feat: upgrade MiniMax default model to M3#1261
Open
octo-patch wants to merge 1 commit into
Open
Conversation
- Add MiniMax-M3 (524k context) to the supported model list, set as default - Retain MiniMax-M2.7 and MiniMax-M2.7-highspeed for compatibility - Remove deprecated MiniMax-M2.5 and MiniMax-M2.5-highspeed entries - Update sample config, docs, and tests to reflect the new default
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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_llmgenerator module to use MiniMax-M3 as the new default model.Changes
MiniMax-M3(524,288 token context) toMAX_TOKEN_DICT, set as the new defaultMiniMax-M2.7andMiniMax-M2.7-highspeedas available alternativesMiniMax-M2.5/MiniMax-M2.5-highspeedentriessimple_minimax.yamlsample config to use M3minimax_llm.mddocs to reflect the new model listWhy
MiniMax-M3is MiniMax's new flagship model with a 512K context window and 128K max output, and it is the recommended default for new integrations. M2.7 (and the high-speed variant) are kept available so users with existing configs continue to work.Testing
pytest tests/autorag/nodes/generator/test_minimax.pypasses (35 unit tests, 3 integration tests skipped withoutMINIMAX_API_KEY)ruff checkandruff formatclean