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

Bleach edition

>News
"GPT2" model on lmsys https://rentry.org/GPT2 (unavailable now)
AWS bedrock now has custom models on demand
https://aws.amazon.com/blogs/aws/import-custom-models-in-amazon-bedrock-preview/
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

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

>Bots
https://chub.ai
https://chub-archive.evulid.cc
https://rentry.org/meta_bot_list

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

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

>Guides
https://rentry.org/tavern4retards

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

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

>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

sand miku: >>100304938

>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.
Building guide: https://wiki.installgentoo.com/index.php/Build_a_PC

>UPCOMING
Intel Battlemage (Q3 2024)
RTX 5000 Series (Q4 2024)
Intel Arrow Lake (Q4 2024)

>CPU
Web browsing: i3 12100/5600G
Budget: 12400F/5600X/12600KF
Gaming: 13600KF/7600
High end gaming: 14700K/7800X3D
Workstation: 14700K/7900X
AM4 upgrade: 5600/5800X3D

>COOLER
AIO: Thermalright Frozen Edge/Arctic Liquid Freezer III
Double towers: TR Phantom Spirit 120 SE/EVO/Peerless Assassin SE, Scythe Mugen 6
Single towers: TR Assassin Spirit EVO
ITX/>42mm RAM: Scythe Fuma 3/TR AXP120-X67
AVOID: Dark Rock Pro 4/5/NH-U12A/D15(S)

>MOTHERBOARD
ASRock B650 LiveMixer

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

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

>GPU
1080p: RTX 4070 Super, RX 7700 XT, RX 7600
1440p: RTX 4070 Ti Super, RX 7900 GRE/7800 XT
2160p: RTX 4080 Super
Workstation: RTX 4000 Series, AVOID: AMD cards

>CASE (from $ to $$$)
mATX: Montech Air 100, Asus Prime AP201, Lian Li O11 Air Mini
ATX: Phanteks XT PRO(ULTRA), Montech AIR 903 Base/MAX, Lian Li Lancool 216/III
AVOID: 'Silent' cases, fanless cases, 4000D airflow

>PSU
Budget: Gold rated 500-600W PSU
Mid range: ATX 3.0 compliant fully modular gold rated PSU @ 75% max load
High end: Seasonic PRIME TX
AVOID: GAMEMAX
PSU buying guide:
https://hwbusters.com/best_picks/best-atx-v3-0-pcie-5-0-ready-psus-picks-2023-hardware-busters/ (updated for 2024)

>MONITOR
Standout:
1080p: Asus VG249Q1A
1440p: Dell G2724D
2160p: Gigabyte M27/28/32U
https://pcpartpicker.com/list/YmTPkJ

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

>CASE FANS
Meta: Case with good stock PWM fans
Budget: Arctic P12/P14 Max (5-pack)
High end: Noctua NF-A12x25 PWM

Previous:
>>100295711

What do /g/entoos?

remember when you had a choice?

Using ffmpeg, how can I make 4chan compatible webms with say an mp4 input?

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

Previous threads: >>100302819 & >>100298534

►News
>(05/02) Nvidia releases Llama3-ChatQA-1.5, excels at QA & RAG: https://hf.co/collections/nvidia/chatqa-15-662ebbf6acc85f5c444029a8
>(05/01) KAN: Kolmogorov-Arnold Networks: https://arxiv.org/abs/2404.19756
>(05/01) Orthogonalized Llama-3-8b: https://hf.co/hjhj3168/Llama-3-8b-Orthogonalized-exl2
>(04/27) Refusal in LLMs is mediated by a single direction: https://alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ
>(04/24) Snowflake Arctic Instruct 128x3B MoE released: https://hf.co/Snowflake/snowflake-arctic-instruct

►News Archive: https://rentry.org/lmg-news-archive
►FAQ: https://wikia.schneedc.com
►Glossary: https://rentry.org/lmg-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://hf.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

What are you working on, /g/?

Previous: >>100261000

Can I fit a Linux distro with X11 on this bad boy? Or is it impossible?

>argiedogs tried to hide their filthy argieroots while using their colors in the logo
fuck off

Proof that AI does not think like a human: