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

Libraries

How to use MiniMaxAI/SynLogic-7B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/MiniMaxAI/SynLogic-7B

SGLang

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

Docker Model Runner
How to use MiniMaxAI/SynLogic-7B with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/SynLogic-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SynLogic-7B: Logical Reasoning Model

🐙 GitHub Repo: https://github.com/MiniMax-AI/SynLogic
📜 Paper (arXiv): https://arxiv.org/abs/2505.19641
🤗 Dataset: SynLogic on Hugging Face

Model Overview

SynLogic-7B is a logical reasoning model built on Qwen2.5-7B-Base and trained using reinforcement learning on our SynLogic dataset. Despite its smaller size, the model demonstrates strong logical reasoning capabilities and effective generalization to mathematical domains.

Key Features

Comprehensive Logical Reasoning: Trained on 27 diverse logical reasoning tasks (adapted for 7B scale) including Sudoku, Game of 24, Cipher, and more
Verifiable Training: All training data can be automatically verified, enabling effective reinforcement learning
Strong Generalization: Transfers logical reasoning skills to mathematical problem-solving without explicit math training
Efficient Scale: Achieves strong performance with a more compact 7B parameter model

Performance Highlights

Logical Reasoning Benchmarks

Model	KOR-Bench	BBH	BBEH
Qwen2.5-7B-Instruct	38.6	62.7	12.4
SynLogic-7B	48.1	66.5	8.0

Mathematical Benchmarks

Model	AIME 2024	MATH 500	AMC 2023
Qwen2.5-7B-Base	0.3	64.6	30.0
Qwen2.5-7B-Instruct	6.3	76.4	52.5
SynLogic-7B	10.0	71.8	55.0

Key Achievements:

+9.5 points improvement over Qwen2.5-7B-Instruct on KOR-Bench
Strong mathematical generalization with 10.0% on AIME 2024 (vs 6.3% for instruct model)
Effective logical reasoning training despite smaller model size

Training Details

Base Model: Qwen2.5-7B-Base
Training Algorithm: GRPO (Group Relative Policy Optimization)
Dataset: 16k SynLogic-Easy samples with controlled difficulty optimized for 7B scale
Reward Design: Binary rewards based on format adherence and correctness verification
Response Length: Achieves average response lengths of ~2,500 tokens with emerging reflection behaviors

Citation

@misc{liu2025synlogic,
      title={SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond}, 
      author={Junteng Liu and Yuanxiang Fan and Zhuo Jiang and Han Ding and Yongyi Hu and Chi Zhang and Yiqi Shi and Shitong Weng and Aili Chen and Shiqi Chen and Yunan Huang and Mozhi Zhang and Pengyu Zhao and Junjie Yan and Junxian He},
      year={2025},
      eprint={2505.19641},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2505.19641}, 
}