diff --git a/examples/cogvideo/README.md b/examples/cogvideo/README.md index 3d22b2bf9931..033b6a17470a 100644 --- a/examples/cogvideo/README.md +++ b/examples/cogvideo/README.md @@ -6,7 +6,7 @@ In a nutshell, LoRA allows adapting pretrained models by adding pairs of rank-de - Previous pretrained weights are kept frozen so that model is not prone to [catastrophic forgetting](https://www.pnas.org/doi/10.1073/pnas.1611835114). - Rank-decomposition matrices have significantly fewer parameters than original model, which means that trained LoRA weights are easily portable. -- LoRA attention layers allow to control to which extent the model is adapted toward new training images via a `scale` parameter. +- LoRA attention layers allow you to control to which extent the model is adapted toward new training images via a `scale` parameter. At the moment, LoRA finetuning has only been tested for [CogVideoX-2b](https://huggingface.co/THUDM/CogVideoX-2b).