Instructions to use simplescaling/s1.1-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use simplescaling/s1.1-32B with Transformers:

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

pipe = pipeline("text-generation", model="simplescaling/s1.1-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("simplescaling/s1.1-32B")
model = AutoModelForCausalLM.from_pretrained("simplescaling/s1.1-32B", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use simplescaling/s1.1-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "simplescaling/s1.1-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "simplescaling/s1.1-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/simplescaling/s1.1-32B

SGLang

How to use simplescaling/s1.1-32B 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 "simplescaling/s1.1-32B" \
    --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": "simplescaling/s1.1-32B",
		"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 "simplescaling/s1.1-32B" \
        --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": "simplescaling/s1.1-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use simplescaling/s1.1-32B with Docker Model Runner:
```
docker model run hf.co/simplescaling/s1.1-32B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Summary

s1.1 is our sucessor of s1 with better reasoning performance by leveraging reasoning traces from r1 instead of Gemini.

Logs: https://wandb.ai/hashimoto-group/o1/runs/m1ilia77/overview
Repository: simplescaling/s1
Paper: https://arxiv.org/abs/2501.19393

This model is a successor of s1-32B with slightly better performance. Thanks to Bespoke Labs (Ryan Marten) for helping generate r1 traces for s1K with Curator.

Use

The model usage is documented here.

Evaluation

Metric	s1-32B	s1.1-32B	o1-preview	o1	DeepSeek-R1	DeepSeek-R1-Distill-Qwen-32B
# examples	1K	1K	?	?	>800K	800K
AIME2024	56.7	56.7	40.0	74.4	79.8	72.6
AIME2025 I	26.7	60.0	37.5	?	65.0	46.1
MATH500	93.0	95.4	81.4	94.8	97.3	94.3
GPQA-Diamond	59.6	63.6	75.2	77.3	71.5	62.1