Add new parameters for loading models correctly to model loading

[MarleneKress79789]

Downloading a model and saving it locally using AutoModel.from_pretrained loses the model specialization (detailed description in #213) . After loading these broken models, using them for prediction returns bad results.

• We see only one option to solve this problem, and this is to specify the task during download of the model.
  • This means the download udf and the upload cli need an additional parameter for the task
    • The task should be part of the name of the uploaded model file, such that users can upload a model for multiple tasks
    • Furthermore, we should store the task inside the model archive file
• To solve the testing issues, we need to make the prediction udfs deterministic
  • For this, we need to be able to download a fixed version of a model and set the seed inside the prediction udf.
  • This means we need a version parameter in download udf, prediction udf and model upload cli
    • The version should be part of the name of the uploaded model file, such that users can upload multiple versions
  • We need a seed parameter in the prediction udfs

Prerequisites: #216, #217, #218

First we want to add the new parameters to the model saving and loading fuctionality:

task list: 

Add a "task" parameter with a default value to

• the HuggingFaceHubBucketFSModelTransferSP
• LoadLocalModel

Add a "version" parameter with default value to the

• HuggingFaceHubBucketFSModelTransferSP

• LoadLocalModel

• change the tests for HuggingFaceHubBucketFSModelTransferSP and LoadLocalModel accordingly. Potentially add new tests for new parameters