Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,12 @@ library_name: transformers
|
|
| 27 |
tags:
|
| 28 |
- vision-language
|
| 29 |
- retrieval
|
| 30 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
pipeline_tag: visual-document-retrieval
|
| 32 |
base_model:
|
| 33 |
- google/gemma-3-4b-it
|
|
@@ -112,7 +117,7 @@ model-index:
|
|
| 112 |
NetraEmbed is a multilingual multimodal embedding model that encodes both visual documents and text queries into single dense vectors. It supports multiple languages and enables efficient similarity search at multiple embedding dimensions (768, 1536, 2560) through Matryoshka representation learning.
|
| 113 |
|
| 114 |
- **Model Type:** Multilingual Multimodal Embedding Model with Matryoshka embeddings
|
| 115 |
-
- **Architecture:** BiEncoder with Gemma3-
|
| 116 |
- **Embedding Dimensions:** 768, 1536, 2560 (Matryoshka)
|
| 117 |
- **Capabilities:** Multilingual, Multimodal (Vision + Text)
|
| 118 |
- **Use Case:** Visual document retrieval, multilingual semantic search, cross-lingual document understanding
|
|
|
|
| 27 |
tags:
|
| 28 |
- vision-language
|
| 29 |
- retrieval
|
| 30 |
+
- multimodal
|
| 31 |
+
- multilingual
|
| 32 |
+
- document-retrieval
|
| 33 |
+
- matryoshka-embeddings
|
| 34 |
+
- dense-retrieval
|
| 35 |
+
- 22-languages
|
| 36 |
pipeline_tag: visual-document-retrieval
|
| 37 |
base_model:
|
| 38 |
- google/gemma-3-4b-it
|
|
|
|
| 117 |
NetraEmbed is a multilingual multimodal embedding model that encodes both visual documents and text queries into single dense vectors. It supports multiple languages and enables efficient similarity search at multiple embedding dimensions (768, 1536, 2560) through Matryoshka representation learning.
|
| 118 |
|
| 119 |
- **Model Type:** Multilingual Multimodal Embedding Model with Matryoshka embeddings
|
| 120 |
+
- **Architecture:** BiEncoder with Gemma3-4B backbone
|
| 121 |
- **Embedding Dimensions:** 768, 1536, 2560 (Matryoshka)
|
| 122 |
- **Capabilities:** Multilingual, Multimodal (Vision + Text)
|
| 123 |
- **Use Case:** Visual document retrieval, multilingual semantic search, cross-lingual document understanding
|