GLM-4.7 and GLM-4.7-Flash#
GLM-4.7 and GLM-4.7-Flash are GLM MoE language models from Zhipu AI. Megatron Bridge supports both checkpoints, with the full GLM-4.7 model handled by the GLM-4.5 bridge registration and the Flash variant handled by a dedicated GLM-4.7-Flash bridge.
Supported Variants#
Variant |
Hugging Face ID |
Bridge |
Notes |
|---|---|---|---|
GLM-4.7 |
|
|
Full MoE model, about 358B total parameters and 32B active |
GLM-4.7-Flash |
|
|
MLA + MoE model, about 30B total parameters and 3B active |
Architecture Notes#
GLM-4.7 uses the
glm4_moearchitecture already covered byGLM45Bridge.GLM-4.7-Flash uses
glm4_moe_lite, Multi-Latent Attention, GLM-style MoE routing, and expert-bias routing.GLM-4.7-Flash stores per-expert gate/up/down tensors in Hugging Face checkpoint format; the bridge maps them into Megatron MoE tensors.
transformers >= 5.0.0rc0is required for the GLM-4.7 Hugging Face model classes used by these bridges.
Examples#
For checkpoint conversion, inference, hardware notes, and validated parallelism settings, see the GLM-4.7 examples README.