AIPython★ 1,067
THU-BPM/MarkLLM
MARKLLM: WATERMARK FOR LLM
MarkLLM — open-source toolkit for watermarks of large language models. Allows embedding, checking and comparing different watermark schemes. Supports popular LLM and integrates via a simple API.
// KEY FEATURES
- Embeds watermarks into LLM texts via the simple embed() function
- Detects presence of marks and evaluates their resistance to attacks
- Compares effectiveness of different watermarking algorithms (KGW, EXP, etc.)
- Supports GPT‑2, LLaMA, Mistral and other models via HuggingFace Transformers
#large-language-models#llm#safety#toolkit#trustworthy-ai#watermark
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram