feat: upgrade MiniMax default model to M3 - #43
Open
octo-patch wants to merge 2 commits into
Open
Conversation
Set MiniMax-M3 as the default model for the --provider minimax vision evaluator and add a --model flag so MiniMax-M2.7 remains selectable. Update unit tests and README accordingly. Co-Authored-By: Octopus <liyuan851277048@icloud.com>
- Include MiniMax-M2.7-highspeed in the minimax provider's models list, alongside the M3 default and MiniMax-M2.7 - Update --model help text and README to mention M2.7-highspeed - Add unit test covering the M2.7-highspeed entry
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Upgrade the MiniMax vision evaluator (
--provider minimax) to use the latest MiniMax-M3 model by default, while keeping MiniMax-M2.7 and MiniMax-M2.7-highspeed available as alternatives.Changes
MiniMax-M3as the default model for theminimaxprovider inPROVIDER_CONFIGSmodelslist (MiniMax-M3,MiniMax-M2.7,MiniMax-M2.7-highspeed) with M3 listed first--modelflag so users can still selectMiniMax-M2.7orMiniMax-M2.7-highspeedwhen neededWhy
MiniMax-M3 is the new flagship multimodal model (512K context window, up to 128K output, image input support), making it a better default than M2.7 for vision-based evaluation. M2.7 and M2.7-highspeed remain available via
--model MiniMax-M2.7/--model MiniMax-M2.7-highspeedfor reproducibility and lower-latency use cases.Testing
python -m unittest MLLM_eval.test_gpt4v_eval-> 30 passed