-
Notifications
You must be signed in to change notification settings - Fork 739
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Pulling Norwegian models directly from Hugging Face into GenAI stack #56
Comments
Hi @HaakonME possible to join our Discord channel? We will help guide you through it so you can upload your own models as you see fit onto Ollama library. |
Hi @mchiang0610 , thanks I may do that. What I would really like is to set any MODEL_REPO in GenAI and pull in whatever model I want from any model repo, something like this branch, which tries to allow for Hugging Face models to be included as well as Ollama models - https://github.com/HaakonME/genai-stack/tree/huggingface |
@HaakonME would you mind proposing a PR to support the additional models? |
Ping? |
@jexp Sorry for the delay, I have been busy travellling around Norway doing AI talks, conferences and architecture work, amongst other things. Yes, I will get a PR proposed, but probably not till next weekend, i.e. another week from now. |
@HaakonME Hi, I'm curious if there is any progress regarding using models on HuggingFace with Docker GenAI? Thanks |
Hi, @sopheck , unfortunately no, and I still need it. I hope to have something to show by end of July, though. |
The number of models available from Ollama.ai at https://ollama.ai/library is quite limited compared to Hugging Face at https://huggingface.co/models , but more importantly, we need Norwegian language models, and there are no Norwegian models available from Ollama, while there a number of Norwegian models available from Hugging Face.
Pulling models directly from Hugging Face into the GenAI stack in addition to Ollama would be a nice feature enhancement.
The text was updated successfully, but these errors were encountered: