Instructions to use PrimeIntellect/glm4-moe-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrimeIntellect/glm4-moe-tiny with Transformers:

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

pipe = pipeline("text-generation", model="PrimeIntellect/glm4-moe-tiny")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PrimeIntellect/glm4-moe-tiny")
model = AutoModelForCausalLM.from_pretrained("PrimeIntellect/glm4-moe-tiny")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PrimeIntellect/glm4-moe-tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PrimeIntellect/glm4-moe-tiny"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PrimeIntellect/glm4-moe-tiny",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PrimeIntellect/glm4-moe-tiny

SGLang

How to use PrimeIntellect/glm4-moe-tiny 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 "PrimeIntellect/glm4-moe-tiny" \
    --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": "PrimeIntellect/glm4-moe-tiny",
		"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 "PrimeIntellect/glm4-moe-tiny" \
        --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": "PrimeIntellect/glm4-moe-tiny",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PrimeIntellect/glm4-moe-tiny with Docker Model Runner:
```
docker model run hf.co/PrimeIntellect/glm4-moe-tiny
```

glm4-moe-tiny / chat_template.jinja

samsja

Upload folder using huggingface_hub

8fc6463 verified 3 months ago

raw

history blame contribute delete

1.02 kB

	[gMASK]<sop>
	{%- if tools -%}
	<\|system\|>
	# 可用工具
	{% for tool in tools %}
	{%- set function = tool.function if tool.get("function") else tool %}

	## {{ function.name }}

	{{ function \| tojson(indent=4, ensure_ascii=False) }}
	在调用上述函数时，请使用 Json 格式表示调用的参数。
	{%- endfor %}
	{%- endif -%}

	{%- for msg in messages %}
	{%- if msg.role == 'system' %}
	<\|system\|>
	{{ msg.content }}
	{%- endif %}
	{%- endfor %}

	{%- for message in messages if message.role != 'system' %}
	{%- set role = message['role'] %}
	{%- set content = message['content'] %}
	{%- set meta = message.get("metadata", "") %}

	{%- if role == 'user' %}
	<\|user\|>
	{{ content }}
	{%- elif role == 'assistant' and not meta %}
	<\|assistant\|>
	{{ content }}
	{%- elif role == 'assistant' and meta %}
	<\|assistant\|>{{ meta }}
	{{ content }}
	{%- elif role == 'observation' %}
	<\|observation\|>
	{{ content }}
	{%- endif %}
	{%- endfor %}
	{% if add_generation_prompt %}<\|assistant\|>{% endif %}