Instructions to use thu-coai/ShieldLM-14B-qwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thu-coai/ShieldLM-14B-qwen with Transformers:

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

pipe = pipeline("text-generation", model="thu-coai/ShieldLM-14B-qwen", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("thu-coai/ShieldLM-14B-qwen", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thu-coai/ShieldLM-14B-qwen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thu-coai/ShieldLM-14B-qwen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thu-coai/ShieldLM-14B-qwen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/thu-coai/ShieldLM-14B-qwen

SGLang

How to use thu-coai/ShieldLM-14B-qwen 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 "thu-coai/ShieldLM-14B-qwen" \
    --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": "thu-coai/ShieldLM-14B-qwen",
		"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 "thu-coai/ShieldLM-14B-qwen" \
        --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": "thu-coai/ShieldLM-14B-qwen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thu-coai/ShieldLM-14B-qwen with Docker Model Runner:
```
docker model run hf.co/thu-coai/ShieldLM-14B-qwen
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Introduction

The ShieldLM model (paper link) initialized from Qwen-14B-Chat. ShieldLM is a bilingual (Chinese and English) safety detector that mainly aims to help to detect safety issues in LLMs' generations. It aligns with general human safety standards, supports fine-grained customizable detection rules, and provides explanations for its decisions. Refer to our github repository for more detailed information.

Usage

Please refer to our github repository for the detailed usage instructions.

Performance

ShieldLM demonstrates impressive detection performance across 4 ID and OOD test sets, compared to strong baselines such as GPT-4, Llama Guard and Perspective API. Refer to our paper for more detailed evaluation results.

Downloads last month: 69

Safetensors

Model size

14B params

Tensor type

BF16

Model tree for thu-coai/ShieldLM-14B-qwen

Quantizations

2 models

Paper for thu-coai/ShieldLM-14B-qwen

ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors

Paper • 2402.16444 • Published Feb 26, 2024