Add PEFT and DeepSpeed dependencies; align Qwen2Model usage and TTS prompt with MiMo-Audio#2
Open
candlewill wants to merge 4 commits intoXiaomiMiMo:mainfrom
Open
Add PEFT and DeepSpeed dependencies; align Qwen2Model usage and TTS prompt with MiMo-Audio#2candlewill wants to merge 4 commits intoXiaomiMiMo:mainfrom
candlewill wants to merge 4 commits intoXiaomiMiMo:mainfrom
Conversation
candlewill
changed the title
candlewill
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR introduces two key improvements for consistency and training efficiency:
peftanddeepspeedtorequirements.txtto support parameter-efficient fine-tuning and distributed training via DeepSpeed integration.is_causal=TruefromQwen2Modelforward call inmodeling_mimo_audio.pyto match the original MiMo-Audio implementation.mimo_audio.py, ensuring better alignment with the base model's training data for improved synthesis quality.