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

Architecture#

  • MiniMaxM2ForCausalLM

Example HF Models#

Model

HF ID

MiniMax M2.1

MiniMaxAI/MiniMax-M2.1

MiniMax M2.5

MiniMaxAI/MiniMax-M2.5

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

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

Note

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:26.02.00

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.

Hugging Face Model Cards#