gte-multilingual-base

RK3588   |   LlamaPi Ready

Model Overview

Run with LlamaPi

llamapi pull gte-multilingual-base
llamapi load gte-multilingual-base

Use the loaded model through LlamaPi's embeddings API. See the LlamaPi Wiki for setup and usage.

About the Original Model

gte-multilingual-base is a multilingual text embedding model in the GTE family from Alibaba-NLP.

• Achieves state-of-the-art multilingual retrieval performance among similarly sized models.
• Uses an encoder-only architecture with lower inference requirements and roughly 10x faster inference than decoder-based embedding models.
• Supports over 70 languages and inputs up to 8,192 tokens, with elastic dense embeddings and sparse vectors.

License & Attribution

The models provided in this repository are converted and adapted by the Firefly AI team from the original models. All intellectual property rights and copyright in the underlying original models remain with the original official team, and their distribution is governed by the corresponding official open-source license.