Update README.md

README.md

@@ -1063,53 +1063,136 @@ model-index:
     - type: f1
       value: 82.61420654584116
 ---
-
 <!-- TODO: add evaluation results here -->
 <br><br>
 
 <p align="center">
-<img src="https://github.com/jina-ai/finetuner/blob/main/docs/_static/finetuner-logo-ani.svg?raw=true" alt="Finetuner logo: Finetuner helps you to create experiments in order to improve embeddings on search tasks. It accompanies you to deliver the last mile of performance-tuning for neural search applications." width="150px">
+<img src="https://aeiljuispo.cloudimg.io/v7/https://cdn-uploads.huggingface.co/production/uploads/603763514de52ff951d89793/AFoybzd5lpBQXEBrQHuTt.png?w=200&h=200&f=face" alt="Finetuner logo: Finetuner helps you to create experiments in order to improve embeddings on search tasks. It accompanies you to deliver the last mile of performance-tuning for neural search applications." width="150px">
 </p>
 
 
 <p align="center">
-<b>The text embedding set trained by <a href="https://jina.ai/"><b>Jina AI</b></a>, <a href="https://github.com/jina-ai/finetuner"><b>Finetuner</b></a> team.</b>
+<b>The text embedding set trained by <a href="https://jina.ai/"><b>Jina AI</b></a>.</b>
 </p>
 
 
 ## Intended Usage & Model Info
 
-`jina-embeddings-v2-base-zh` is a Chinese/English bilingual text **embedding model** supporting **8192 sequence length**. Our model has the same architecture as `jina-embeddings-v2-base-en` and has 161 million parameters.
-We have designed it for high performance in cross-language applications and trained it specifically to support mixed Chinese-English input without bias. 
+`jina-embeddings-v2-base-zh` is a Chinese/English bilingual text **embedding model** supporting **8192 sequence length**.
+It is based on a BERT architecture (JinaBERT) that supports the symmetric bidirectional variant of [ALiBi](https://arxiv.org/abs/2108.12409) to allow longer sequence length.
+We have designed it for high performance in mongolingual & cross-language applications and trained it specifically to support mixed Chinese-English input without bias. 
+
+The embedding model was trained using 512 sequence length, but extrapolates to 8k sequence length (or even longer) thanks to ALiBi.
+This makes our model useful for a range of use cases, especially when processing long documents is needed, including long document retrieval, semantic textual similarity, text reranking, recommendation, RAG and LLM-based generative search, etc.
+
+With a standard size of 161 million parameters, the model enables fast inference while delivering better performance than our small model. It is recommended to use a single GPU for inference.
+Additionally, we provide the following embedding models:
+
+- [`jina-embeddings-v2-small-en`](https://huggingface.co/jinaai/jina-embeddings-v2-small-en): 33 million parameters.
+- [`jina-embeddings-v2-base-en`](https://huggingface.co/jinaai/jina-embeddings-v2-base-en): 137 million parameters.
+- [`jina-embeddings-v2-base-zh`](): Chinese-English Bilingual embeddings (soon) **(you are here)**.
+- [`jina-embeddings-v2-base-de`](): German-English Bilingual embeddings (soon).
+- [`jina-embeddings-v2-base-es`](): Spanish-English Bilingual embeddings (soon).
+
+## Data & Parameters
+
+Jina Embeddings V2 [technical report](https://arxiv.org/abs/2310.19923)
+
+## Usage
+
+**<details><summary>Please apply mean pooling when integrating the model.</summary>**
+<p>
 
-| Model | Language | Max Sequence Length | Dimension | Model Size |
-|:-----: | :-----: |:-----: |:-----: |:-----: |
-|[jina-embeddings-v2-base-en](https://huggingface.co/jinaai/jina-embeddings-v2-base-en) | English             | 8192 | 768 | 0.27GB |
-|[jina-embeddings-v2-base-zh](https://huggingface.co/jinaai/jina-embeddings-v2-base-zh) | Chinese and English | 8192 | 768 | 0.32GB |
+### Why mean pooling?
 
+`mean poooling` takes all token embeddings from model output and averaging them at sentence/paragraph level.
+It has been proved to be the most effective way to produce high-quality sentence embeddings.
+We offer an `encode` function to deal with this.
 
-You can use the embedding model either via the  Jina AI's [Embedding platform](https://jina.ai/embeddings/), AWS SageMaker or in your private deployments.
+However, if you would like to do it without using the default `encode` function:
 
-## Usage Jina Embedding API
+```python
+import torch
+import torch.nn.functional as F
+from transformers import AutoTokenizer, AutoModel
 
-The following code snippet shows the usage of the Jina Embedding API:
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0]
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+sentences = ['How is the weather today?', 'What is the current weather like today?']
+
+tokenizer = AutoTokenizer.from_pretrained('jinaai/jina-embeddings-v2-small-en')
+model = AutoModel.from_pretrained('jinaai/jina-embeddings-v2-small-en', trust_remote_code=True)
+
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+embeddings = F.normalize(embeddings, p=2, dim=1)
 ```
-curl https://api.jina.ai/v1/embeddings \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer jina_xxxxxxx" \
-  -d '{
-    "input": ["你的输入可以是纯中文", "or purely in English", "or like mixture of 中文 and 英文"],
-    "model": "jina-embeddings-v2-base-zh"
-  }'
 
+</p>
+</details>
+
+You can use Jina Embedding models directly from transformers package:
+```python
+!pip install transformers
+from transformers import AutoModel
+from numpy.linalg import norm
+
+cos_sim = lambda a,b: (a @ b.T) / (norm(a)*norm(b))
+model = AutoModel.from_pretrained('jinaai/jina-embeddings-v2-base-en', trust_remote_code=True) # trust_remote_code is needed to use the encode method
+embeddings = model.encode(['How is the weather today?', 'What is the current weather like today?'])
+print(cos_sim(embeddings[0], embeddings[1]))
+```
+
+If you only want to handle shorter sequence, such as 2k, pass the `max_length` parameter to the `encode` function:
+
+```python
+embeddings = model.encode(
+    ['Very long ... document'],
+    max_length=2048
+)
 ```
 
-Get your free API key on: https://jina.ai/embeddings/
+## Fully-managed Embeddings Service
+
+Alternatively, you can use Jina AI's [Embedding platform](https://jina.ai/embeddings/) for fully-managed access to Jina Embeddings models.
+
+## Use Jina Embeddings for RAG
+
+According to the latest blog post from [LLamaIndex](https://blog.llamaindex.ai/boosting-rag-picking-the-best-embedding-reranker-models-42d079022e83),
 
-## Opensource
+> In summary, to achieve the peak performance in both hit rate and MRR, the combination of OpenAI or JinaAI-Base embeddings with the CohereRerank/bge-reranker-large reranker stands out.
 
-We will add more information about this model and opensource the full model in a few days!
+<img src="https://miro.medium.com/v2/resize:fit:4800/format:webp/1*ZP2RVejCZovF3FDCg-Bx3A.png" width="780px">
+
+
+## Plans
+
+1. Bilingual embedding models supporting more European & Asian languages, including Spanish, French, Italian and Japanese.
+2. Multimodal embedding models enable MultimodalRAG applications.
+3. High-performt rerankers.
 
 ## Contact
 
-Join our [Discord community](https://discord.jina.ai) and chat with other community members about ideas.
+Join our [Discord community](https://discord.jina.ai) and chat with other community members about ideas.
+
+## Citation
+
+If you find Jina Embeddings useful in your research, please cite the following paper:
+
+```
+@misc{günther2023jina,
+      title={Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents}, 
+      author={Michael Günther and Jackmin Ong and Isabelle Mohr and Alaeddine Abdessalem and Tanguy Abel and Mohammad Kalim Akram and Susana Guzman and Georgios Mastrapas and Saba Sturua and Bo Wang and Maximilian Werk and Nan Wang and Han Xiao},
+      year={2023},
+      eprint={2310.19923},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```