sberbank-ai
commited on
Commit
•
4dc33e2
1
Parent(s):
e21c2bb
Update README.md
Browse files
README.md
CHANGED
@@ -13,12 +13,12 @@ This is a fine-tuned version of the pre-trained [RuDOLPH 2.7B model](https://hug
|
|
13 |
|
14 |
*Hyper-tasking means generalized multi-tasking, e.g., the model that can solve almost all tasks within supported modalities (two modalities in case of RUDOLPH: images and Russian texts).*
|
15 |
|
16 |
-
* 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`
|
17 |
-
* Language: `Russian`
|
18 |
-
* Type: `decoder`
|
19 |
-
* Num Parameters: `2.7B`
|
20 |
-
* Training Data Volume: `119 million text-image pairs, 60 million text paragraphs`
|
21 |
-
* Fine-tuning Data Volume: `43 334 text question-answer pairs, 100 000 math tasks, 85 000 text-image pairs (for captioning, generation), 85 759 visual question-answer pairs, 140 000 image-text pairs for text recognition`
|
22 |
|
23 |
The model was prepared as a baseline for FusionBrain Challenge 2.0 (as a part of AI Journey Contest 2022) and is a fine-tuned version of the pre-trained [RuDOLPH 2.7B model](https://huggingface.co/sberbank-ai/RuDOLPH-2.7B) using 6 tasks:
|
24 |
|
|
|
13 |
|
14 |
*Hyper-tasking means generalized multi-tasking, e.g., the model that can solve almost all tasks within supported modalities (two modalities in case of RUDOLPH: images and Russian texts).*
|
15 |
|
16 |
+
* 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`
|
17 |
+
* Language: ` Russian`
|
18 |
+
* Type: ` decoder`
|
19 |
+
* Num Parameters: ` 2.7B`
|
20 |
+
* Training Data Volume: ` 119 million text-image pairs, 60 million text paragraphs`
|
21 |
+
* Fine-tuning Data Volume: ` 43 334 text question-answer pairs, 100 000 math tasks, 85 000 text-image pairs (for captioning, generation), 85 759 visual question-answer pairs, 140 000 image-text pairs for text recognition`
|
22 |
|
23 |
The model was prepared as a baseline for FusionBrain Challenge 2.0 (as a part of AI Journey Contest 2022) and is a fine-tuned version of the pre-trained [RuDOLPH 2.7B model](https://huggingface.co/sberbank-ai/RuDOLPH-2.7B) using 6 tasks:
|
24 |
|