Output GenerationConfig for LLMs imported from HF

[marcromeyn]

Important

The Update branch button must only be pressed in very rare occassions.
An outdated branch is never blocking the merge of a PR.
Please reach out to the automation team before pressing that button.

What does this PR do ?

Allowing models to be served in NIMs automatically by outputting the generation_config from HF.

Collection: [Note which collection this PR will affect]

Changelog

• Add specific line by line info of high level changes in this PR.

Usage

• You can potentially add a usage example below

# Add a code snippet demonstrating how to use this 

GitHub Actions CI

The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.

The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".

Before your PR is "Ready for review"

Pre checks:

• Make sure you read and followed Contributor guidelines
• Did you write any new necessary tests?
• Did you add or update any necessary documentation?
• Does the PR affect components that are optional to install? (Ex: Numba, Pynini, Apex etc)
  • Reviewer: Does the PR have correct import guards for all optional libraries?

PR Type:

• New Feature
• Bugfix
• Documentation

If you haven't finished some of the above items you can still open "Draft" PR.

Who can review?

Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.

Additional Information

• Related to # (issue)

[github-actions]

[🤖]: Hi @marcromeyn 👋,

We wanted to let you know that a CICD pipeline for this PR just finished successfully

So it might be time to merge this PR or get some approvals

I'm just a bot so I'll leave it you what to do next.

//cc @pablo-garay @ko3n1g

[janekl]

In the edited files on importing a particular model (Llama, Deepseek, etc.) we are adding instantiation of GenerationConfig as if it exists with:

generation_config = GenerationConfig.from_pretrained(str(self))

I wonder if this assumption is true. Will the import_ckpt call work fine if there is no generation_config.json present in the model directory?

@PeganovAnton pointed out one counterexample https://huggingface.co/nvidia/Minitron-4B-Base/tree/main w/o generation_config.json (though we don't have support for this one).

[janekl]

LGTM. @marcromeyn could you please add a short description in the MR body under "What does this PR do" on what happens here? Like a command, one-sentence explanation and maybe that nice directory structure pasted (from _build_directory_tree).

I'm asking so that everyone immediately knows that the change here is about getting artifacts/generation_config.json into the context directory

[github-actions]

[🤖]: Hi @marcromeyn 👋,

We wanted to let you know that a CICD pipeline for this PR just finished successfully

So it might be time to merge this PR or get some approvals

I'm just a bot so I'll leave it you what to do next.

//cc @pablo-garay @ko3n1g