Commit
•
a0194f2
1
Parent(s):
796e22a
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ Model was trained by [Sber AI](https://github.com/sberbank-ai) and [SberDevices]
|
|
| 15 |
|
| 16 |
# Model Description
|
| 17 |
|
| 18 |
-
**Ru**ssian **D**iffusion **O**n **L**anguage **P**icture **H**yper-modality (RuDOLPH)
|
| 19 |
|
| 20 |
*(!!!) Hyper-modality means generalized multi-modal, e.g., model that consists of two multi-modal parts: text-2-image and image-2-text becomes text and image hyper-modality model*
|
| 21 |
|
|
|
|
| 15 |
|
| 16 |
# Model Description
|
| 17 |
|
| 18 |
+
**Ru**ssian **D**iffusion **O**n **L**anguage **P**icture **H**yper-modality (RuDOLPH) 350M is a fast and light text-image-text transformer (350M GPT-3) designed for a quick and easy fine-tuning setup for the solution of various tasks: from generating images by text description and image classification to visual question answering and more. This model demonstrates the power of Hyper-modality Transformers.
|
| 19 |
|
| 20 |
*(!!!) Hyper-modality means generalized multi-modal, e.g., model that consists of two multi-modal parts: text-2-image and image-2-text becomes text and image hyper-modality model*
|
| 21 |
|