-
Notifications
You must be signed in to change notification settings - Fork 50
[Ready For Review][AQUA][Multi-Model] Enhance AQUA CLI to Accept Fine-Tuned Weights Under Base Model in Multi-Model Deployment #1209
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
…l in Multi-Model Deployment
List[str] | ||
A list of all model OCIDs associated with this multi-model reference. | ||
""" | ||
ids = {self.model_id} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Check if self.model_id exists before inserting/ creating set?
# Use fallback name if needed | ||
ft_model.model_name = ( | ||
ft_model.model_name or fine_tune_source_model.display_name | ||
) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
are we allowing users to name their own FT modules?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
changes lgtm 👍
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Description
Currently, the CLI and UI handler for multi-model deployment accept a flat list of models, where model_id can refer to either a base model or a fine-tuned weight. Under the hood, the handler detects fine-tuned models and transforms the input into a nested structure grouping fine-tuned weights under their respective base models. This logic should be improved by explicitly allowing users to provide a base model and its associated fine-tuned weights directly in the input structure. This enhancement simplifies user intent, reduces ambiguity, and enables direct validation of base-to-weight relationships.
Current CLI command
New CLI command