Jina Embeddings V3 Separation Distilled

🚀 jina-embeddings-v3-separation-distilled

This model is a distilled version of the jinaai/jina-embeddings-v3 Sentence Transformer. It uses static embeddings, enabling much faster computation of text embeddings on both GPU and CPU. It's ideal for applications with limited computational resources or those requiring real - time performance.

📦 Installation

Install model2vec using pip:

pip install model2vec

💻 Usage Examples

Basic Usage

Load this model using the from_pretrained method:

from model2vec import StaticModel

# Load a pretrained Model2Vec model
model = StaticModel.from_pretrained("CISCai/jina-embeddings-v3-separation-distilled")

# Compute text embeddings
embeddings = model.encode(["Example sentence"])

Advanced Usage

The following code snippet shows how to load a Model2Vec model into a Sentence Transformer model:

from sentence_transformers import SentenceTransformer
from sentence_transformers.models import StaticEmbedding

# Initialize a StaticEmbedding module
static_embedding = StaticEmbedding.from_model2vec("CISCai/jina-embeddings-v3-separation-distilled")
model = SentenceTransformer(modules=[static_embedding])
embeddings = model.encode(["Example sentence"])

Another Advanced Usage

Alternatively, you can distill your own model using the distill method:

from model2vec.distill import distill

# Choose a Sentence Transformer model
model_name = "BAAI/bge-base-en-v1.5"

# Distill the model
m2v_model = distill(model_name=model_name, pca_dims=256)

# Save the model
m2v_model.save_pretrained("m2v_model")

🔧 Technical Details

Model2vec creates a small, fast, and powerful model that outperforms other static embedding models by a large margin on all tasks we could find, while being much faster to create than traditional static embedding models such as GloVe. Best of all, you don't need any data to distill a model using Model2Vec.

It works by passing a vocabulary through a sentence transformer model, then reducing the dimensionality of the resulting embeddings using PCA, and finally weighting the embeddings using zipf weighting. During inference, we simply take the mean of all token embeddings occurring in a sentence.

📚 Documentation

Additional Resources

• All Model2Vec models on the hub
• Model2Vec Repo
• Model2Vec Results
• Model2Vec Tutorials

Library Authors

Model2Vec was developed by the Minish Lab team consisting of Stephan Tulkens and Thomas van Dongen.

Citation

Please cite the Model2Vec repository if you use this model in your work.

@software{minishlab2024model2vec,
  authors = {Stephan Tulkens, Thomas van Dongen},
  title = {Model2Vec: Turn any Sentence Transformer into a Small Fast Model},
  year = {2024},
  url = {https://github.com/MinishLab/model2vec},
}

Model Information