From 782e2019996c3836c20f3f5eb3024223c5b9bcbb Mon Sep 17 00:00:00 2001
From: Amil Dravid <46203730+avdravid@users.noreply.github.com>
Date: Thu, 18 Jul 2024 19:11:12 -0700
Subject: [PATCH] Update README.md

---
 README.md | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index c5f2e85..f3a23ac 100644
--- a/README.md
+++ b/README.md
@@ -20,9 +20,10 @@ $ pip install -r requirements.txt
 ```
 
 ### Files
-The files needed to create *w2w* space, load models, train classifiers, etc. can be downloaded at this [link](https://drive.google.com/file/d/1W1_klpdeCZr5b0Kdp7SaS7veDV2ZzfbB/view?usp=sharing). Keep the folder structure and place it into the `weights2weights` folder containing all the code.
+The Hugging Face model card is available at this [link] (https://huggingface.co/Snapchat/weights2weights). You can find info on all the files there. 
+The files needed to create *w2w* space, load models, train classifiers, etc. can be downloaded at this [link](https://drive.google.com/file/d/1W1_klpdeCZr5b0Kdp7SaS7veDV2ZzfbB/view?usp=sharing), or this [link](https://huggingface.co/Snapchat/weights2weights/tree/main/files). Keep the folder structure and place the `files` folder into the `weights2weights` folder containing all the code.
 
-The dataset of full model weights (i.e. the full Dreambooth LoRA parameters) will be released within the next week (by June 21). 
+The dataset of full model weights (i.e. the full Dreambooth LoRA parameters) is available [here] (https://huggingface.co/Snapchat/weights2weights/tree/main/weights_datasets).  
 
 ## Sampling 
 We provide an interactive notebook for sampling new identity-encoding models from *w2w* space in `sampling/sampling.ipynb`. Instructions are provided in the notebook. Once a model is sampled, you can run typical inference with various text prompts and generation seeds as with a typical personalized model.