GLM-4 MoE (GLM-4.5 / GLM-4.7)#
GLM-4.5 and GLM-4.7 are Mixture-of-Experts variants of the GLM family released under the zai-org HuggingFace organization. GLM-4.7-Flash is a lighter variant with fewer active parameters.
Task |
Text Generation (MoE) |
Architecture |
|
Parameters |
varies |
HF Org |
Available Models#
GLM-4.5-Air (
Glm4MoeForCausalLM)GLM-4.7 (
Glm4MoeForCausalLM)GLM-4.7-Flash (
Glm4MoeLiteForCausalLM): lightweight MoE variant
Architectures#
Glm4MoeForCausalLM— GLM-4.5, GLM-4.7Glm4MoeLiteForCausalLM— GLM-4.7-Flash
Example HF Models#
Model |
HF ID |
|---|---|
GLM-4.5-Air |
|
GLM-4.7 |
|
GLM-4.7-Flash |
Example Recipes#
Recipe |
Description |
|---|---|
SFT — GLM-4.5-Air with TE + DeepEP |
|
SFT — GLM-4.7 with TE + DeepEP |
|
SFT — GLM-4.7-Flash with TE + DeepEP |
|
SFT — GLM-4.7-Flash with packed sequences |
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/glm/glm_4.5_air_te_deepep.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/glm/glm_4.5_air_te_deepep.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.