Model CoverageLarge Language ModelsZ.aiglm-4-9b-chat-hf

glm-4-9b-chat-hf

View as Markdown

GLM-4 is Zhipu AI’s fourth-generation General Language Model, featuring strong multilingual capabilities and tool-use support.

Set up NeMo AutoModel with the latest container or follow the installation instructions.

Fine-Tune glm-4-9b-chat-hf

From the repository root, run:

uv run automodel --nproc-per-node=8 examples/llm_finetune/glm/glm_4_9b_chat_hf_squad.yaml

Choose a Workflow

GoalStart Here
Supervised fine-tuning (SFT) - GLM-4 9B on SQuADUse glm_4_9b_chat_hf_squad.yaml.
Supervised fine-tuning (SFT) - GLM-4 9B on HellaSwag with FP8Use glm_4_9b_chat_hf_hellaswag_fp8.yaml.

Model Reference

Model Architecture

PropertyValue
TaskText Generation
ArchitectureGlmForCausalLM / Glm4ForCausalLM
Parameters9B
Hugging Face Organizationzai-org
  • GlmForCausalLM - GLM-4 series
  • Glm4ForCausalLM - GLM-4-0414 series

Available Models

ModelHF ID
GLM-4-9B-Chat-HFzai-org/glm-4-9b-chat-hf