ottoline/ottoline-toxicity-guard

Overview

Flags abusive and harassing messages in English and Indonesian chat.

ottoline/ottoline-toxicity-guard is a 140M-parameter text classification model, published in safetensors under the apache-2.0 license.

Intended use

• Text classification in en, id.
• Research, prototypes and products that keep a person in the loop.
• Fine-tuning as a starting point for a narrower task.

How to use

# Command-line client (planned; the shape may change)
pace pull ottoline/ottoline-toxicity-guard

# Python (planned)
from openpace import load
model = load("ottoline/ottoline-toxicity-guard")

Limitations

• It can state wrong things fluently. Check facts that matter.
• Quality drops on languages and domains that were thin in its training data.
• It reflects biases present in public text.

License

Released under apache-2.0. Read the license file before using the weights commercially.