This is a Japanese-specific Sentence-BERT model (version 2) based on the sentence-transformers framework. It generates high-quality embeddings for Japanese text that can be used for semantic similarity, clustering, and retrieval tasks. The model improves upon the first version with better loss functions and training data.
Sentence Bert Base Ja Mean Tokens is a Foundation models & chat product. It focuses on creating high-quality vector embeddings for Japanese sentences to enable semantic search and similarity tasks. Sentence Bert Base Ja Mean Tokens is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web, the command line, and API.
sonoisa builds and maintains Sentence Bert Base Ja Mean Tokens, and the product first shipped in 2022. Among its 3 catalogued features are Sentence Embeddings, Japanese Support, and Semantic Similarity.
Latest indexed changes and source events
sonoisa/sentence-bert-base-ja-mean-tokens-v2 verified by the PulseGate indexer
Other apps tracked under the same category.
