M3E (Moka Massive Mixed Embedding) is an open-source text embedding model trained on over 22 million Chinese sentence pairs. It produces high-quality vector representations for semantic similarity, retrieval, and classification tasks. The base model supports both Chinese and English and is compatible with the sentence-transformers library.
M3e Base sits in PulseGate's Other AI category. It focuses on generating high-quality embeddings for Chinese and English text retrieval and semantic search. It is built as an open-source project for developers. M3e Base is open source under the Apache-2.0 license. The product ships for the web, the command line, and API.
Behind M3e Base is Moka AI, and the product first shipped in 2023. Development happens publicly on GitHub with 876 stars. Key capabilities include sentence embeddings, semantic similarity, and MTEB benchmark.
Latest indexed changes and source events
moka-ai/m3e-base verified by the PulseGate indexer
Other apps tracked under the same category.
