> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/automodel/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/automodel/_mcp/server.

# glm-4-9b-chat-hf

> Use glm-4-9b-chat-hf with NeMo AutoModel for language model fine-tuning, with documented checkpoints, runnable recipes, setup guidance, and model reference details.

[GLM-4](https://github.com/zai-org/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](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the [installation instructions](/get-started/installation).

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

From the repository root, run:

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

## Choose a Workflow

| Goal                                                          | Start Here                                                                                                                                                         |
| ------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Supervised fine-tuning (SFT) - GLM-4 9B on SQuAD              | Use [glm\_4\_9b\_chat\_hf\_squad.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/glm/glm_4_9b_chat_hf_squad.yaml).                  |
| Supervised fine-tuning (SFT) - GLM-4 9B on HellaSwag with FP8 | Use [glm\_4\_9b\_chat\_hf\_hellaswag\_fp8.yaml](https://github.com/NVIDIA-NeMo/Automodel/blob/main/examples/llm_finetune/glm/glm_4_9b_chat_hf_hellaswag_fp8.yaml). |

## Model Reference

### Model Architecture

| Property                  | Value                                     |
| ------------------------- | ----------------------------------------- |
| Task                      | Text Generation                           |
| Architecture              | `GlmForCausalLM` / `Glm4ForCausalLM`      |
| Parameters                | 9B                                        |
| Hugging Face Organization | [zai-org](https://huggingface.co/zai-org) |

* `GlmForCausalLM` - GLM-4 series
* `Glm4ForCausalLM` - GLM-4-0414 series

### Available Models

| Model            | HF ID                                                                         |
| ---------------- | ----------------------------------------------------------------------------- |
| GLM-4-9B-Chat-HF | [`zai-org/glm-4-9b-chat-hf`](https://huggingface.co/zai-org/glm-4-9b-chat-hf) |

## Related Resources

* [LLM Fine-Tuning Guide](/recipes-e2e-examples/sft-peft)