LionGuard

Inputs are anonymised and logged to improve LionGuard's moderation models.

Model Selection

Input

Analysis

Enter text to analyze

Category scores will appear here after analysis

Inputs are anonymised and logged to improve LionGuard's moderation models.

Model Selection

No Moderation

OpenAI Moderation

LionGuard is a family of open-source content moderation models specifically designed for Singapore's multilingual environment. Optimized for Singapore’s linguistic mix, including Singlish, Mandarin, Malay, and Tamil, LionGuard delivers accurate moderation grounded in local usage and cultural nuance.

Developed by GovTech Singapore.

Open-Sourced Models

LionGuard 2.1 LionGuard 2 LionGuard 2 Lite LionGuard 1

Open-Sourced Datasets

Subset of Training Data RabakBench

Blog Posts

LionGuard 2 LionGuard

Research Papers

LionGuard 2 (arXiv:2507.05980) RabakBench (arXiv:2507.15339) LionGuard 1 (arXiv:2407.10995)

Option 1: Self-Host the Classifier

Integrate LionGuard directly into your applications. Toggle between models to see the implementation details.

import os
import numpy as np
from transformers import AutoModel
from google import genai

# Load model directly from HF
model = AutoModel.from_pretrained("govtech/lionguard-2.1", trust_remote_code=True)

# Text to classify
texts = ["hello", "world"]

# Get embeddings (users to input their own Gemini API key)
client = genai.Client(api_key=os.getenv("GEMINI_API_KEY"))
response = client.models.embed_content(
    model="gemini-embedding-001",
    contents=texts
)
embeddings = np.array([emb.values for emb in response.embeddings])

# Run inference
results = model.predict(embeddings)

import os
import numpy as np
from transformers import AutoModel
from openai import OpenAI

# Load model directly from HF
model = AutoModel.from_pretrained(
    "govtech/lionguard-2", 
    trust_remote_code=True
    )

# Get OpenAI embeddings (users to input their own OpenAI API key)
client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
response = client.embeddings.create(
    input="Hello, world!", # users to input their own text
    model="text-embedding-3-large",
    dimensions=3072 # dimensions of the embedding
    )
embeddings = np.array([data.embedding for data in response.data])

# Run LionGuard 2
results = model.predict(embeddings)

import numpy as np
from sentence_transformers import SentenceTransformer
from transformers import AutoModel

# Load model directly from Hub
model = AutoModel.from_pretrained("govtech/lionguard-2-lite", trust_remote_code=True)

# Download model from the 🤗 Hub
embedding_model = SentenceTransformer("google/embeddinggemma-300m")

# Text to classify
texts = ["hello", "world"]

# Add prompt instructions to generate embeddings that are optimized to classify texts according to preset labels
formatted_texts = [f"task: classification | query: {c}" for c in texts]
embeddings = embedding_model.encode(formatted_texts) # NOTE: use encode() instead of encode_documents()

# Run inference
results = model.predict(embeddings)

Option 2: via AI Guardians - Sentinel

Managed service for Singapore public sector agencies.

Visit AI Guardians