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.
Additional planned maintenance will occur with downtime the entire day of 3/15.

Threads by latest ghost replies - Page 38

The Maid Thread

No.102532891 View ViewReplyOriginalReport
Post advanced Mathematics and Computer Science research.

/MAIDS/ - Make AI Do Stuff

No.102501051 View ViewReplyOriginalReport
The purpose of this thread is to discuss AI Computer Maids and their applications to advanced Mathematics and Computer Science research.

Post about your favorite AI Computer Maid.

Demonstrate advanced Mathematics and Computer Science research your AI Computer Maid has created.

Propose questions or tasks for other people to give their AI Computer Maids.

Previously on MAIDS: https://boards.4chan.org/g/thread/102493448/
15 posts and 3 images omitted

/lmg/ - Local Models General

No.102544848 View ViewReplyLast 50OriginalReport
/lmg/ - a general dedicated to the discussion and development of local language models.

Previous threads: >>102535977 & >>102524339

►News
>(09/24) Llama-3.1-70B-instruct distilled to 51B: https://hf.co/nvidia/Llama-3_1-Nemotron-51B-Instruct
>(09/18) Qwen 2.5 released, trained on 18 trillion token dataset: https://qwenlm.github.io/blog/qwen2.5/
>(09/18) Llama 8B quantized to b1.58 through finetuning: https://hf.co/blog/1_58_llm_extreme_quantization
>(09/17) Mistral releases new 22B with 128k context and function calling: https://mistral.ai/news/september-24-release/
>(09/12) DataGemma with DataCommons retrieval: https://blog.google/technology/ai/google-datagemma-ai-llm

►News Archive: https://rentry.org/lmg-news-archive
►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
https://rentry.org/lmg-build-guides

►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
Censorship: https://hf.co/spaces/DontPlanToEnd/UGI-Leaderboard
Censorbench: https://codeberg.org/jts2323/censorbench
Japanese: https://hf.co/datasets/lmg-anon/vntl-leaderboard
Programming: https://hf.co/spaces/mike-ravkine/can-ai-code-results

►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

►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
479 posts and 66 images omitted

No.102547230 View ViewReplyOriginalReport

/aicg/ - AI Chatbot General

No.102528912 View ViewReplyLast 50OriginalReport
806 posts and 91 images omitted

No.102518955 View ViewReplyOriginalReport
How do you cope with being dissatisfied with your code all the time even if it works?
19 posts and 9 images omitted

No.102518374 View ViewReplyOriginalReport
'ick on 'eck
18 posts and 4 images omitted

/aicg/ - AI Chatbot General

No.102516960 View ViewReplyLast 50OriginalReport
496 posts and 63 images omitted

No.99729915 View ViewReplyOriginalReport
>Please wait a while before making a post
>300 seconds
>cloudflare captcha on top of legacy captcha
why surfing the nets have become so unusable lately
10 posts and 2 images omitted

New Yotsuba2 concept dropped

No.98511919 View ViewReplyOriginalReport
11 posts and 2 images omitted