Model CoverageLarge Language Models (LLMs)

Step-3.5

View as Markdown

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

TaskText Generation (MoE)
ArchitectureStep3p5ForCausalLM
Parametersvaries
HF Orgstepfun-ai

Available Models

  • Step-3.5-Flash

Architecture

  • Step3p5ForCausalLM

Example HF Models

ModelHF ID
Step-3.5-Flashstepfun-ai/Step-3.5-Flash

Example Recipes

RecipeDescription
step_3.5_flash_hellaswag_pp.yamlSFT — 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

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

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:26.04.00

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