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

Previous threads: >>99154635 & >>99144750

►News
>(02/21) Google releases two open model, Gemma, possibly worse than Mistral-7b https://blog.google/technology/developers/gemma-open-models/
>(02/18) 1.5bit quant for lcpp merged https://github.com/ggerganov/llama.cpp/pull/5453
>(02/17) Kobold.cpp-1.58 prebuilt released https://github.com/LostRuins/koboldcpp/releases/tag/v1.58
>(02/16) Exl2 added Qwen support https://github.com/turboderp/exllamav2/issues/334
>(02/16) ZLUDA for lcpp merged, however, outlook is questionable at best https://github.com/vosen/ZLUDA/pull/102

►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

►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

►ERP/RP Datasets
https://rentry.org/qib8f
https://rentry.org/ashh2

►Tools
Alpha Calculator: https://desmos.com/calculator/ffngla98yc
GGUF VRAM Calculator: https://hf.co/spaces/NyxKrage/GGUF-VRAM-Calculator

►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
https://github.com/turboderp/exllamav2