Update README.md
Browse files
README.md
CHANGED
|
@@ -21,10 +21,9 @@ For Semantic Search Applications<br/>
|
|
| 21 |
</h3>
|
| 22 |
|
| 23 |
---
|
| 24 |
-
|
| 25 |
UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space!
|
| 26 |
|
| 27 |
-
This is model card of the __Multilingual model__ with:
|
| 28 |
|
| 29 |
* 12 layers BERT (8 layers for unimodal encoding and rest layers for multimodal encoding)
|
| 30 |
* ViT-B/16 (image resolution is 224x224)
|
|
@@ -32,6 +31,7 @@ This is model card of the __Multilingual model__ with:
|
|
| 32 |
The model was trained on balanced multilingual dataset.
|
| 33 |
|
| 34 |
If you need English model, check [this](https://huggingface.co/unum-cloud/uform-vl-english).
|
|
|
|
| 35 |
|
| 36 |
## Evaluation
|
| 37 |
|
|
|
|
| 21 |
</h3>
|
| 22 |
|
| 23 |
---
|
|
|
|
| 24 |
UForm is a Multi-Modal Modal Inference package, designed to encode Multi-Lingual Texts, Images, and, soon, Audio, Video, and Documents, into a shared vector space!
|
| 25 |
|
| 26 |
+
This is model card of the __Multilingual model__ (12 languages) with:
|
| 27 |
|
| 28 |
* 12 layers BERT (8 layers for unimodal encoding and rest layers for multimodal encoding)
|
| 29 |
* ViT-B/16 (image resolution is 224x224)
|
|
|
|
| 31 |
The model was trained on balanced multilingual dataset.
|
| 32 |
|
| 33 |
If you need English model, check [this](https://huggingface.co/unum-cloud/uform-vl-english).
|
| 34 |
+
If you need more languages, check [this](https://huggingface.co/unum-cloud/uform-vl-multilingual-v2)
|
| 35 |
|
| 36 |
## Evaluation
|
| 37 |
|