Fix the cli to have the proper model config over written. #960
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
#926 reported the current cli script is broken. The root cause is we only set the reference model config and other model config (rollout, actor, etc.) cannot pick up from there. This PR fixes this issue by dynamically picking up the updated model config and override in other model configs. This PR also fixes the issue that "gemma-3" in the model name is not supported issue. So now all the script at least can process the configs properly.
Reference
Colab Notebook
Checklist