From 3c4b64785f2f0b68da55e058830e6feb168fd6a2 Mon Sep 17 00:00:00 2001 From: Sayak Paul Date: Tue, 7 Feb 2023 11:11:36 +0530 Subject: [PATCH] Update README.md --- examples/image_classification/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/image_classification/README.md b/examples/image_classification/README.md index 8973aae..24828f6 100644 --- a/examples/image_classification/README.md +++ b/examples/image_classification/README.md @@ -2,6 +2,6 @@ [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/sayakpaul/peft/blob/example/img-cls/examples/image_classification/image_classification_peft_lora.ipynb) -We provide a notebook (`image_classification_peft_lora.ipynb`) where we learn how to use [LoRA](https://arxiv.org/abs/2106.09685) from 🤗 PEFT to fine-tune an image classification modelby ONLY using **0.6%** of the original trainable parameters of the model. +We provide a notebook (`image_classification_peft_lora.ipynb`) where we learn how to use [LoRA](https://arxiv.org/abs/2106.09685) from 🤗 PEFT to fine-tune an image classification modelby ONLY using **0.7%** of the original trainable parameters of the model. -LoRA adds low-rank "update matrices" to certain blocks in the underlying model (in this case the attention blocks) and ONLY trains those matrices during fine-tuning. During inference, these update matrices are _merged_ with the original model parameters. For more details, check out the [original LoRA paper](https://arxiv.org/abs/2106.09685). \ No newline at end of file +LoRA adds low-rank "update matrices" to certain blocks in the underlying model (in this case the attention blocks) and ONLY trains those matrices during fine-tuning. During inference, these update matrices are _merged_ with the original model parameters. For more details, check out the [original LoRA paper](https://arxiv.org/abs/2106.09685).