Model CoverageLarge Language Models (LLMs)

Qwen2 MoE

View as Markdown

Qwen1.5-MoE is a Mixture-of-Experts variant from Alibaba Cloud that activates only a fraction of parameters per token, enabling efficient training and inference at scale.

TaskText Generation (MoE)
ArchitectureQwen2MoeForCausalLM
Parameters14.3B total / 2.7B active
HF OrgQwen

Available Models

  • Qwen1.5-MoE-A2.7B: 14.3B total parameters, 2.7B activated per token

Architecture

  • Qwen2MoeForCausalLM

Example HF Models

ModelHF ID
Qwen1.5 MoE A2.7BQwen/Qwen1.5-MoE-A2.7B
Qwen1.5 MoE A2.7B ChatQwen/Qwen1.5-MoE-A2.7B-Chat

Example Recipes

RecipeDescription
qwen1_5_moe_a2_7b_qlora.yamlQLoRA — Qwen1.5 MoE A2.7B

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

3. Run the recipe from inside the repo:

$automodel --nproc-per-node=8 examples/llm_finetune/qwen/qwen1_5_moe_a2_7b_qlora.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/qwen/qwen1_5_moe_a2_7b_qlora.yaml

See the Installation Guide and LLM Fine-Tuning Guide.

Fine-Tuning

See the LLM Fine-Tuning Guide and the Large MoE Fine-Tuning Guide.

Hugging Face Model Cards