fix(config): align default decoder_kwargs with checkpoint (3× patch2)#8
Open
Mi221e wants to merge 1 commit intoOpenMOSS:mainfrom
Open
fix(config): align default decoder_kwargs with checkpoint (3× patch2)#8Mi221e wants to merge 1 commit intoOpenMOSS:mainfrom
Mi221e wants to merge 1 commit intoOpenMOSS:mainfrom
Conversation
Remove duplicate Transformer + PatchedPretransform stage so total temporal ratio stays 240×2³=1920, matching encoder and official config.json. Made-with: Cursor
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
The default
decoder_kwargsinMossAudioTokenizerConfigcontained an extraTransformer(384→768) and an extraPatchedPretransform(patch_size=2)compared to the shippedconfig.jsonand trained weights.Why
240 × 2³ = 1920matchesdownsample_rate.Verification
decoder_kwargsin the official modelconfig.json(e.g. Hugging Face / local weights).decoder.0/2/4/6), consistent with three interleavedpatch_size:2PatchedPretransform layers (no weights) plus finalpatch_size:240.