Add MiniMax provider with M3 as default model#136
Open
octo-patch wants to merge 2 commits into
Open
Conversation
Add MiniMax AI as a new LLM provider alongside OpenAI, Anthropic, and Vertex AI. MiniMax offers OpenAI-compatible API with models like MiniMax-M2.7 and MiniMax-M2.5-highspeed (204K context). New files: - skllm/llm/minimax/ - credentials, completion, and mixin modules - skllm/models/minimax/ - classification (zero-shot, few-shot, CoT), text2text (summarization, translation), and tagging (NER) - tests/llm/minimax/ - 27 unit tests and 6 integration tests Modified files: - skllm/config.py - add set_minimax_key()/get_minimax_key() - skllm/model_constants.py - add MINIMAX_MODEL constant - README.md - add MiniMax usage example
- Add MiniMax-M3 as the new default model in MINIMAX_MODEL constant - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives - Remove older models (M2.5 and M2.5-highspeed) from documentation - Update default-model docstrings across classifier, summarizer, translator, NER - Update unit-test assertions for default model - Update integration tests to use the still-available MiniMax-M2.7-highspeed
octo-patch
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Add MiniMax AI as a new LLM provider alongside OpenAI, Anthropic, and Vertex AI. MiniMax offers an OpenAI-compatible API. This PR ships MiniMax-M3 as the default model and keeps
MiniMax-M2.7/MiniMax-M2.7-highspeedas alternatives.Available models
MiniMax-M3MiniMax-M2.7MiniMax-M2.7-highspeedChanges
skllm/llm/minimax/): credentials, completion (with temperature clamping to [0,1] and think-tag stripping), and mixin modules following the existing Anthropic/GPT patternskllm/models/minimax/): zero-shot / few-shot / CoT classifiers, multi-label classifiers, dynamic few-shot classifiers, summarizer, translator, and NER — all default toMiniMax-M3skllm/config.py):SKLLMConfig.set_minimax_key()/get_minimax_key()for API key managementskllm/model_constants.py):MINIMAX_MODEL = "MiniMax-M3"README.md): Quick-start example usesMiniMax-M3; available-models list isMiniMax-M3,MiniMax-M2.7,MiniMax-M2.7-highspeedWhy
MiniMax-M3is the latest MiniMax model — 512K context window, up to 128K output, and image-input support. Older entries (MiniMax-M2.5/MiniMax-M2.5-highspeed) were dropped from the public surface in favor of M3 as default and the still-supported M2.7 line as alternatives.Test plan
MiniMax-M3)MiniMax-M2.7-highspeed