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

Libraries

How to use pixas/DECS_NRP_DETECTOR with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pixas/DECS_NRP_DETECTOR")
model = AutoModelForCausalLM.from_pretrained("pixas/DECS_NRP_DETECTOR")
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 pixas/DECS_NRP_DETECTOR with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pixas/DECS_NRP_DETECTOR

SGLang

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

Docker Model Runner
How to use pixas/DECS_NRP_DETECTOR with Docker Model Runner:
```
docker model run hf.co/pixas/DECS_NRP_DETECTOR
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DECS NRP Detector

This repository contains the NRP (Necessary Reasoning Prefix) detector model used in the DECS algorithm, as presented in the paper Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling.

The NRP detector is designed to determine whether a given reasoning chunk contains the ground truth signal, enabling surgically precise token-level rewards to reduce "overthinking" in reasoning models.

Project Page: https://pixas.github.io/decs-iclr26-site/
Repository: https://github.com/pixas/DECS
Paper: arXiv:2509.25827

Usage

According to the official repository, you can deploy the NRP detector using vLLM:

vllm serve --model pixas/DECS_NRP_DETECTOR --port 10041

Citation

If you use this model, please cite the following work:

@inproceedings{jiang2026decs,
  title     = {Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling},
  author    = {Jiang, Shuyang and Tao, Xiaofeng and Zhang, Kui and Xiao, Yanghua},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2026},
  note      = {Oral},
  url       = {https://arxiv.org/abs/2509.25827}
}