How do I download llama-2

Hi there,

I’m trying to understand the process to download a llama-2 model from TheBloke/LLaMa-7B-GGML · Hugging Face

I’ve already been given permission from Meta. But I don’t understand what to do next. Am I supposed to ask permission from huggingface as well? If so, where/how? Or is there code I can run which will do the installation I seek? I see that KoboldCpp is suggested as a model to try. I’d like to try that. But is that a separate download?

Hello there,

You need to also go on the original llama model page on HuggingFace and ask as well. Once you get it, you’ll be able to use TheBloke’s model.

Beware, for a lot of users the request is never answered. I don’t know why.