GLuCoSE-base-ja-v2 is a Japanese sentence embedding model hosted on Hugging Face. It belongs to the class of foundation models and supports the sentence-similarity task through dense vector representations of text. The model was created by pkshatech and made publicly available on the platform in 2024. It addresses the need for semantic processing of Japanese language inputs in embedding-based workflows.
The model is listed with a specific tokenizer configuration that defines special tokens including cls_token, eos_token, mask_token, pad_token, sep_token, and unk_token. It can be accessed for inference via providers on the Hugging Face infrastructure, where it is marked as live for the sentence-similarity task. Downloads of the model exceed one million in total, indicating repeated use by the community.
Delivery occurs through the Hugging Face ecosystem as an open-weights model that supports local download and integration into pipelines compatible with the platform's standards. No pricing details are stated for the model itself, which aligns with the open nature of content published on Hugging Face. The entry appears under the organization's repository without reference to proprietary licensing restrictions.
GLuCoSE Base Ja sits in PulseGate's Foundation models & chat category. It focuses on generating high-quality Japanese text embeddings for semantic search and similarity applications. It is built as an open-source project for developers. GLuCoSE Base Ja is open source under the Open Source license. GLuCoSE Base Ja is available on the web and API, and it can be self-hosted.
PKSHA Technology builds and maintains GLuCoSE Base Ja, and the product first shipped in 2019. Development happens publicly on GitHub with 13 stars. Key capabilities include Sentence Embeddings, Semantic Similarity, and Japanese Language Support. It exposes integrations via a public API.
Latest indexed changes and source events
pkshatech/GLuCoSE-base-ja-v2 verified by the PulseGate indexer
Other apps tracked under the same category.
