Re:Bumblebee: GPT2, Stable Diffusion, and More in Elixir
by pbowyer on Thursday December 08, 2022 @04:47PM
(#33914010)
Congratulations on this release!
If I have a Huggingface model that I've finetuned, can I load it using Bumblebee? I fine-tuned ConvNext and changed it into a multi-label classifier and saved it as a PyTorch model. It works great but being able to use it in LiveBook instead of Jupyter Notebook would be fantastic.
I think I'd have to convert the format, but what then?
Re:Bumblebee: GPT2, Stable Diffusion, and More in Elixir
by seanmor5 on Thursday December 08, 2022 @05:11PM
(#33914395)
No need to convert the format! Bumblebee supports loading parameters directly from PyTorch. You can just specify `{:local, path/to/checkpoint}` in `Bumblebee.load_model`
If I have a Huggingface model that I've finetuned, can I load it using Bumblebee? I fine-tuned ConvNext and changed it into a multi-label classifier and saved it as a PyTorch model. It works great but being able to use it in LiveBook instead of Jupyter Notebook would be fantastic.
I think I'd have to convert the format, but what then?