feat: add MiniMax provider with M3 as default model#1661
Open
octo-patch wants to merge 2 commits into
Open
Conversation
- Add MiniMax chat model provider (MiniMax-M2.7, MiniMax-M2.7-highspeed) - Leverage OpenAI-compatible API via OpenAISolver inheritance - Add MINIMAX_API_KEY environment variable support - Add unit tests for solver properties and model validation - Add YAML registry configuration for direct and CoT solvers Octopus <liyuan851277048@icloud.com>
octo-patch
requested review from
andrew-openai,
etr2460 and
katyhshi
as code owners
- Add MiniMax-M3 to model registry and set as default - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives - Update unit tests to cover M3 alongside existing models
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 as a new LLM provider for the evals framework, with MiniMax-M3 as the default model and MiniMax-M2.7 / MiniMax-M2.7-highspeed as alternatives.
Changes
evals/solvers/providers/minimax/minimax_solver.py— inherits fromOpenAISolver, uses MiniMax's OpenAI-compatible API endpoint (https://api.minimax.io/v1)evals/registry/solvers/minimax.yaml— registers MiniMax-M3 (default), MiniMax-M2.7, and MiniMax-M2.7-highspeed for direct and chain-of-thought (CoT) solver configurationsevals/solvers/providers/minimax/minimax_solver_test.py— tests covering model validation, API configuration, solver properties, and error handling for M3 and M2.7 variantsSupported Models
MiniMax-M3MiniMax-M2.7MiniMax-M2.7-highspeedEnvironment Variable
MINIMAX_API_KEY— Required for authenticationMINIMAX_BASE_URL— Optional, defaults tohttps://api.minimax.io/v1API Reference
Implementation Approach
Follows the same pattern as
TogetherSolver— inherits fromOpenAISolverand overrides API base URL, API key, model validation, and prechecks (since tiktoken doesn't support MiniMax models).