Instructions to use zai-org/GLM-4-9B-0414 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-4-9B-0414 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zai-org/GLM-4-9B-0414")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4-9B-0414")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4-9B-0414")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zai-org/GLM-4-9B-0414 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-4-9B-0414"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-4-9B-0414",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-4-9B-0414

SGLang

How to use zai-org/GLM-4-9B-0414 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "zai-org/GLM-4-9B-0414" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-4-9B-0414",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "zai-org/GLM-4-9B-0414" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-4-9B-0414",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-4-9B-0414 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-4-9B-0414
```

Base model

by mrfakename - opened Apr 14, 2025

Discussion

mrfakename

Apr 14, 2025

Hi,
Thanks for releasing GLM-4 9B! I saw the 32B base model was released. Are there any plans to release the 9B base model?
Thanks!

ZHANGYUXUAN-zR

Z.ai org Apr 14, 2025

•

edited Apr 14, 2025

No, this time we are only open-sourcing the 32B base model. There are no plans to open-source the 9B base model.

mrfakename

Apr 14, 2025

Hi,
Thanks for the clarification!
Totally understand if there are no current plans, but just wanted to say that I'd personally love to see an open-sourced 9B base model (especially with the MIT license!) - 32B is a bit large for fine-tuning and consumer hardware, so a strong 9B model would be a great base for finetuning.
If there's any chance the decision not to release the 9B base model could be reconsidered in the future, I'd really appreciate it.
Thanks again for your work on GLM-4 - the models look awesome!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment