Instructions to use DORAEMONG/PRO-STEP-Policy-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DORAEMONG/PRO-STEP-Policy-7B with Transformers:

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

pipe = pipeline("text-generation", model="DORAEMONG/PRO-STEP-Policy-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DORAEMONG/PRO-STEP-Policy-7B")
model = AutoModelForCausalLM.from_pretrained("DORAEMONG/PRO-STEP-Policy-7B")
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

vLLM

How to use DORAEMONG/PRO-STEP-Policy-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DORAEMONG/PRO-STEP-Policy-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": "DORAEMONG/PRO-STEP-Policy-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DORAEMONG/PRO-STEP-Policy-7B

SGLang

How to use DORAEMONG/PRO-STEP-Policy-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 "DORAEMONG/PRO-STEP-Policy-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": "DORAEMONG/PRO-STEP-Policy-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 "DORAEMONG/PRO-STEP-Policy-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": "DORAEMONG/PRO-STEP-Policy-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

PRO-STEP: Step-level Process Reward Optimization for RAG (Policy Model)

This is the main policy model for PRO-STEP, a self-improving framework for agentic Retrieval-Augmented Generation. The policy is trained on its own MCTS trajectories scored by an open-source 8B PRM, using step-level DPO.

Backbone: Qwen2.5-7B-Instruct
PRM: DORAEMONG/PRO-STEP-PRM-8B
Preference data: DORAEMONG/PRO-STEP-Preference-Data
Training: DPO (β=0.1) with document-token masking, LoRA r=64/α=128, 1 epoch, 5,000 questions / 15,877 step-level preference pairs
MCTS: K=3 branching, depth 7, 64 rollouts/question, value V(s) = Q̄(s) + α · r̂(s) with α=0.3

Performance (5-dataset, identical FlashRAG eval pipeline)

Method	Train data	HotpotQA	PopQA	2Wiki	Bamboogle	Musique	AVG
Search-R1	~90,000	37.88 / 49.56	40.65 / 46.78	34.87 / 42.50	33.60 / 43.55	12.99 / 21.23	32.00 / 40.72
ReasonRAG	~5,000	36.37 / 47.51	37.78 / 44.87	39.80 / 46.32	38.40 / 46.86	10.59 / 19.22	32.59 / 40.96
StepSearch	~19,000	38.72 / 50.67	39.24 / 44.97	40.38 / 47.12	33.60 / 44.16	13.82 / 23.06	33.15 / 42.00
PRO-STEP (ours) ★	5,000	38.73 / 51.63	40.47 / 47.37	44.07 / 51.43	36.80 / 47.63	12.49 / 22.41	34.51 / 44.09

EM / F1 (Strict EM, token-F1). Bootstrap 95% CI: vs Search-R1 +2.51 EM [+1.01, +4.06], vs ReasonRAG +1.93 EM [+0.46, +3.36].

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("DORAEMONG/PRO-STEP-Policy-7B", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("DORAEMONG/PRO-STEP-Policy-7B")

# Use with FlashRAG SearchR1Pipeline or any agentic-RAG inference loop
# System prompt: see paper Appendix A

Citation

@article{prostep2026,
  title={PRO-STEP: Step-level Process Reward Optimization for Retrieval-Augmented Generation},
  author={...},
  year={2026}
}

Downloads last month: 16

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for DORAEMONG/PRO-STEP-Policy-7B

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(3288)

this model

Quantizations

2 models

DORAEMONG
/

PRO-STEP-Policy-7B

PRO-STEP: Step-level Process Reward Optimization for RAG (Policy Model)

Performance (5-dataset, identical FlashRAG eval pipeline)

Usage

Citation

Model tree for DORAEMONG/PRO-STEP-Policy-7B

Dataset used to train DORAEMONG/PRO-STEP-Policy-7B