Remove random data from model - #20
Open
christophe0606 wants to merge 1 commit into
Open
christophe0606 wants to merge 1 commit into
christophe0606 wants to merge 1 commit into
Conversation
With fixed weights and fixed quantization data it makes it possible to compare with data in the README to quickly check the flow is ok.
MatthiasHertelArm
pushed a commit
that referenced
this pull request
Sep 10, 2026
Ported from PR #20 by Christophe Favergeon. The calibration data was a random tensor, so the output logits differed from one export to the next and could not be compared with the README. get_calibration_inputs() returns fixed samples; the exported program and the logits in the README are now reproducible (8832 bytes, verified on the FVP).
Contributor
|
Thanks. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
With fixed weights and fixed quantization data it makes it possible to compare with data in the README to quickly check the flow is ok.
The model was using random initialization weights and the quantization data was random.
Model weights are now fixed with a fixed seed for the random initialization.
quantization samples now have fixed values and a list of samples can be used.