Instructions to use Multiverse4FM/Multiverse-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Multiverse4FM/Multiverse-32B with Transformers:

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

pipe = pipeline("text-generation", model="Multiverse4FM/Multiverse-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Multiverse4FM/Multiverse-32B")
model = AutoModelForCausalLM.from_pretrained("Multiverse4FM/Multiverse-32B")
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 Multiverse4FM/Multiverse-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Multiverse4FM/Multiverse-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": "Multiverse4FM/Multiverse-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Multiverse4FM/Multiverse-32B

SGLang

How to use Multiverse4FM/Multiverse-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 "Multiverse4FM/Multiverse-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": "Multiverse4FM/Multiverse-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 "Multiverse4FM/Multiverse-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": "Multiverse4FM/Multiverse-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Multiverse4FM/Multiverse-32B with Docker Model Runner:
```
docker model run hf.co/Multiverse4FM/Multiverse-32B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Summary

Multiverse-32B, built on Multiverse, is the first open-source, non-AR model to achieve scores of 54% and 46% on AIME 2024 & 2025.

Webpage: Multiverse
Paper: https://arxiv.org/abs/2506.09991

Use

The model usage is documented here.

Evaluation

Model	AIME24	AIME25	MATH500	GPQA-Diamond
s1-32B	35.4	25.8	88.6	48.0
s1.1-32B	52.9	41.7	93.4	62.6
Qwen2.5-32B-Instruct	15.8	10.4	80.4	47.0
Autoregressive-32B	54.6	45.0	92.8	61.6
Multiverse-32B-zero	52.1	44.2	92.4	63.6
Multiverse-32B	53.8	45.8	91.8	60.7

Acknowledge

Thanks to the amazing s1 team for their s1.1 dataset as base data, and the Qwen team for their Qwen-2.5-32B-Instruct as base model.

Citation Information

@misc{yang2025multiverselanguagemodelssecretly,
      title={Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation}, 
      author={Xinyu Yang and Yuwei An and Hongyi Liu and Tianqi Chen and Beidi Chen},
      year={2025},
      eprint={2506.09991},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2506.09991}, 
}