Add MiMo-7B model support for introspective interpretation #1
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
Integrate Xiaomi's MiMo-7B reasoning model as an alternative to Llama for self-explanation tasks. MiMo-7B achieves 95.8% on MATH500 and 68.2% on AIME 2024, rivaling OpenAI o1-mini performance. Changes: - Add ContinuousMiMo adapter class based on Qwen2 architecture - Register MiMo models in MODEL_TYPE_TO_VANILLA_MODEL_MAPPING - Add config files for feature descriptions, activation patching, and input ablation tasks - Support all MiMo variants (Base, SFT, RL, RL-Zero, RL-0530) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.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
ContinuousMiMoadapter class based on Qwen2 architecture with MTP supportChanges
model/continuous_mimo.py- New MiMo adapter with continuous token supportmodel/utils.py- Register MiMo in MODEL_TYPE_TO_VANILLA_MODEL_MAPPINGmodel/__init__.py- Export ContinuousMiMoSupported Models
XiaomiMiMo/MiMo-7B-BaseXiaomiMiMo/MiMo-7B-RLXiaomiMiMo/MiMo-7B-RL-0530(latest)XiaomiMiMo/MiMo-7B-SFTXiaomiMiMo/MiMo-7B-RL-ZeroTest plan
python train.py --config config/feature_descriptions/mimo_131k.yaml --debugtrust_remote_code=True🤖 Generated with Claude Code