Update README.md

README.md

@@ -41,8 +41,8 @@ This model is still in its infancy and it's meant to be constantly updated and t
   - #### Stable:
     - None
   - #### Beta:
-    - [vae.6770000.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.6770000.pt): Trained from scratch for 6.77M steps with **dim: 32**,**vq_codebook_dim: 8192** and **vq_codebook_size: 8192**.
-    - [maskgit.2896000.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/maskgit.2896000.pt): Maskgit trained from the beta VAE for 2.89M steps.
+    - [vae.7960000.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/vae.7960000.pt): Trained from scratch for 7.96M steps with **dim: 32**,**vq_codebook_dim: 8192** and **vq_codebook_size: 8192**.
+    - [maskgit.3500000.pt](https://huggingface.co/Sygil/Sygil-Muse/blob/main/maskgit.3500000.pt): Maskgit trained from the beta VAE for 3.50M steps.
 
   Note: Checkpoints under the Beta section are updated daily or at least 3-4 times a week. While the beta checkpoints can be used as they are, only the latest version is kept on the repo and the older checkpoints are removed when a new one
   is uploaded to keep the repo clean.
@@ -71,8 +71,8 @@ The model was trained on the following dataset:
 - **heads:** 8
 - **depth:** 4
 - **Random Crop:** True
-- **Total MaskGit Training Steps:** 2,896,000
-- **Total VAE Training Steps:** 6,770,000
+- **Total MaskGit Training Steps:** 3,500,000
+- **Total VAE Training Steps:** 7,960,000
 
   Note: On Muse we can change the image_size or resolution at any time without having to train the model from scratch again, this allows us to first train the model at low resolution using the same `dim` and `vq_codebook_size` to train faster and then we can increase the `image_size` and use a higher resolution once the model has trained enough.