From 1a7e4a03378cd34d3da766fa13f8aa805b1c00d9 Mon Sep 17 00:00:00 2001 From: Sanyam Bhutani Date: Fri, 15 Nov 2024 05:38:31 -0800 Subject: [PATCH] Update README.md --- recipes/quickstart/Multi-Modal-RAG/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/recipes/quickstart/Multi-Modal-RAG/README.md b/recipes/quickstart/Multi-Modal-RAG/README.md index 30c2f0281..9f4e5b9b9 100644 --- a/recipes/quickstart/Multi-Modal-RAG/README.md +++ b/recipes/quickstart/Multi-Modal-RAG/README.md @@ -2,7 +2,7 @@ ## Story Overview: Multi-Modal RAG using `Llama-3.2-11B` model: -- **Data Labeling and Preparation:** We start by downloading 5000 images of clothing items and labeling them using 11B model +- **Data Labeling and Preparation:** We start by downloading 5000 images of clothing items and labeling them using `Llama-3.2-11B-Vision-Instruct` model - **Cleaning Labels:** With the labels based on the notebook above, we will then clean the dataset and prepare it for RAG - **Building Vector DB and RAG Pipeline:** With the final clean dataset, we can use descriptions and 11B model to generate recommendations