Refine merge script #92
Open
Conversation
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
There was a problem hiding this comment.
Pull Request Overview
This PR adds configurable aggregation options to a model merging script, allowing users to specify custom weights for each model and choose between averaging or summing parameters.
- Added
--source-weightsparameter to specify individual model weights - Added
--aggregation-methodparameter to choose between "average" and "sum" operations - Modified parameter accumulation logic to use weighted calculations instead of simple averaging
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
| if param_sums[key].shape != tensor.shape: | ||
| raise ValueError(f"Shape mismatch for key '{key}': " | ||
| f"{param_sums[key].shape} vs {tensor.shape}") | ||
| param_sums[key] += tensor |
There was a problem hiding this comment.
The parameter accumulation is not applying the weights. It should be param_sums[key] += tensor * weight to properly implement weighted merging.
|
@reiyw ping |
reiyw
approved these changes
Aug 29, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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.
モデルマージ用スクリプトに計算式を変更するオプションを追加：
何も指定しなければ単純な相加平均になります。