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

Played Us Like a Damn Fiddle 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: >>>>100068739

Why aren't there more people like this in the tech industry?

When will radio die out?

FAQ:
>How do I activate Windows?
https://github.com/massgravel/Microsoft-Activation-Scripts
HWID2 mimics a valid installation to generate a permanent legitimate license.

>Which version should I install?
W10 Enterprise IoT LTSC 2021
-10 yrs support, EoL 2032
-5 yrs on non-IoT LTSC
-No feature updates
-Comes with Win32 system utils
-Binary identical to Enterprise except no MS Store and no bloat apps
-If you need MS Store run this in cmd: wsreset -i
-Basically Windows: Classic 9x/XP/7 Edition, 10 years support and you decide when you want to update/upgrade

W10/W11 Home/Pro/Edu/Ent
-Dont install
-1.5-2 yrs support
-Constant forced updates
-Preinstalled bloatware apps (games, music, news, weather, people, onedrive, ads in start menu, etc)
*W11 specific
*Massive UI usability downgrades
*Taskbar removed features and options
*File explorer rewritten w/ reduced performance
*Has new CPU scheduler to support 12th+ gen Intel E-cores (its only redeeming feature)

>Is there a good version of W11?
No, 11 IoT LTSC *might* be good when released 24H2.

>How do I activate Office?
https://github.com/massgravel/Microsoft-Activation-Scripts
Alternatively, use MSOffice through your browser since it's free,
or try OnlyOffice/LibreOffice and set it to save as MSOffice file formats.

>ISOs:
Windows https://pastebin.com/nUMgAr0b
IoT LTSC https://pastebin.com/ywkasnhM
Office https://pastebin.com/G8w5qu6z

>Should I debloat or Optimize-Offline?
If you need to ask, then no. You WILL break something.
If you know what you're doing:
https://pastebin.com/S5VKBirt

>Windows/Office install guide
https://rentry.org/windowsinstallguide

>Portable programs & reinstall-proofing
https://pastebin.com/Zh7WSbJ2

>Useful programs for a new install
https://pastebin.com/hN8nnwns

>I miss Windows##
OpenShell/RetroBar/WinClassic/StartIsBack

WinInfo&OtherPastas:
https://rentry.org/fwt
https://rentry.org/ltsc
Change to .co if links don't work

Previous thread: >>99922670

The gimp logo has been flattened.
https://gitlab.gnome.org/GNOME/gimp-data/-/blob/main/images/logo/README.md
https://gitlab.gnome.org/GNOME/gimp-data/-/blob/main/images/logo-log.md

Microsoft unveils VASA, an AI that can generate hyper-realistic talking face videos with precise lip-audio sync, lifelike facial behavior, and naturalistic head movements in real-time, from just a single portrait and voice clip.

>We introduce VASA, a framework for generating lifelike talking faces of virtual charactors with appealing visual affective skills (VAS), given a single static image and a speech audio clip. Our premiere model, VASA-1, is capable of not only producing lip movements that are exquisitely synchronized with the audio, but also capturing a large spectrum of facial nuances and natural head motions that contribute to the perception of authenticity and liveliness. The core innovations include a holistic facial dynamics and head movement generation model that works in a face latent space, and the development of such an expressive and disentangled face latent space using videos. Through extensive experiments including evaluation on a set of new metrics, we show that our method significantly outperforms previous methods along various dimensions comprehensively. Our method not only delivers high video quality with realistic facial and head dynamics but also supports the online generation of 512x512 videos at up to 40 FPS with negligible starting latency. It paves the way for real-time engagements with lifelike avatars that emulate human conversational behaviors.

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

Previous threads: >>100066834 & >>100063933

►News
>(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
>(04/09) Llama 3 coming in the next month: https://techcrunch.com/2024/04/09/meta-confirms-that-its-llama-3-open-source-llm-is-coming-in-the-next-month/

►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
General Purpose:
https://hf.co/spaces/HuggingFaceH4/open_llm_leaderboard
https://hf.co/spaces/lmsys/chatbot-arena-leaderboard
Programming: https://hf.co/spaces/bigcode/bigcode-models-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

There is basically no competition on the laptop market. How did that happen? Why is Apple so good?

Why do Nvindians hate AMD GPUs?

>UPGRADE & BUILD ADVICE.
Post build list or current specs including MONITOR: https://pcpartpicker.com/
Provide specific use cases.
State BUDGET and COUNTRY or you will NOT be helped.

>CPU
Web browsing: i3 14100, 5600G
Budget: i5 12400F, 5600
Gaming: i5 12600KF, 7600
High end gaming: i5 14600K, 7800X3D
Workstation: i7 14700K, 7900X
AM4 upgrade: 5600, 5800X3D

>COOLER
Arctic Liquid Freezer III
Thermalright Phantom Spirit 120 EVO
Scythe Fuma 3
Thermalright Peerless Assassin SE
Budget: Assassin X 120 Refined SE, ID-COOLING SE-214-XT
AVOID: Dark Rock Pro 4/5, NH-U12A/D15

>RAM
DDR4: 2x16GB 3200CL16. Budget, 2x8GB 3200CL16
DDR5: 2x16GB 7200CL34. Budget: 6400CL32, AM5: 6000CL30
Workstation/high end: consider 2x32GB

>SSD (OS drive)
Budget: Cheapest PCIE4
Mid range: WD SN770
High end: Sabrent Rocket 5, Samsung 990 Pro, Solidigm P44 Pro

>GPU
1080p: 7700XT, budget: 6700XT, 6650XT, used RTX 2080 Ti
1440p: 7900GRE budget: 7800XT, used 6800XT
2160p: RX 7900XTX, budget: RX 7900XT
AVOID: Nvidia GPUs (4070 series has too many driver issues on Windows 10 & 11, 4080 and 4090 have board design issues causing hardware failure)

>CASE (from $ to $$$)
mATX: Thermaltake Versa H18, Thermaltake S100, Deepcool CH370, Fractal Pop Mini Air, Lian Li O11 Air Mini
ATX: Phanteks G300A (1 fan), Montech AIR 903 Base, Lian Li Lancool 216, Lian Li Lancool III, Fractal Torrent

>PSU
Budget: High end gold rated 500-600W PSU
Mid range: ATX 3.0 compliant gold rated PSU @ 75% max load
High end: Seasonic PRIME TX, be quiet! Dark Power Pro 13, Corsair HX1500i refresh
AVOID: GAMEMAX
https://cultists.network/140/psu-tier-list/
https://hwbusters.com/best_picks/best-atx-v3-0-pcie-5-0-ready-psus-picks-2023-hardware-busters/

>OS
Activate Windows @ >>>/g/fwt

>MONITORS
https://pcpartpicker.com/user/pcbg/saved/dP3v4D

>CASE FANS
Meta: get a case with good stock PWM fans
Budget: Arctic P12 PWM PST 5 pack
High end: Noctua NF-A12x25 PWM

Previous: >>100061271