|
--- |
|
tags: |
|
- RUDOLPH |
|
- text-image |
|
- image-text |
|
- decoder |
|
--- |
|
# RUDOLPH-1.3B (Large) |
|
|
|
RUDOLPH: One Hyper-Tasking Transformer Can be Creative as DALL-E and GPT-3 and Smart as CLIP |
|
|
|
<img src="https://raw.githubusercontent.com/sberbank-ai/ru-dolph/master/pics/RUDOLPH.png" width=60% border="2"/> |
|
|
|
Model was trained by [Sber AI](https://github.com/sberbank-ai) team. |
|
|
|
# Model Description |
|
|
|
**RU**ssian **D**ecoder **O**n **L**anguage **P**icture **H**yper-tasking (**RUDOLPH**) **1.3B** is a large text-image-text transformer designed for an easy fine-tuning for a range of tasks: from generating images by text description and image classification to visual question answering and more. This model demonstrates the power of Hyper-tasking Transformers. |
|
|
|
*Hyper-tasking model is a generalized multi-tasking model, i.e., the model that can solve almost all tasks within supported modalities, mandatory including mutual pairwise translations between modalities (two modalities in case of RUDOLPH: images and Russian texts).* |
|
|
|
* Tasks: ` text2image generation, self reranking, text ranking, image ranking, image2text generation, zero-shot image classification, text2text generation, text-qa, math-qa, image captioning, image generation, text-in-the-wild, vqa, and so on` |
|
* Language: ` Russian` |
|
* Type: ` decoder` |
|
* Num Parameters: ` 1.3B` |
|
* Training Data Volume: ` 119 million text-image pairs, 60 million text paragraphs` |
|
|
|
# Details of architecture |
|
|
|
<img src=https://raw.githubusercontent.com/ai-forever/ru-dolph/master/pics/scheme-rudolph_13b.jpg height="20" border="2"/> |
|
|
|
The maximum sequence length that this model may be used with depends on the modality and stands for 128 - 1024 - 128 for the left text tokens, image tokens, and right text tokens, respectively. |
|
|
|
RUDOLPH 1.3B is a Transformer-based decoder model with the following parameters: |
|
|
|
* num\_layers (24) — Number of hidden layers in the Transformer decoder. |
|
* hidden\_size (2048) — Dimensionality of the hidden layers. |
|
* num\_attention\_heads (16) — Number of attention heads for each attention layer. |
|
|
|
# Sparse Attention Mask |
|
|
|
The primary proposed method is to modify the sparse transformer's attention mask to better control multi-modalities and up to the next level with "hyper-modality". It allows us to calculate the transitions of modalities in both directions, unlike another similar work DALL-E Transformer, which used only one direction, "text to image". The proposed "image to right text" direction is achieved by extension sparse attention mask to the right for auto-repressively text generation with both image and left text condition. |
|
|
|
<img src="https://raw.githubusercontent.com/lizagonch/ru-dolph/develop_v1/pics/attention_masks_1300m.png" height="20" border="2"/> |
|
|
|
# Authors |
|
|
|
+ Alex Shonenkov: [Github](https://github.com/shonenkov), [Kaggle GM](https://www.kaggle.com/shonenkov) |
