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

Libraries

How to use ReasoningShield/ReasoningShield-3B with Transformers:

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

pipe = pipeline("text-generation", model="ReasoningShield/ReasoningShield-3B")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ReasoningShield/ReasoningShield-3B", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ReasoningShield/ReasoningShield-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ReasoningShield/ReasoningShield-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ReasoningShield/ReasoningShield-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ReasoningShield/ReasoningShield-3B

SGLang

How to use ReasoningShield/ReasoningShield-3B 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 "ReasoningShield/ReasoningShield-3B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ReasoningShield/ReasoningShield-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ReasoningShield/ReasoningShield-3B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ReasoningShield/ReasoningShield-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ReasoningShield/ReasoningShield-3B with Docker Model Runner:
```
docker model run hf.co/ReasoningShield/ReasoningShield-3B
```

Update pipeline tag to text-classification and add paper link

by nielsr HF Staff - opened Oct 16, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+35

-32

nielsr

Oct 16, 2025

This PR improves the model card for ReasoningShield by:

Updating the pipeline_tag: The pipeline_tag has been changed from text-generation to text-classification. This more accurately reflects the model's primary function of safety detection and moderation over reasoning traces, where it classifies text into predefined safety risk levels. This change will enhance the model's discoverability on the Hub under the correct task category.
Adding a paper link: A direct link to the associated paper, ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models, has been added to the model card content for improved visibility and accessibility of the research.

Please review these changes.

Update pipeline tag to text-classification and add paper linkbcfed0d5

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment