Step-3.5#

Step-3.5-Flash is a Mixture-of-Experts language model from Stepfun AI, designed for efficient inference.

Task

Text Generation (MoE)

Architecture

Step3p5ForCausalLM

Parameters

varies

HF Org

stepfun-ai

Available Models#

  • Step-3.5-Flash

Architecture#

  • Step3p5ForCausalLM

Example HF Models#

Model

HF ID

Step-3.5-Flash

stepfun-ai/Step-3.5-Flash

Example Recipes#

Recipe

Description

step_3.5_flash_hellaswag_pp.yaml

SFT — Step-3.5-Flash 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 16 nodes × 8 GPUs (128 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/stepfun/step_3.5_flash_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/stepfun/step_3.5_flash_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#