Instructions to use Gen-Verse/ReasonFlux-PRM-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gen-Verse/ReasonFlux-PRM-7B with Transformers:

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

pipe = pipeline("text-generation", model="Gen-Verse/ReasonFlux-PRM-7B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gen-Verse/ReasonFlux-PRM-7B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Gen-Verse/ReasonFlux-PRM-7B", trust_remote_code=True, 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 Gen-Verse/ReasonFlux-PRM-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Gen-Verse/ReasonFlux-PRM-7B

SGLang

How to use Gen-Verse/ReasonFlux-PRM-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 "Gen-Verse/ReasonFlux-PRM-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": "Gen-Verse/ReasonFlux-PRM-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 "Gen-Verse/ReasonFlux-PRM-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": "Gen-Verse/ReasonFlux-PRM-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Gen-Verse/ReasonFlux-PRM-7B with Docker Model Runner:
```
docker model run hf.co/Gen-Verse/ReasonFlux-PRM-7B
```

Lingaaaaaaa commited on Jun 24, 2025

Commit

835c480

verified ·

1 Parent(s): 3fd1042

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -16

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ library_name: transformers
 # ReasonFlux-PRM
-[Code](https://github.com/Gen-Verse/ReasonFlux) | [Paper]()
 We introduce ReasonFlux-PRM, a trajectory-aware process reward model (PRM) explicitly designed to evaluate the trajectory-response type of reasoning traces. ReasonFlux-PRM incorporates both step-level and trajectory-level supervision, enabling fine-grained reward assignment aligned with structured chain-of-thought data. ReasonFlux-PRM is able to support both offline and online reward supervision, by selecting high-quality training data for model distillation, providing dense process-level rewards for policy optimization during reinforcement learning, and enabling reward-guided test-time scaling.
@@ -53,21 +53,7 @@ We introduce ReasonFlux-PRM, a trajectory-aware process reward model (PRM) expli
 @article{zou2025reasonfluxprm,
   title={ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs},
   author={Zou, Jiaru and Yang, Ling and Gu, Jingwen and Qiu, Jiahao and Shen, Ke and He, Jingrui and Wang, Mengdi},
-  journal={arXiv preprint arXiv:2506.},
-  year={2025}
-}
-@article{yang2025reasonflux,
-  title={ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates},
-  author={Yang, Ling and Yu, Zhaochen and Cui, Bin and Wang, Mengdi},
-  journal={arXiv preprint arXiv:2502.06772},
-  year={2025}
-}
-@article{wang2025cure,
-  title={Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning},
-  author={Wang, Yinjie and Yang, Ling and Tian, Ye and Shen, Ke and Wang, Mengdi},
-  journal={arXiv preprint arXiv:2506.03136},
   year={2025}
 }
 ```

 # ReasonFlux-PRM
+[Code](https://github.com/Gen-Verse/ReasonFlux) | [Paper](https://arxiv.org/abs/2506.18896)
 We introduce ReasonFlux-PRM, a trajectory-aware process reward model (PRM) explicitly designed to evaluate the trajectory-response type of reasoning traces. ReasonFlux-PRM incorporates both step-level and trajectory-level supervision, enabling fine-grained reward assignment aligned with structured chain-of-thought data. ReasonFlux-PRM is able to support both offline and online reward supervision, by selecting high-quality training data for model distillation, providing dense process-level rewards for policy optimization during reinforcement learning, and enabling reward-guided test-time scaling.
 @article{zou2025reasonfluxprm,
   title={ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs},
   author={Zou, Jiaru and Yang, Ling and Gu, Jingwen and Qiu, Jiahao and Shen, Ke and He, Jingrui and Wang, Mengdi},
+  journal={arXiv preprint arXiv:2506.18896},
   year={2025}
 }
 ```