amildravid4292 commited on
Commit
17f0c3d
·
verified ·
1 Parent(s): 7154c0d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -7,17 +7,17 @@ This repository contains the dataset of model weights and utility files for [Int
7
  The `files/` folder contains the files needed in our code [here](https://snap-research.github.io/weights2weights/) in order to conduct sampling, inversion, and editing in *weights2weights* space.
8
  - `files/V.pt`
9
  - 99648x10000 dimensional tensor used to project or unproject LoRA weights onto a principal component representation in *w2w* space or to unproject back into the LoRA space.
10
- - 'files/mean.pt'
11
  - 99648 dimensional tensor of the mean for each parameter in the original LoRA space. Used for projection/unprojection.
12
- - 'files/std.pt'
13
  - 99648 dimensional tensor of the standard deviation for each parameter in the original LoRA space. Used for projection/unprojection.
14
- - 'files/proj_1000pc.pt'
15
  - 64974x1000 dimensional tensor where each row is a 1000-dimensional principal component projection for each identity-encoding model in our dataset of model weights.
16
- - 'files/pinverse.pt'
17
  - Precomputed pseudoinverse of 'proj.pt', used for obtaining the classifier weight space directions given labels.
18
- - 'files/identity_df.pt'
19
  - A pandas dataframe with each identity model in our dataset of weights and their associated binary labels. Used for getting labels for training linear classifiers.
20
- - 'files/weight_dimensions.pt'
21
  - A dictionary of the dimensionality for each LoRA module in the diffusion UNet. Used to save models in Diffusers pipeline format.
22
 
23
  **Drag-Based Manipulation**
 
7
  The `files/` folder contains the files needed in our code [here](https://snap-research.github.io/weights2weights/) in order to conduct sampling, inversion, and editing in *weights2weights* space.
8
  - `files/V.pt`
9
  - 99648x10000 dimensional tensor used to project or unproject LoRA weights onto a principal component representation in *w2w* space or to unproject back into the LoRA space.
10
+ - `files/mean.pt`
11
  - 99648 dimensional tensor of the mean for each parameter in the original LoRA space. Used for projection/unprojection.
12
+ - `files/std.pt`
13
  - 99648 dimensional tensor of the standard deviation for each parameter in the original LoRA space. Used for projection/unprojection.
14
+ - `files/proj_1000pc.pt`
15
  - 64974x1000 dimensional tensor where each row is a 1000-dimensional principal component projection for each identity-encoding model in our dataset of model weights.
16
+ - `files/pinverse.pt`
17
  - Precomputed pseudoinverse of 'proj.pt', used for obtaining the classifier weight space directions given labels.
18
+ - `files/identity_df.pt`
19
  - A pandas dataframe with each identity model in our dataset of weights and their associated binary labels. Used for getting labels for training linear classifiers.
20
+ - `files/weight_dimensions.pt`
21
  - A dictionary of the dimensionality for each LoRA module in the diffusion UNet. Used to save models in Diffusers pipeline format.
22
 
23
  **Drag-Based Manipulation**