GeWu-Lab commited on
Commit
ff43d88
·
verified ·
1 Parent(s): 3b7cf39

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -4,7 +4,7 @@ tags:
4
  - multimodal
5
  - discrete-diffusion
6
  - vision-language
7
- - continual-pretraining
8
  ---
9
 
10
  <p align="center">
@@ -47,7 +47,7 @@ tags:
47
 
48
  ## Model Description
49
 
50
- This is the **Continual Pretraining (CPT)** checkpoint of Gestalt, trained with conditional masked prediction on 8M samples. For the full SFT model, see [GeWuLab/Gestalt-SFT](https://huggingface.co/GeWuLab/Gestalt-SFT).
51
 
52
  | Property | Value |
53
  |:--|:--|
 
4
  - multimodal
5
  - discrete-diffusion
6
  - vision-language
7
+ - unified-model
8
  ---
9
 
10
  <p align="center">
 
47
 
48
  ## Model Description
49
 
50
+ This is the official checkpoint of **Gestalt**, a large multimodal interplay model trained through three progressive stages: multimodal pretraining (70M), continual pretraining (8M), and interplay-oriented supervised fine-tuning (13.7M + 2.5M T2I). Gestalt supports both multimodal understanding and image generation within a unified discrete diffusion framework.
51
 
52
  | Property | Value |
53
  |:--|:--|