This is an academic project that can be used to add watermarks to the output of large language models that are invisible to humans but can be detected by specific algorithms, and to trace its users.
The result of watermarking the model's output.
so robustness.
Hi @jianuo , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.
· Sign up or log in to comment