/news/claude-3-family

additional info: https://rentry.org/aicg_extra_information

>Bots
https://chub.ai
https://chub-archive.evulid.cc
https://booru.plus/+pygmalion
https://rentry.org/meta_bot_list
https://rentry.org/charcardrentrylist

>Guides
https://rentry.org/tavern4retards - https://rentry.org/agnai_guides

>Jailbreaks
https://rentry.org/jb-listing

>Frontends
https://sillytavern.app [SillyTavern]
https://agnai.chat [Agnai]
https://risuai.xyz [RisuAI]
https://docs.miku.gg [Miku]
https://character.ai [Cai]

>Models
gpt: https://platform.openai.com/docs
claude: https://docs.anthropic.com
gemini: https://ai.google.dev/docs
local: >>>/g/lmg
https://rentry.org/meta_golocal_list

>Botmaking
https://rentry.org/meta_botmaking_list
https://desune.moe/aichared
https://agnai.chat/editor

>Meta
OP templates: https://rentry.org/aicgOP
services assessment: https://rentry.org/aicg_meta
try these -> https://rentry.org/weirdbutfunjailbreaksandprompts - https://rentry.org/jinxbreaks
old slaude stuff: https://rentry.org/meta_claude_list
logs: https://chatlogs.neocities.org
aicg botmaking events: https://rentry.org/meta_event_list

Previous: >>100136480

Previous thread >>100112723

>What is DALL-E 3?
You type some text and it makes some images

>Links
https://www.bing.com/images/create
https://designer.microsoft.com/image-creator
https://copilot.microsoft.com/

Bing AI Slop 0.6.0
https://pastebin.com/raw/LTrjKzeG

Designer AI Slop 0.4.4
https://pastebin.com/raw/U0SWtzm4

>How does it work on Bing?
In Bing's Image Creator, "boosts" are used to speed up the image creation process, each user starts with 15 boosts. When you use a boost, the AI creates your image quickly. If you run out of boosts, the image waiting time increases, ranging from seconds to minutes.

(You can also click on previous images you have created, do this several times and it seems to speed up the unboosted prompts)

>Resetting Boosts
Try clearing your search history at https://www.bing.com/profile/history

>(NEW) Landscape and Portrait regeneration
Follow the instructions here: rentry /bicedit

>Prompt Generator
https://tipseason.com/dalle-prompt-generator

>Related Boards
>>>/v/dall-e
>>>/co/dall-e
>>>/trash/aibf
>>>/aco/dall
>>>/tg/slop

Odd question but the one I have to ask - how "safe" it is to use social media nowadays?

By "safe" I mean the whole data collection and profile making, even when you don't provide info on your own, totally aware of the fact. Let me explain the problem. Since last few years, I constantly hit the wall of social media - I cannot play board/wargames because everyone uses solely Facebook to arrange meetings, I cannot show photos outside of /p/ because everyone insist on using FB/IG and don't want to visit my private site, people think I'm suspicious for not owning FB account and so on. I was not using it so far, I even tried making account few years ago but it was auto-blocked after few hours, probably because I used protonmail but it could be something else with IP (since I didn't post anything, only provided name, surname and phone number). I have spare (or two) Gmail addresses so I could try again but question is - assuming I would use separate Firefox profile, just for using FB, would it still collect more data than what I already would provide it (like few photos I'm content with losing but also combination of name, surname, face photo and phone number, which are however already present on LinkedIn)? Assuming I would use it "just" for said meeting arrangements and communication with models, completely avoiding posting on other places, commenting, etc - would it be "safe"? I once heard that only thing FB knows is what you tells it on your own but I want to know how true is that.

>Lisp is a family of programming languages with a long history and a distinctive parenthesized prefix notation. There are many dialects of Lisp, including Common Lisp, Scheme, Clojure and Elisp.

>Emacs is an extensible, customizable, self-documenting free/libre text editor and computing environment, with a Lisp interpreter at its core.

>Emacs Resources
https://gnu.org/s/emacs (Site)
https://github.com/emacs-tw/awesome-emacs (Awesome Emacs)

>Learning Emacs
C-h t (Interactive Tutorial)
https://emacs.amodernist.com (Configuration Generator)
https://systemcrafters.net/emacs-from-scratch (Emacs from Scratch)
http://xahlee.info/emacs (Xah Emacs Tutorial)

>Emacs Distros
https://spacemacs.org (Spacemacs)
https://doomemacs.org (Doom Emacs)
https://ergoemacs.github.io (Ergoemacs)

>Elisp
Docs: C-h f [function] C-h v [variable] C-h k [keybinding] C-h m [mode] M-x ielm [REPL]
https://gnu.org/s/emacs/manual/eintr.html (Introduction to Elisp)
https://gnu.org/s/emacs/manual/elisp.html (Elisp Manual)

>Common Lisp
https://lispcookbook.github.io/cl-cookbook (CL Cookbook)
https://cs.cmu.edu/~dst/LispBook (CL: A Gentle Introduction)
https://gigamonkeys.com/book (PCL)
https://lem-project.github.io (CL editor/IDE)
https://nyxt.atlas.engineer (CL Browser)

>Scheme
https://docs.scheme.org (Docs)
https://scheme.com/tspl4 (TSPL4)
https://eecs.berkeley.edu/~bh/ss-toc2.html (Simply Scheme)
https://archive.org/details/Schemer (Books)

>Clojure
https://clojure.org (Site)
https://clojure-doc.org (Docs)
https://mooc.fi/courses/2014/clojure (Functional programming with Clojure)

>Guix
https://guix.gnu.org/manual/devel (Guix Manual)
https://systemcrafters.net/craft-your-system-with-guix (Introduction to Guix)
https://gitlab.com/nonguix/nonguix (Nonguix)

>SICP/HtDP
https://web.mit.edu/6.001/6.037/sicp.pdf
https://htdp.org

>More Lisp Resources
https://paste.textboard.org/52b08691

(define alt-names '(/emg/ /emac/ /lambda/ /lol/ /let/ /flet/))
(set! prev-bread >>100071263)

>“It’s years behind what we have in the United States,” Raimondo said in the interview broadcast Sunday. “We have the most sophisticated semiconductors in the world. China doesn’t. We’ve out-innovated China.”

Will anybody catch up to the US in making the world's best semiconductors?

Damn MATE is ugly, like you linuxtrannies

>unlimited mobile internet data
>cheap electronics from anywhere in the world
>good used stuff are almost free
>they live in the college and go straight to work in FAGMAN companies
>they can buy tech stuff IRL in malls
>a good VPS is like 2% of the minimum wage