Add unimodal teacher method to train the multimodal model

[dfulu]

Pull Request

Description

• Add in support for training the multimodal model via unimodal-teacher [1]
• Add tests for unimodal teacher model
• Add in support to convert the unimodal-teacher into a multimodal model and to push this to huggingface for production
• Also accidentally included another NWP / satellite encoder and tests
• Also included method to adapt batches which are too big either spatially or in time for easier experimentation
• Also light refactoring and removing duplicated code

[1] https://arxiv.org/pdf/2305.01233.pdf

Checklist:

• [x] My code follows OCF's coding style guidelines
• [x] I have performed a self-review of my own code
• [x] I have made corresponding changes to the documentation
• [x] I have added tests that prove my fix is effective or that my feature works
• [x] I have checked my code and corrected any misspellings

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 42.00743% with 156 lines in your changes are missing coverage. Please review.

Project coverage is 54.88%. Comparing base (5ce274a) to head (7bf98dd). Report is 4 commits behind head on main.

Files	Patch %	Lines
pvnet/models/multimodal/unimodal_teacher.py	33.49%	135 Missing :warning:
pvnet/models/multimodal/multimodal_base.py	23.80%	16 Missing :warning:
pvnet/models/multimodal/multimodal.py	78.57%	3 Missing :warning:
pvnet/data/base.py	33.33%	2 Missing :warning:

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #145 +/- ## ========================================== - Coverage 56.97% 54.88% -2.10% ========================================== Files 28 30 +2 Lines 1799 2037 +238 ========================================== + Hits 1025 1118 +93 - Misses 774 919 +145 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.