arpytanshu/llm-watermark
re-implementaion of "A watermark for Large Language Models" ( https://arxiv.org/abs/2301.10226 )
This project helps content creators, educators, or anyone generating text with Large Language Models (LLMs) to identify if a piece of text was created by a specific LLM. You input a text prompt and receive generated text that contains an undetectable 'watermark'. Later, you can check any text to see if it carries this unique mark, which helps verify its origin.
No commits in the last 6 months.
Use this if you need to subtly mark LLM-generated content to later prove its source or distinguish it from human-written text.
Not ideal if you require a highly visible or obvious attribution method, or if you need to detect text generated by *any* LLM, rather than one you've specifically watermarked.
Stars
6
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/arpytanshu/llm-watermark"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
meta-llama/llama-cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started...
changyeyu/LLM-RL-Visualized
๐100+ ๅๅ LLM / RL ๅ็ๅพ๐๏ผใๅคงๆจกๅ็ฎๆณใไฝ่ ๅทจ็ฎ๏ผ๐ฅ๏ผ100+ LLM/RL Algorithm Maps ๏ผ
mindspore-lab/step_into_llm
MindSpore online courses: Step into LLM
kyegomez/LFM
An open source implementation of LFMs from Liquid AI: Liquid Foundation Models