The text embedding set trained by Jina AI.
## Intended Usage & Model Info `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 **### 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. However, if you would like to do it without using the default `encode` function: ```python import torch import torch.nn.functional as F from transformers import AutoTokenizer, AutoModel 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) ```
## 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.
## 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}
}
```