Instructions to use dongguanting/Qwen2.5-3B-ARPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dongguanting/Qwen2.5-3B-ARPO with Transformers:

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

pipe = pipeline("text-generation", model="dongguanting/Qwen2.5-3B-ARPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dongguanting/Qwen2.5-3B-ARPO")
model = AutoModelForCausalLM.from_pretrained("dongguanting/Qwen2.5-3B-ARPO", 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 dongguanting/Qwen2.5-3B-ARPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dongguanting/Qwen2.5-3B-ARPO"
# 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/Qwen2.5-3B-ARPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dongguanting/Qwen2.5-3B-ARPO

SGLang

How to use dongguanting/Qwen2.5-3B-ARPO 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/Qwen2.5-3B-ARPO" \
    --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/Qwen2.5-3B-ARPO",
		"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/Qwen2.5-3B-ARPO" \
        --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/Qwen2.5-3B-ARPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dongguanting/Qwen2.5-3B-ARPO with Docker Model Runner:
```
docker model run hf.co/dongguanting/Qwen2.5-3B-ARPO
```

Enhance model card with metadata, abstract, usage, and comprehensive links

by nielsr HF Staff - opened Jul 29, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+116

-4

nielsr

Jul 29, 2025

This PR significantly enhances the model card by:

Adding essential metadata: license (MIT), pipeline_tag (text-generation), library_name (transformers), and additional tags (agents, tool-use, conversational, qwen2). This ensures proper categorization, discoverability, and compatibility information on the Hugging Face Hub.
Expanding the content to include the paper abstract, a visual overview from the official repository, and comprehensive links to the paper and related Hugging Face collections.
Providing a practical Python usage example with the transformers library, demonstrating how to load the model and perform text generation using its chat template.
Including the BibTeX citation for proper academic attribution.
Adding sections for license information, acknowledgements, and contact details.

This update will provide users with a more complete understanding of the model's capabilities and how to use it, greatly improving the model's utility and discoverability on the Hugging Face Hub.

Enhance model card with metadata, abstract, usage, and comprehensive linksb91a7ac3

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