Instructions to use Satori-reasoning/Satori-7B-Round2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Satori-reasoning/Satori-7B-Round2 with Transformers:

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

pipe = pipeline("text-generation", model="Satori-reasoning/Satori-7B-Round2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Satori-reasoning/Satori-7B-Round2")
model = AutoModelForCausalLM.from_pretrained("Satori-reasoning/Satori-7B-Round2")
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 Settings

vLLM

How to use Satori-reasoning/Satori-7B-Round2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Satori-reasoning/Satori-7B-Round2"
# 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-7B-Round2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Satori-reasoning/Satori-7B-Round2

SGLang

How to use Satori-reasoning/Satori-7B-Round2 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-7B-Round2" \
    --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-7B-Round2",
		"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-7B-Round2" \
        --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-7B-Round2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Satori-reasoning/Satori-7B-Round2 with Docker Model Runner:
```
docker model run hf.co/Satori-reasoning/Satori-7B-Round2
```

Add Github link, Transformers library, pipeline tag

by nielsr HF Staff - opened Feb 9, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+16

-1

Files changed (1) hide show

README.md +16 -1

README.md CHANGED Viewed

@@ -1,5 +1,18 @@
 ---
 license: apache-2.0
 datasets:
 - Satori-reasoning/Satori_FT_data
 - Satori-reasoning/Satori_RL_data
@@ -112,7 +125,7 @@ Satori-7B-Round2 achieves SOTA performance and outperforms Qwen-2.5-Math-7B-Inst
 |           | OpenMath2-Llama3.1-8B     | 90.5 | 67.8 | 28.9 | 37.5 | 6.7  | 46.3 |
 |           | NuminaMath-7B-CoT         | 78.9 | 54.6 | 15.9 | 20.0 | 10.0 | 35.9 |
 |           | Qwen-2.5-7B-Instruct      | 91.6 | 75.5 | 35.5 | 52.5 | 6.7  | 52.4 |
-|           | Qwen-2.5-Math-7B-Instruct |95.2  | 83.6 | 41.6 | 62.5 | 16.7 | 59.9 |
 |           | **Satori-7B-Round2**  | 93.9 | 83.6 | 48.5 | 72.5 | 23.3 | **64.4** |
 ### **General Domain Reasoning Benchmarks**
@@ -140,6 +153,8 @@ Please refer to our blog and research paper for more technical details of Satori
  - [Blog](https://satori-reasoning.github.io/blog/satori/)
  - [Paper](https://arxiv.org/pdf/2502.02508)
 # **Citation**
 If you find our model and data helpful, please cite our paper:
 ```

 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+datasets:
+- Satori-reasoning/Satori_FT_data
+- Satori-reasoning/Satori_RL_data
+base_model:
+- Qwen/Qwen2.5-Math-7B
+---
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 datasets:
 - Satori-reasoning/Satori_FT_data
 - Satori-reasoning/Satori_RL_data
 |           | OpenMath2-Llama3.1-8B     | 90.5 | 67.8 | 28.9 | 37.5 | 6.7  | 46.3 |
 |           | NuminaMath-7B-CoT         | 78.9 | 54.6 | 15.9 | 20.0 | 10.0 | 35.9 |
 |           | Qwen-2.5-7B-Instruct      | 91.6 | 75.5 | 35.5 | 52.5 | 6.7  | 52.4 |
+|           | Qwen-2.5-Math-7B-Instruct | 95.2 | 83.6 | 41.6 | 62.5 | 16.7 | 59.9 |
 |           | **Satori-7B-Round2**  | 93.9 | 83.6 | 48.5 | 72.5 | 23.3 | **64.4** |
 ### **General Domain Reasoning Benchmarks**
  - [Blog](https://satori-reasoning.github.io/blog/satori/)
  - [Paper](https://arxiv.org/pdf/2502.02508)
+For code, see https://github.com/Satori-reasoning/Satori
 # **Citation**
 If you find our model and data helpful, please cite our paper:
 ```