feat: add MiniMax as LLM provider with M3 default#1568
Open
octo-patch wants to merge 3 commits into
Open
Conversation
Add MiniMax (MiniMax-M2.5, MiniMax-M2.5-highspeed) as a new LLM provider option alongside OpenAI and Azure OpenAI. MiniMax offers an OpenAI-compatible API with up to 204K context length. Changes: - Add MiniMax provider detection and API endpoint construction in awesome_chat.py with priority: local > azure > minimax > openai - Handle MiniMax temperature constraint (must be > 0) by adjusting zero values to 0.01 - Add MiniMax model encodings and context lengths in get_token_ids.py - Create config.minimax.yaml template for MiniMax configuration - Update README.md with MiniMax setup instructions
Author
|
@microsoft-github-policy-service agree |
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list - Set MiniMax-M2.7 as default model in config and docs - Keep all previous models (M2.5, M2.5-highspeed) as alternatives - Update token encodings and max context length for new models
octo-patch
changed the title
- Add MiniMax-M3 as the new default model (512K context window) - Keep MiniMax-M2.7 and MiniMax-M2.7-highspeed as alternatives - Remove older MiniMax-M2.5 and MiniMax-M2.5-highspeed models - Update README.md and config.minimax.yaml to reflect new default
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 JARVIS/HuggingGPT, alongside the existing OpenAI and Azure OpenAI options. MiniMax provides an OpenAI-compatible chat completions API with models offering up to 512K context length on the M3 flagship.
Changes
awesome_chat.py): Added MiniMax to the provider priority chain (local > azure > minimax > openai) with proper API endpoint construction, key resolution (config file orMINIMAX_API_KEYenv var), and temperature clampingget_token_ids.py): RegisteredMiniMax-M3(512K context, default),MiniMax-M2.7, andMiniMax-M2.7-highspeed(204K context) with cl100k_base encoding. OlderMiniMax-M2.5*models have been removed.config.minimax.yaml): Pre-configured YAML withMiniMax-M3as the default modelREADME.md): Added MiniMax as a supported LLM provider with setup instructions, marking M3 as the defaultDefault Model
MiniMax-M3 — Latest flagship model with 512K context window and enhanced reasoning / coding / image-input capabilities.
Available MiniMax Models
MiniMax-M3MiniMax-M2.7MiniMax-M2.7-highspeedTesting
MiniMax-M3is the default model inconfig.minimax.yaml