Instructions to use dongguanting/Qwen3-14B-ARPO-DeepSearch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dongguanting/Qwen3-14B-ARPO-DeepSearch with Transformers:

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

pipe = pipeline("text-generation", model="dongguanting/Qwen3-14B-ARPO-DeepSearch")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dongguanting/Qwen3-14B-ARPO-DeepSearch")
model = AutoModelForCausalLM.from_pretrained("dongguanting/Qwen3-14B-ARPO-DeepSearch")
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 dongguanting/Qwen3-14B-ARPO-DeepSearch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dongguanting/Qwen3-14B-ARPO-DeepSearch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dongguanting/Qwen3-14B-ARPO-DeepSearch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dongguanting/Qwen3-14B-ARPO-DeepSearch

SGLang

How to use dongguanting/Qwen3-14B-ARPO-DeepSearch 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 "dongguanting/Qwen3-14B-ARPO-DeepSearch" \
    --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": "dongguanting/Qwen3-14B-ARPO-DeepSearch",
		"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 "dongguanting/Qwen3-14B-ARPO-DeepSearch" \
        --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": "dongguanting/Qwen3-14B-ARPO-DeepSearch",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dongguanting/Qwen3-14B-ARPO-DeepSearch with Docker Model Runner:
```
docker model run hf.co/dongguanting/Qwen3-14B-ARPO-DeepSearch
```

Enhance model card with metadata, abstract, overview, and usage example

by nielsr HF Staff - opened Jul 29, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+124

-4

Enhance model card with metadata, abstract, overview, and usage example9fd46d2a

nielsr

Jul 29, 2025

This PR significantly enhances the model card by:

Adding pipeline_tag: text-generation to ensure the model appears in relevant searches and filter categories.
Adding library_name: transformers to indicate compatibility with the Hugging Face Transformers library, enabling the "Use in Transformers" widget.
Including relevant tags such as agent, tool-use, reinforcement-learning, qwen, and llm for better categorization.
Expanding the model card content with the paper's abstract, a detailed overview including key highlights and visuals from the project's GitHub, and comprehensive usage instructions for text generation with the transformers library.
Consolidating existing links and adding new ones (Hugging Face collection, Hugging Face Space demo) for a richer set of resources.
Incorporating additional valuable sections from the GitHub README, such as Citation, Acknowledgements, and Contact information.

dongguanting changed pull request status to merged Aug 12, 2025

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

Tap or paste here to upload images

· Sign up or log in to comment