docs(llm): upgrade default MiniMax model to M3#55
Open
octo-patch wants to merge 1 commit into
Open
Conversation
Add MiniMax-M3 as the new default model in the README example, while keeping MiniMax-M2.7 and MiniMax-M2.7-highspeed in the supported list for users who want the prior generation. - README.md: bump --lm_model_name example to MiniMax-M3 and refresh the supported models line. - backend/tests/test_minimax_lm.py: switch MINIMAX_MODEL default to MiniMax-M3 and add a unit test pinning the legacy MiniMax-M2.7 model name so existing users keep working.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Bump the documented default MiniMax model from
MiniMax-M2.7toMiniMax-M3in the README example, and align the existingbackend/tests/test_minimax_lm.pyconstants accordingly. The earlierMiniMax-M2.7andMiniMax-M2.7-highspeedmodels stay in the supported list for users who want to keep the prior generation.Changes
README.md: change theSupport for MiniMaxexample's--lm_model_nametoMiniMax-M3and refresh the Supported models line to listMiniMax-M3(default),MiniMax-M2.7,MiniMax-M2.7-highspeed.backend/tests/test_minimax_lm.py:MINIMAX_MODELconstant toMiniMax-M3so the existing unit and integration tests now exercise M3.MINIMAX_MODEL_M27constant +test_legacy_m27_model_name_storedtest to pin the prior generation model name so existing users keep working.No code paths in
s2s_server_pipeline.pyare changed; the LLM provider integration is model-name agnostic, so passingMiniMax-M3via--lm_model_nameworks without further changes. The OpenAI-compatible base URL (https://api.minimax.io/v1),MINIMAX_API_KEYenv var fallback, and temperature clamp logic are untouched.Test plan
pytest backend/tests/test_minimax_lm.py -v— 11 unit tests pass, 2 live integration tests skip withoutMINIMAX_API_KEY(unchanged behaviour).rg "MiniMax-M2(\.[0-9]+)?[^.7]"— no leftover references to older M1/M2/M2.1/M2.5 model IDs (project never had them).