this post was submitted on 08 Jun 2023
25 points (100.0% liked)
LocalLLaMA
2871 readers
33 users here now
Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.
Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.
As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
llama cpp is crashy on my computer, it even didn't compiled.
Huh, that's interesting. If llama.cpp doesn't work, try https://github.com/oobabooga/text-generation-webui which (tries to) provides a user-friendly(-ier) experience.
it launches just fine, but when loading a model it says something like: successfully loaded none
Have you put your model in the "models" folder in the "text-generation-webui" folder? If you have, then navigate over to the "Model" section (button for the menu should be at the top of the page) and select your model using the box below the menu.
I tried to download an example one, cus I don't have any model, failed.
I'd recommend the model Wizard-Vicuna-7b-Uncensored (i know it's like a sentence https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GGML) direct download link is here: https://huggingface.co/TheBloke/Wizard-Vicuna-7B-Uncensored-GGML/blob/main/Wizard-Vicuna-7B-Uncensored.ggmlv3.q5_1.bin