Currently, we use from_pretrained with the cache_dir option to load the model and upload the cache directory to the BucketFS
The current approach in general works, but seems to check each time online if the model exists, or we have access and if we have the newest version
This is not possible in some deployments
To solve this issue, we could follow the following example using save_pretrained which stores the model into a directory which we then could upload
We can then load the model with from_pretrained from a local path
In #143 and #145 we added functionality for downloading and loading the model using save_pretrained
These functions now need to be integrated
### Acceptance Criteria
- [x] Change download of model to function created in #143
- [x] Upload the save model to the BucketFS
- [x] Use a local path to load the model during inference with function from #145
- [x] add documentation for new load with save_pretrained
- [x] change model_fixture/download_model to also use save_pretrained?
Background: