Update README.md

README.md

@@ -123,31 +123,36 @@ library_name: transformers
 The easiest way to starting using `jina-embeddings-v3` is to use Jina AI's [Embedding API](https://jina.ai/embeddings/).
 
 
-## Intended Usage & Model Info
+## Intended Usage & Model info
 
-`jina-embeddings-v3` is a multilingual **text embedding model** supporting **8192 sequence length**.
-It is based on a XLMRoBERTa architecture (JinaXLMRoBERTa) that supports the Rotary Position Embeddings to allow longer sequence length.
-The backbone `JinaXLMRoBERTa ` is pretrained on variable length textual data on Mask Language Modeling objective for 160k steps on 89 languages.
-The model is further trained on Jina AI's collection of more than 500 millions of multilingual sentence pairs and hard negatives.
-These pairs were obtained from various domains and were carefully selected through a thorough cleaning process.
 
-`jina-embeddings-v3` has 5 task-specific LoRA adapters tuned on top of our backbone, add `task_type` as additional parameter when using the model:
+`jina-embeddings-v3` is a **multilingual multi-task text embedding model** designed for a variety of NLP applications.
+Based on the [XLM-RoBERTa architecture](https://huggingface.co/jinaai/xlm-roberta-flash-implementation), this model supports [Rotary Position Embeddings (RoPE)](https://arxiv.org/abs/2104.09864) to handle long sequences up to **8192 tokens**.
+Additionally, it features [LoRA](https://arxiv.org/abs/2106.09685) adapters to generate task-specific embeddings efficiently.
 
-TODO UPDATE THIS
+### Key Features:
+- **Extended Sequence Length:** Supports up to 8192 tokens with RoPE.
+- **Task-Specific Embedding:** Customize embeddings through the `task_type` argument with the following options:
+    - `retrieval.query`: Query encoding for asymmetric retrieval tasks
+    - `retrieval.passage`: Passage encoding for asymmetric retrieval tasks
+    - `separation`: For clustering and re-ranking applications
+    - `classification`: For classification tasks
+    - `text-matching`: For measuring textual similarity
+- **Matryoshka Embeddings**: Supports flexible embedding sizes (`32, 64, 128, 256, 512, 768, 1024`), allowing for truncating embeddings to fit your application.
 
-1. **query**: Handles user incoming queries at search time.
-2. **index**: Manages user documents submitted for indexing.
-3. **text-matching**: Processes symmetric text similarity tasks, whether short or long, such as STS (Semantic Textual Similarity).
-4. **classification**: Classifies user inputs into predefined categories.
-5. **clustering**: Facilitates the clustering of embeddings for further analysis.
+### Model Lineage:
 
-`jina-embeddings-v3` supports Matryoshka representation learning. We recommend using an embedding size of 128 or higher (1024 provides optimal performance) for storing your embeddings.
+`jina-embeddings-v3` builds upon the [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) model, which was originally trained on 100 languages. 
+We extended its capabilities with an extra pretraining phase on the [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX) dataset, then contrastively fine-tuned it on 30 languages for enhanced performance in both monolingual and cross-lingual setups.
 
+### Supported Languages:
+While the base model supports 100 languages, we've focused our tuning efforts on the following 30 languages to maximize performance: 
+**Arabic, Bengali, Chinese, Danish, Dutch, English, Finnish, French, Georgian, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Latvian, Norwegian, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Thai, Turkish, Ukrainian, Urdu,** and **Vietnamese.**
 
 
 ## Data & Parameters
 
-coming soon.
+The data and training details are described in this technical report (coming soon).
 
 ## Usage