Donations to the archive would be appreciated to help fund our server hardware & storage drives. We are looking for developers to help build new software and archives, discuss here.

No.100169864 View ViewReplyOriginalReport
how slow is you'r 'puter?
12 posts and 3 images omitted

Is Rust Dead Yet?

No.100168503 View ViewReplyOriginalReport
I've been living under a rock for the past few months, is that language finally gone? What sort of insane tranny Rust Foundation drama have I missed?
2 posts omitted

No.100167452 View ViewReplyLast 50OriginalReport
Why are HAMs such bootlicking faggots? They are like avatarfagging hall monitors. Were they always this way? I remember hearing all these cool stories about the "old days" of pirate radio stations and local access tv when I was a kid in the early 90's. Did the culture change or was there some kind of legislation/funding that gave the fcc more enforcement capability? I recently learned it's federally illegal to jam signals on your own private land in the USA, even if the transmission does not extend beyond the bounds of your property... what the actual fuck
92 posts and 5 images omitted

No.100166709 View ViewReplyOriginalReport
>a shitty clone of macOS: the DE
Why not just use the real thing at this point?
36 posts and 3 images omitted

No.100167434 View ViewReplyOriginalReport
Do audiophiles really think they need more than this?

/lmg/ - Local Models General

No.100166886 View ViewReplyLast 50OriginalReport
/lmg/ - a general dedicated to the discussion and development of local language models.

Previous threads: >>100161515 & >>100154945

â–ºNews
>(04/24) Snowflake Arctic Instruct 128x3B MoE released: https://hf.co/Snowflake/snowflake-arctic-instruct
>(04/23) Phi-3 Mini model released: https://hf.co/microsoft/Phi-3-mini-128k-instruct-onnx
>(04/21) Llama3 70B pruned to 42B parameters: https://hf.co/chargoddard/llama3-42b-v0
>(04/18) Llama3 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/

â–ºNews Archive: https://rentry.org/lmg-news-archive
â–ºFAQ: https://wikia.schneedc.com
â–ºGlossary: https://rentry.org/lmg-glossary
â–ºLinks: https://rentry.org/LocalModelsLinks
â–ºOfficial /lmg/ card: https://files.catbox.moe/cbclyf.png

â–ºGetting 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

â–ºFurther Learning
https://rentry.org/machine-learning-roadmap
https://rentry.org/llm-training
https://rentry.org/LocalModelsPapers

â–ºBenchmarks
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

â–ºTools
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

â–ºText 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
203 posts and 18 images omitted

No.100168293 View ViewReplyOriginalReport
Why do people who get less than 50 views a video upload videos continuously for years with no return? Why make content
27 posts and 2 images omitted

/dpt/ - Daily Programming Thread

No.100159394 View ViewReplyLast 50OriginalReport
 
console.log("What are you working on, g?");
220 posts and 19 images omitted

Why are codemonkeys working to replace themselves?

No.100170054 View ViewReplyOriginalReport
2 posts and 1 image omitted

/aicg/ - AI Chatbot General

No.100168428 View ViewReplyLast 50OriginalReport
280 posts and 43 images omitted