feat: upgrade MiniMax default model to M3#1143
Open
octo-patch wants to merge 1 commit into
Open
Conversation
- Update MINIMAX_MODEL default from MiniMax-M2.7 to MiniMax-M3 in pdf2zh/translator.py - Update docs (ADVANCED.md, README_ja-JP.md, README_ko-KR.md, README_zh-TW.md) to reflect the new default model MiniMax-M3 is MiniMax's latest flagship model. The MINIMAX_MODEL env var still allows users to pick any other available model (e.g., MiniMax-M2.7) if desired.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 default MiniMax model used by
MiniMaxTranslatorfromMiniMax-M2.7toMiniMax-M3, MiniMax's latest flagship model.Changes
pdf2zh/translator.py: bump defaultMINIMAX_MODELtoMiniMax-M3docs/ADVANCED.md,docs/README_ja-JP.md,docs/README_ko-KR.md,docs/README_zh-TW.md: update the example default in the provider tableWhy
MiniMax-M3 is the new flagship model with 512K context window, 128K max output, and image input support across both OpenAI-compatible and Anthropic-compatible interfaces. It generally produces higher quality translations than M2.7 while remaining drop-in compatible with the existing OpenAI-style endpoint already used by
MiniMaxTranslator.Users who prefer the previous default can still select it explicitly via the
MINIMAX_MODELenv var (e.g.,MINIMAX_MODEL=MiniMax-M2.7).Testing
MiniMaxTranslator.envs