feat: upgrade MiniMax default model to M2.7#1027
Conversation
Add MINIMAX class to the LLM provider abstraction, enabling inference via MiniMax's OpenAI-compatible API (https://api.minimax.io/v1). MiniMax offers models with up to 204K context windows: - MiniMax-M1 - MiniMax-M1-80k - MiniMax-M2.5 The implementation follows the same pattern as existing providers (OPENAI, ANYSCALE) using the openai SDK with a custom base_url. Also updates the 3p-integrations notebook with a MiniMax usage example.
|
Hi @octo-patch! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list - Set MiniMax-M2.7 as default model (first in list) - Keep all previous models as alternatives
octo-patch
changed the title
1 participant
Summary
Upgrade MiniMax model configuration to include the latest M2.7 models.
Changes
MiniMax-M2.7andMiniMax-M2.7-highspeedto the model selection listMiniMax-M2.7as the new default model (first in valid_models list)MiniMax-M2.5,MiniMax-M1,MiniMax-M1-80k) as available alternativesMiniMax-M2.7Why
MiniMax-M2.7 is the latest flagship model with enhanced reasoning and coding capabilities. M2.7-highspeed is optimized for low-latency scenarios.
Testing