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

Previous threads: >>100815708 & >>100811614

►News
>(06/01) KV cache quantization support merged: https://github.com/ggerganov/llama.cpp/pull/7527
>(05/31) K2: Fully-reproducible model outperforming Llama 2 70B using 35% less compute: https://hf.co/LLM360/K2
>(05/29) Mistral releases Codestral-22B: https://mistral.ai/news/codestral/
>(05/28) DeepSeek-V2 support officially merged: https://github.com/ggerganov/llama.cpp/pull/7519
>(05/24) Draft PR adds support for Jamba: https://github.com/ggerganov/llama.cpp/pull/7531

►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
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
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

►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