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

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
```

Model breaks apart when used with different languages

#38

by nephepritou - opened Jan 23

Discussion

nephepritou

Jan 23

Description

For example, let's take a conversation:

> User: Hello! Write me simple shell script to get SHA256 checksum of files in folder.
> Model: <think>step_1; step_2; step_3;</think> response

It works great and has no issues. But then:

> User: Translate it to Russian
> Model: <think> step_4;step_5;step_6;</think> PERFECT response IN Russian without errors

Still works great. Try other option (request in Greek to translate to Russian):

> User: Μεταφράστε το στα Ρωσική
> Model: <think> step_4; step_4; step_5; step_4; step_6;</think> Response in step_6; Russ##&*an with step_7;step_4; errors

Now it broken completely. Try other option:

> User: Переведи на русский
> Model: <think> step_4; step_4; step_5; step_4; step_6;</think> Response in step_6; Russ##&*an with step_7;step_4; errors

Observations

There are no such issues with GGUF model using llama.cpp or ik_llama.cpp, no matter which quant to use. Only VLLM and SGLang are affected;
Same issue happening with Glm 4.5 Air AWQ, but I though it was because of lobotomized AWQ;
Qwen models (both instruct and thinking, 30B and 80B, dense and MoE, BF16, FP8 and AWQ) are not affected at all;
Noticed [gMASK] in jinja, tried to ask model itself "What is [gMASK] %template content%" and got broken output immediately;
Changing sampling parameters (or enabling speculative decoding, which disables min_p) may help. For example, it gives adequate responses (SOME TIMES) with top_p: 0.9;
Inference from Zai.org in model card works flawless, no issues.

May it be caused by specific UTF-8 issues with jinja? Or my configuration with 4 GPUs where 3 3090 and 1 4090? Or VLLM has issues with default sampling params?

nephepritou

Jan 23

I've tried to copy llama.cpp default sampling parameters and now it works much better. I've used

temperature: 0.8
top_p: 0.95
min_p: 0.05

Is this intended way to deploy model?

nephepritou

Jan 25

I've tried to copy llama.cpp default sampling parameters and now it works much better. I've used

temperature: 0.8

top_p: 0.95

min_p: 0.05

Is this intended way to deploy model?

Nevermind, just needs 1-2 more messages to break again.

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