tutorials: compose ALORA model from source in race notebook#56
Merged
yairallouche merged 5 commits intoMay 24, 2026
Merged
Conversation
added 5 commits
May 21, 2026 17:38
Replace the pre-built Hub checkpoint (granite-switch-4.1-3b-preview) with a freshly composed model, so both race legs are built from the same three granitelib adapters using the same compose pipeline. The ALORA leg uses no --technology-filter so the composer prefers ALORA adapters and falls back to LoRA where unavailable — symmetric with the existing LoRA leg which uses --technology-filter lora.
Also fix stale section 4 markdown that still referenced the Hub checkpoint after the previous commit switched to composing from source.
guardian_check's target_role= kwarg was removed; use scoring_schema='user_prompt'.
The coloransi import was patching TermColors attributes that were never read anywhere in the file — dead code. Removing it makes the script runnable outside Jupyter without requiring ipython installed.
yairallouche
approved these changes
May 24, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
ibm-granite/granite-switch-4.1-3b-previewHub checkpoint with a freshly composed model in the ALORA race leg, so both legs are built from the same three granitelib adapters using the same compose pipeline (no--technology-filter, so ALORA is preferred with LoRA as fallback)--alora-modeltobench_pipeline_race.pyin the ALORA benchmark cellbench_pipeline_race.py:target_role→scoring_schema,utcnow()→datetime.now(datetime.UTC), remove dead IPython importTest plan