blog.notmyidea.org/content/code/2023-09-22.md
Alexis Métaireau 91159ecc80 New version of the website.
- More categories are displayed
- Change the URL Scheme for categories
- Add a view for weeknotes, readings and code.
2023-09-25 16:50:07 +02:00

737 B

tags
llm

How to run the vigogne model locally

Vigogne is a LLM model based on LLAMA2, but trained with french data. As I'm working mostly in french, it might be useful. The current models that I can get locally are in english.

The information I've found online are scarse and not so easy to follow, so here is a step by step tutorial you can follow. I'm using pipenv almost everywhere now, it's so easy :-)


llm install -U llm-llama-cpp
wget https://huggingface.co/TheBloke/Vigogne-2-7B-Chat-GGUF/resolve/main/vigogne-2-7b-chat.Q4_K_M.gguf
llm llama-cpp add-model vigogne-2-7b-chat.Q4_K_M.gguf -a vigogne
llm models default vigogne