fix: support qwen3 model_type and mlx-4bit subdir for moss models#2
Open
teddywangsg wants to merge 1 commit intoappautomaton:mainfrom
Open
Conversation
- Add recognition of 'qwen3' model_type as valid moss family, matching the behavior of 'moss_tts_delay' for sound_effect/local/delay dispatch - Look for config.json in common subdirs (mlx-4bit, mlx-int8, mlx-8bit) when not found directly in model_dir, fixing appautomaton/openmoss-* model layout issues
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
Two issues with
appautomaton/openmoss-sound-effect-mlxand related models:1.
model_type: "qwen3"not recognizedThe model has
config.jsonwithmodel_type: "qwen3"(incorrect, should bemoss_tts_delay), causing_resolve_tts_family()to reject it with:2.
config.jsonin subdirectoryThe model's
config.jsonlives inmlx-4bit/subdirectory, butMossTTSDelayConfig.from_path()looks directly in the snapshot root.Fix
_registry.py: Addqwen3as a valid model_type that dispatches likemoss_tts_delay— checking directory name forsound_effectto returnmoss_sound_effect.config.py: Fall back to searching common subdirs (mlx-4bit,mlx-int8,mlx-8bit) whenconfig.jsonis not found directly inmodel_dir.Testing
Verified against
appautomaton/openmoss-sound-effect-mlx— both issues resolved, audio generation works.