Add functions to collate deepspeed zero 3 checkpoints

[SeanNaren]

What does this PR do?

Required for #8691, follow-up from #8397

Adds a utility as suggested by @kaushikb11 to collate deepspeed sharded checkpoints. This is nicer than pointing users to a random gist by me :)

Before submitting

• Was this discussed/approved via a GitHub issue? (not for typos and docs)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes? (if necessary)
• Did you write any new necessary tests? (not for typos and docs)
• Did you verify new and existing tests pass locally with your changes?
• Did you list all the breaking changes introduced by this pull request?
• Did you update the CHANGELOG? (not for typos, docs, test updates, or internal minor changes/refactorings)

PR review

Anyone in the community is welcome to review the PR.
Before you start reviewing make sure you have read Review guidelines. In short, see the following bullet-list:

• Is this pull request ready for review? (if not, please submit in draft mode)
• Check that all items from Before submitting are resolved
• Make sure the title is self-explanatory and the description concisely explains the PR
• Add labels and milestones (and optionally projects) to the PR so it can be classified

Did you have fun?

Make sure you had fun coding 🙃

[codecov]

Codecov Report

Merging #8701 (69072ec) into master (a1be621) will increase coverage by 0%.
The diff coverage is 94%.

@@          Coverage Diff           @@
##           master   #8701   +/-   ##
======================================
  Coverage      93%     93%           
======================================
  Files         167     169    +2     
  Lines       14037   14075   +38     
======================================
+ Hits        13008   13045   +37     
- Misses       1029    1030    +1     

[kaushikb11]

LGTM!

[Borda]

how much is it our original code?

[SeanNaren]

how much is it our original code?

I found out you can bundle MIT/apache together under the apache licence, so i've done that and included lightning in the licence :)