Instructions to use efficientscaling/Z1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use efficientscaling/Z1-7B with Transformers:

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

pipe = pipeline("text-generation", model="efficientscaling/Z1-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("efficientscaling/Z1-7B")
model = AutoModelForCausalLM.from_pretrained("efficientscaling/Z1-7B")
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 efficientscaling/Z1-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "efficientscaling/Z1-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "efficientscaling/Z1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/efficientscaling/Z1-7B

SGLang

How to use efficientscaling/Z1-7B 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 "efficientscaling/Z1-7B" \
    --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": "efficientscaling/Z1-7B",
		"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 "efficientscaling/Z1-7B" \
        --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": "efficientscaling/Z1-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use efficientscaling/Z1-7B with Docker Model Runner:
```
docker model run hf.co/efficientscaling/Z1-7B
```

zjy2001 commited on Apr 3, 2025

Commit

8a89646

verified ·

1 Parent(s): e6110bd

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -31,6 +31,14 @@ Z1: Efficient Test-time Scaling with Code
 ## Model Details
 To begin with the shifted thinking mode, please refer to https://github.com/efficientscaling/Z1.
 ## Gradio Demo
 ```python
@@ -176,14 +184,6 @@ if __name__ == "__main__":
     demo.launch()
 ```
-## Evaluation
-<p align="left">
-    <img src="tts.png" width="700">
-    <br>
-    <!-- <em>Test-time scaling comparison between Z1-7B and R1-Distill-Qwen-7B. </em> -->
-</p>
 ## Citation
 ```
 @misc{yu2025efficientscaling,

 ## Model Details
 To begin with the shifted thinking mode, please refer to https://github.com/efficientscaling/Z1.
+## Evaluation
+<p align="left">
+    <img src="tts.png" width="700">
+    <br>
+    <!-- <em>Test-time scaling comparison between Z1-7B and R1-Distill-Qwen-7B. </em> -->
+</p>
 ## Gradio Demo
 ```python
     demo.launch()
 ```
 ## Citation
 ```
 @misc{yu2025efficientscaling,