Instructions to use zai-org/GLM-4.7-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-4.7-Flash with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-4.7-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4.7-Flash")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.7-Flash")
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 Settings

vLLM

How to use zai-org/GLM-4.7-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-4.7-Flash"
# 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-4.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-4.7-Flash

SGLang

How to use zai-org/GLM-4.7-Flash 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-4.7-Flash" \
    --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-4.7-Flash",
		"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-4.7-Flash" \
        --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-4.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-4.7-Flash with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-4.7-Flash
```

WARNING 02-08 00:50:40 [vllm.py:1500] `torch.compile` is turned on, but the model zai-org/GLM-4.7-Flash does not support it. Please open an issue on GitHub if you want it to be supported.

#62

by ANASDAVOODTK - opened Feb 8

Discussion

ANASDAVOODTK

Feb 8

Loading safetensors checkpoint shards: 92% Completed | 44/48 [00:26<00:02, 1.90it/s]
Loading safetensors checkpoint shards: 94% Completed | 45/48 [00:26<00:01, 1.84it/s]
Loading safetensors checkpoint shards: 96% Completed | 46/48 [00:27<00:01, 1.78it/s]
Loading safetensors checkpoint shards: 98% Completed | 47/48 [00:27<00:00, 1.74it/s]
Loading safetensors checkpoint shards: 100% Completed | 48/48 [00:28<00:00, 1.71it/s]
Loading safetensors checkpoint shards: 100% Completed | 48/48 [00:28<00:00, 1.68it/s]
glm-4-7-flash | (EngineCore_DP0 pid=321)
glm-4-7-flash | (EngineCore_DP0 pid=321) INFO 02-08 00:50:40 [default_loader.py:291] Loading weights took 28.57 seconds
glm-4-7-flash | (EngineCore_DP0 pid=321) INFO 02-08 00:50:40 [gpu_model_runner.py:4139] Loading drafter model...
glm-4-7-flash | (EngineCore_DP0 pid=321) WARNING 02-08 00:50:40 [vllm.py:1500] torch.compile is turned on, but the model zai-org/GLM-4.7-Flash does not support it. Please open an issue on GitHub if you want it to be supported.
Loading safetensors checkpoint shards: 0% Completed | 0/48 [00:00<?, ?it/s]
Loading safetensors checkpoint shards: 4% Completed | 2/48 [00:00<00:13, 3.52it/s]
Loading safetensors checkpoint shards: 19% Completed | 9/48 [00:00<00:02, 16.44it/s]
Loading safetensors checkpoint shards: 33% Completed | 16/48 [00:00<00:01, 27.28it/s]
Loading safetensors checkpoint shards: 48% Completed | 23/48 [00:00<00:00, 36.51it/s]
Loading safetensors checkpoint shards: 60% Completed | 29/48 [00:01<00:00, 25.57it/s]
Loading safetensors checkpoint shards: 77% Completed | 37/48 [00:01<00:00, 34.56it/s]
Loading safetensors checkpoint shards: 92% Completed | 44/48 [00:01<00:00, 28.55it/s]
Loading safetensors checkpoint shards: 100% Completed | 48/48 [00:01<00:00, 27.21it/s]

samarth9

Feb 22

Hey were you able to find the issue. Did you find a way to use torch.compile?

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