Instructions to use bmbgsj/ProRAG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bmbgsj/ProRAG with Transformers:

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

pipe = pipeline("text-generation", model="bmbgsj/ProRAG")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bmbgsj/ProRAG")
model = AutoModelForCausalLM.from_pretrained("bmbgsj/ProRAG")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bmbgsj/ProRAG with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bmbgsj/ProRAG

SGLang

How to use bmbgsj/ProRAG 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 "bmbgsj/ProRAG" \
    --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": "bmbgsj/ProRAG",
		"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 "bmbgsj/ProRAG" \
        --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": "bmbgsj/ProRAG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bmbgsj/ProRAG with Docker Model Runner:
```
docker model run hf.co/bmbgsj/ProRAG
```

Model Card for ProRAG

This model is a fine-tuned version of Qwen/Qwen3-8B based on the methodology described in the paper associated with arXiv ID: 2601.21912.

Model Details

Base Model: Qwen3-8B
Language: English, Chinese (and others supported by Qwen3)
Paper: View on arXiv
Library: Transformers

💻 Code & Inference

For inference code, usage examples, and reproduction scripts, please refer to our GitHub repository:

👉 Click here to view the GitHub Repository

(Please verify the details and instructions on the GitHub page.)

Citation

If you use this model or the associated paper in your research, please cite:

@misc{wang2026proragprocesssupervisedreinforcementlearning,
      title={ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation}, 
      author={Zhao Wang and Ziliang Zhao and Zhicheng Dou},
      year={2026},
      eprint={2601.21912},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2601.21912}, 
}