MiniMax-M2

MiniMax-M2 is MiniMax’s large Mixture-of-Experts language model with linear attention for efficient long-context inference.


Task	Text Generation (MoE)
Architecture	`MiniMaxM2ForCausalLM`
Parameters	varies
HF Org	MiniMaxAI

Available Models

MiniMax-M2.1
MiniMax-M2.5
MiniMax-M2.7

Architecture

MiniMaxM2ForCausalLM

Example HF Models

Model	HF ID
MiniMax M2.1	`MiniMaxAI/MiniMax-M2.1`
MiniMax M2.5	`MiniMaxAI/MiniMax-M2.5`
MiniMax M2.7	`MiniMaxAI/MiniMax-M2.7`

Example Recipes

Recipe	Description
minimax_m2.1_hellaswag_pp.yaml	SFT — MiniMax-M2.1 on HellaSwag with pipeline parallelism
minimax_m2.5_hellaswag_pp.yaml	SFT — MiniMax-M2.5 on HellaSwag with pipeline parallelism
minimax_m2.7_hellaswag_pp.yaml	SFT — MiniMax-M2.7 on HellaSwag with pipeline parallelism

Try with NeMo AutoModel

1. Install (full instructions):

$ pip install nemo-automodel

2. Clone the repo to get the example recipes:

$ git clone https://github.com/NVIDIA-NeMo/Automodel.git
$ cd Automodel

This recipe was validated on 8 nodes × 8 GPUs (64 H100s). See the Launcher Guide for multi-node setup.

3. Run the recipe from inside the repo:

$ automodel --nproc-per-node=8 examples/llm_finetune/minimax_m2/minimax_m2.1_hellaswag_pp.yaml

Run with Docker

1. Pull the container and mount a checkpoint directory:

$ docker run --gpus all -it --rm \
>   --shm-size=8g \
>   -v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
>   nvcr.io/nvidia/nemo-automodel:26.06.00

2. Navigate to the AutoModel directory (where the recipes are):

$ cd /opt/Automodel

3. Run the recipe:

$ automodel --nproc-per-node=8 examples/llm_finetune/minimax_m2/minimax_m2.1_hellaswag_pp.yaml

See the Installation Guide and LLM Fine-Tuning Guide.

Fine-Tuning

See the Large MoE Fine-Tuning Guide.