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

Libraries

How to use Satori-reasoning/Satori-RM-7B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("Satori-reasoning/Satori-RM-7B")
model = AutoModel.from_pretrained("Satori-reasoning/Satori-RM-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Satori-reasoning/Satori-RM-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Satori-reasoning/Satori-RM-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": "Satori-reasoning/Satori-RM-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Satori-reasoning/Satori-RM-7B

SGLang

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

Docker Model Runner
How to use Satori-reasoning/Satori-RM-7B with Docker Model Runner:
```
docker model run hf.co/Satori-reasoning/Satori-RM-7B
```

Satori-RM-7B / README.md

maohaos2

Update README.md

df808b1 verified 12 months ago

preview code

raw

history blame contribute delete

1.54 kB

metadata

license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model:
  - Satori-reasoning/Satori-SFT-7B

Satori-RM-7B is the Outcome Reward model for training our RL model Satori-7B-Round2. The usage of Satori-RM-7B can be found in our released RL training code.

Resources

We provide our training datasets:

Full format tuning dataset with 300K unique questions.
RL dataset with 550K unique questions.

Please refer to our blog and research paper for more technical details of Satori.

Blog
Paper

For code, see https://github.com/Satori-reasoning/Satori

Citation

If you find our model and data helpful, please cite our paper:

@misc{shen2025satorireinforcementlearningchainofactionthought,
      title={Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search}, 
      author={Maohao Shen and Guangtao Zeng and Zhenting Qi and Zhang-Wei Hong and Zhenfang Chen and Wei Lu and Gregory Wornell and Subhro Das and David Cox and Chuang Gan},
      year={2025},
      eprint={2502.02508},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.02508}, 
}