Instructions to use PolarSeeker/OpenSeeker-v1-30B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PolarSeeker/OpenSeeker-v1-30B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="PolarSeeker/OpenSeeker-v1-30B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("PolarSeeker/OpenSeeker-v1-30B-SFT")
model = AutoModelForMultimodalLM.from_pretrained("PolarSeeker/OpenSeeker-v1-30B-SFT")
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 PolarSeeker/OpenSeeker-v1-30B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PolarSeeker/OpenSeeker-v1-30B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PolarSeeker/OpenSeeker-v1-30B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PolarSeeker/OpenSeeker-v1-30B-SFT

SGLang

How to use PolarSeeker/OpenSeeker-v1-30B-SFT 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 "PolarSeeker/OpenSeeker-v1-30B-SFT" \
    --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": "PolarSeeker/OpenSeeker-v1-30B-SFT",
		"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 "PolarSeeker/OpenSeeker-v1-30B-SFT" \
        --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": "PolarSeeker/OpenSeeker-v1-30B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PolarSeeker/OpenSeeker-v1-30B-SFT with Docker Model Runner:
```
docker model run hf.co/PolarSeeker/OpenSeeker-v1-30B-SFT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data

OpenSeeker is an open-source search agent system that democratizes access to frontier search capabilities by fully open-sourcing its training data. We fine-tuned Qwen3-30B-A3B-Thinking-2507 with 11.7K training examples and achieved state-of-the-art performance on frontier search benchmarks:

Highlights

Superior performance on search agent benchmarks: 48.4 on BrowseComp-ZH, 29.5 on BrowseComp, 74.0 on xbench-DeepSearch, and 59.4 on WideSearch.
Competitive with industrial models: Surpasses Tongyi DeepResearch on BrowseComp-ZH (48.4% vs. 46.7%), despite Tongyi DeepResearch being trained with extensive continual pre-training, supervised fine-tuning, and reinforcement learning.
Fully open-sourced training data: The first work by a purely academic team to achieve state-of-the-art performance while simultaneously open-sourcing the full training data.