Instructions to use RUC-AIBOX/Qwen-32B-SimpleDeepSearcher with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RUC-AIBOX/Qwen-32B-SimpleDeepSearcher with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RUC-AIBOX/Qwen-32B-SimpleDeepSearcher")
model = AutoModelForCausalLM.from_pretrained("RUC-AIBOX/Qwen-32B-SimpleDeepSearcher")
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 RUC-AIBOX/Qwen-32B-SimpleDeepSearcher with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/RUC-AIBOX/Qwen-32B-SimpleDeepSearcher

SGLang

How to use RUC-AIBOX/Qwen-32B-SimpleDeepSearcher 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 "RUC-AIBOX/Qwen-32B-SimpleDeepSearcher" \
    --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": "RUC-AIBOX/Qwen-32B-SimpleDeepSearcher",
		"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 "RUC-AIBOX/Qwen-32B-SimpleDeepSearcher" \
        --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": "RUC-AIBOX/Qwen-32B-SimpleDeepSearcher",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RUC-AIBOX/Qwen-32B-SimpleDeepSearcher with Docker Model Runner:
```
docker model run hf.co/RUC-AIBOX/Qwen-32B-SimpleDeepSearcher
```

Qwen-32B-SimpleDeepSearcher / README.md

nielsr HF Staff

Improve model card for Qwen-32B-CyberSearcher with paper, code, description, and metadata

5052152 verified 8 months ago

5.02 kB

library_name: transformers
pipeline_tag: text-generation
license: mit
tags:
  - generated_from_trainer
  - deep-search
  - retrieval-augmented-generation
  - web-agent
  - qwen
model-index:
  - name: Qwen-32B-CyberSearcher
    results: []

Qwen-32B-CyberSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis

This model is a 32B parameter variant part of the SimpleDeepSearcher framework, presented in the paper SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis.

Code: https://github.com/RUCAIBox/SimpleDeepSearcher

SimpleDeepSearcher Logo

Model description

SimpleDeepSearcher is a lightweight yet effective framework for enhancing Large Language Models (LLMs) in complex deep search scenarios that require multi-step reasoning and iterative information retrieval. It addresses critical limitations of existing Retrieval-Augmented Generation (RAG) systems by strategically synthesizing high-quality training data from realistic user interactions in live web search environments, coupled with a multi-criteria curation strategy. This approach enables efficient supervised fine-tuning (SFT) with only a small amount of curated data, establishing SFT as a viable pathway for building efficient deep search systems with reduced computational cost and development complexity.

Key Contributions

A real web-based data synthesis framework that simulates realistic user search behaviors, generating multi-turn reasoning and search trajectories.
A multi-criteria data curation strategy that jointly optimizes both input question selection and output response filtering through orthogonal filtering dimensions.
Experimental results demonstrate that SFT on only 871 curated samples enables SimpleDeepSearcher to outperform strong baselines (especially RL-based baselines) on both in-domain and out-of-domain benchmarks.

Framework Overview

SimpleDeepSearcher achieves intelligent search through efficient supervised fine-tuning (SFT) using minimal, high-quality training data constructed via a systematic data synthesis and curation pipeline.

SimpleDeepSearcher Pipeline

Overall Performance

SimpleDeepSearcher consistently outperforms all baselines across five benchmark datasets, including both in-domain (2Wiki, MuSiQue) and out-of-domain (Bamboogle, FRAMES, GAIA) settings, demonstrating strong generalization and high data efficiency.

Overall Performance

Intended uses & limitations

This model is intended for advanced deep search scenarios where large language models need to perform multi-step reasoning and iterative information retrieval through web searches. It can be utilized as a core component for building efficient and effective deep search systems.

Limitations may include dependency on the quality of synthesized training data and the performance of the underlying web search API.

Training and evaluation data

The model was fine-tuned via Supervised Fine-tuning (SFT) on only 871 curated samples. This high-quality training data was synthesized by simulating realistic user interactions in live web search environments, followed by a multi-criteria curation strategy that optimized the diversity and quality of input and output.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3.0

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu124
Datasets 2.19.0
Tokenizers 0.20.3

Citation

Please kindly cite our report if they are helpful for your research:

@article{sun2025simpledeepsearcher,
  title={SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis},
  author={Sun, Shuang and Song, Huatong and Wang, Yuhao and Ren, Ruiyang and Jiang, Jinhao and Zhang, Junjie and Bai, Fei and Deng, Jia and Zhao, Wayne Xin and Liu, Zheng and others},
  journal={arXiv preprint arXiv:2505.16834},
  year={2025}
}

License

This project is released under the MIT License.

Contact

For any questions or feedback, please reach out to us at sunshuanguns@gmail.com or songhuatong123@ruc.edu.cn.