nomic-embed-text-v2-moe
Multilingual MoE text embedding model excelling at multilingual retrieval with SoTA performance compared to ~300M parameter models, supporting ~100 languages with Matryoshka Embeddings trained on 1.6B pairs.
About this tool
Overview
nomic-embed-text-v2-moe is a multilingual MoE (Mixture of Experts) text embedding model that excels at multilingual retrieval. It offers high performance with state-of-the-art multilingual performance compared to ~300M parameter models.
Key Features
Multilingual Support
Supports approximately 100 languages, providing robust multilingual, cross-lingual, and code retrieval capabilities.
Training
Trained on over 1.6 billion pairs, ensuring comprehensive coverage across languages and domains.
Matryoshka Embeddings
Supports flexible embedding dimensions through Matryoshka Embeddings, allowing you to truncate vectors to smaller dimensions without retraining.
Performance
Offers state-of-the-art multilingual performance compared to models with around 300M parameters, making it highly efficient for its size.
Local Deployment
Available through Ollama, allowing you to:
- Run the model completely offline
- Ensure complete data privacy
- Eliminate internet dependency for processing documents
- Deploy on your own infrastructure
Use Cases
- Multilingual semantic search
- Cross-lingual information retrieval
- International document processing
- Code search across multiple programming languages
- RAG systems for multilingual content
Integration
- Available through Ollama for easy local deployment
- Compatible with various embedding frameworks
- Can be used with Chroma, Milvus, and other vector databases
Pricing
Free and open-source, runs locally through Ollama.
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)