Am I downloading directly from HuggingFace when I download models?
When I download a model from huggingface, am I using up their bandwidth or does runpod have some cache server that sits between my runpod and huggingface? I feel bad downloading from huggingface, bandwidth isn't free for them and all that.
9 Replies
yes
wget --header="Authorization: Bearer <HF_TOKEN> url
make a read token from ur user settings page
depending on what ur trying to download u might not even need a token
I want to play around with this model: https://huggingface.co/anthracite-org/magnum-v1-72b/tree/main
but it's 160GB.... I don't want to download all of that from hugging face just to play with it for a few hours, that feels like such a waste of their bandwidth
whats that ?
hugging face is down for me
It's an LLM for chatbots
okies
so thats the model ?
yeah. I don't think the model is too specific to my question though.
okies , how would u use it ?
sounds like a serverless workflow
I want to use it with sillytavern, there seems to be a project that makes sillytavern work with serverless, but I think it's abandoned
It's ok huggingface.co can handle them
Haha
Just download them if you want