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

Libraries

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

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

pipe = pipeline("text-generation", model="RUC-AIBOX/QwQ-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/QwQ-32B-SimpleDeepSearcher")
model = AutoModelForCausalLM.from_pretrained("RUC-AIBOX/QwQ-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/QwQ-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/QwQ-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/QwQ-32B-SimpleDeepSearcher",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Improve model card: Add description, paper/code links, relevant tags, license, and pipeline tag

by nielsr HF Staff - opened Oct 9, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+60

-7

nielsr

Oct 9, 2025

This PR significantly enhances the model card for Online-Searcher-QwQ-32B.

It provides a detailed model description, intended uses, and training data information, drawing extensively from the paper's abstract and the project's GitHub README.

It adds direct links to the scientific paper, SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis, and the GitHub repository, RUCAIBox/SimpleDeepSearcher.

Visuals illustrating the project's overview, performance, and framework are embedded directly from the GitHub repository.

Additionally, the metadata is updated by:

Specifying the license as mit, as indicated in the GitHub repository.
Adding the pipeline_tag: text-generation to enable better discoverability on the Hub.
Adding relevant tags: deep-search, web-agent, and rag, which accurately describe the model's functionality.
The library_name: transformers is retained, as the model is compatible with the 🤗 Transformers library, allowing for an automated usage snippet on the Hub.

Finally, a citation section is included with the BibTeX entry from the paper, and the initial auto-generated comment has been removed as the model card is now complete.

Improve model card: Add description, paper/code links, relevant tags, license, and pipeline tag27499fad

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment