From 7a0d2254ef2fb04442fb12f5192ce191f0d54b9c Mon Sep 17 00:00:00 2001 From: mrchatam Date: Fri, 11 Sep 2026 23:27:05 +0000 Subject: [PATCH] docs: fix 'allows to' grammar in advanced diffusion training README --- examples/advanced_diffusion_training/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/advanced_diffusion_training/README.md b/examples/advanced_diffusion_training/README.md index 9d68bf9a825f..cc584bf875cf 100644 --- a/examples/advanced_diffusion_training/README.md +++ b/examples/advanced_diffusion_training/README.md @@ -7,7 +7,7 @@ [DreamBooth](https://huggingface.co/papers/2208.12242) is a method to personalize text2image models like stable diffusion given just a few(3~5) images of a subject. LoRA - Low-Rank Adaption of Large Language Models, was first introduced by Microsoft in [LoRA: Low-Rank Adaptation of Large Language Models](https://huggingface.co/papers/2106.09685) by *Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen* -In a nutshell, LoRA allows to adapt pretrained models by adding pairs of rank-decomposition matrices to existing weights and **only** training those newly added weights. This has a couple of advantages: +In a nutshell, LoRA allows adapting pretrained models by adding pairs of rank-decomposition matrices to existing weights and **only** training those newly added weights. This has a couple of advantages: - Previous pretrained weights are kept frozen so that the model is not prone to [catastrophic forgetting](https://www.pnas.org/doi/10.1073/pnas.1611835114) - Rank-decomposition matrices have significantly fewer parameters than the original model, which means that trained LoRA weights are easily portable. - LoRA attention layers allow to control to which extent the model is adapted towards new training images via a `scale` parameter.