Instructions to use zai-org/GLM-5.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-5.1 with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-5.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-5.1")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-5.1")
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
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zai-org/GLM-5.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-5.1"
# 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-5.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-5.1

SGLang

How to use zai-org/GLM-5.1 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-5.1" \
    --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-5.1",
		"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-5.1" \
        --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-5.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-5.1 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-5.1
```

⚠️ Warning: Fake / Malicious GLM Repository on GitHub (Phishing & Virus)

#23

by WDDW - opened Apr 14

Discussion

WDDW

Apr 14

Dear GLM team,

I would like to report a fake and potentially dangerous repository impersonating the official GLM project on GitHub.

Malicious repository link:
https://github.com/GLM-5-1/GLM-5.1

Issue:
This repository pretends to be an official GLM-related project, but its Releases section contains suspected malware / phishing software (e.g., password-protected archives or executable files). Users who download and run these files may be at risk of credential theft or system infection.

Suggestion to the community:

Please do NOT download any release files from the suspicious repository.

@THUDM team, could you please:

Consider issuing a public warning to your community (e.g., pin a notice or tweet).

Report the malicious repository to GitHub Security if you have not done so already.

Thank you for your attention and for maintaining the safety of the open-source ecosystem.

Best regards

ZHANGYUXUAN-zR

Z.ai org Apr 16

We will check this issue in the next two days. Thank you for bringing this to our attention.

WDDW

Apr 18

Hello everyone,

I previously reported a fake GLM repository, and it has now been taken down (404). However, a new malicious repository has appeared:

🔗 https://github.com/Zai-glm/GLM-5.1

This fake repo ranks quite high in Bing search results for "GLM-5.1". The attacker didn't even bother to change the README.md — it's very likely the same person, and they are still targeting you.

What I have done so far:

Reported the malware to Huorong (火绒). They have already added detection for the malicious package.

Tested with other antivirus software:

Microsoft Defender (with reputation-based protection enabled) can directly delete it.

360 Security can also detect and remove it.

Advice for users:

As long as your security software's virus definitions are up to date and at least one real-time protection is enabled, this malware should have a hard time executing — unless the attacker releases a new variant.

I'm afraid I've done everything I can at this point. I'm out of options.

Finally, I would like to express my sincere thanks to the GLM team, ZHANGYUXUAN-zR, and Z.ai org for your hard work. Thank you for continuously maintaining high-quality open-source models and for taking security issues like this seriously. I hope my feedback is helpful to you. Please be aware of this new impersonation attempt.

Thank you all.

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