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
After we extracted the load class in #144 , we can then create a new load function which loads the model from a local path during inference
### Acceptance Criteria
- [x] Create a load class, which uses a local path to load the model during inference
- [x] add tests for new load function
- [x] add documentaion for the new load function like doc strings, full user docu will be added in #146
Background: