Instructions to use sxiong/DeepControl-Qwen2.5-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sxiong/DeepControl-Qwen2.5-7B with Transformers:

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

pipe = pipeline("text-generation", model="sxiong/DeepControl-Qwen2.5-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sxiong/DeepControl-Qwen2.5-7B")
model = AutoModelForCausalLM.from_pretrained("sxiong/DeepControl-Qwen2.5-7B", device_map="auto")
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 Settings

vLLM

How to use sxiong/DeepControl-Qwen2.5-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sxiong/DeepControl-Qwen2.5-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sxiong/DeepControl-Qwen2.5-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sxiong/DeepControl-Qwen2.5-7B

SGLang

How to use sxiong/DeepControl-Qwen2.5-7B 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 "sxiong/DeepControl-Qwen2.5-7B" \
    --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": "sxiong/DeepControl-Qwen2.5-7B",
		"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 "sxiong/DeepControl-Qwen2.5-7B" \
        --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": "sxiong/DeepControl-Qwen2.5-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sxiong/DeepControl-Qwen2.5-7B with Docker Model Runner:
```
docker model run hf.co/sxiong/DeepControl-Qwen2.5-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DeepControl-Qwen2.5-7B

Deep search agent checkpoint from Qwen2.5-7B-Instruct under Adaptive Information Control for Search-Augmented LLM Reasoning.

Quick start

See our repo DeepControl for more details.

Recommended Configuration:

Setting	Value
Inference dtype	BF16
Context length	8,192
Generation temperature	0
Maximum new tokens per action	512
Maximum agent turns	8
Retrieval top-k	5
Retrieval corpus	Wikipedia 2018 (`wiki18`)

For example, the model server can be started with:

vllm serve <MODEL_PATH_OR_HF_REPO> \
  --dtype bfloat16 \
  --max-model-len 8192

Loading the model alone does not provide retrieval. It requires the DeepControl system prompt, action parser, and wiki18 corpus.

Citation

@article{xiong2026adaptive,
  title={Adaptive Information Control for Search-Augmented LLM Reasoning},
  author={Xiong, Siheng and Gungordu, Oguzhan and Kerce, James C and Fekri, Faramarz},
  journal={arXiv preprint arXiv:2602.01672},
  year={2026}
}