Part of the GTE (General Text Embeddings) family, this 7B parameter model is based on Qwen2 and fine-tuned for sentence similarity and embedding tasks. It achieves strong results on the MTEB benchmark and is intended for semantic search, retrieval-augmented generation, and clustering applications.
In the Foundation models & chat space, Gte Qwen2 7B Instruct takes a focused approach. It focuses on creating high-quality dense vector embeddings for text retrieval and semantic search. It is built as an open-source project for developers. Gte Qwen2 7B Instruct is open source under the Open Source license. It runs on the web and the command line, and it can be self-hosted.
Alibaba-NLP builds and maintains Gte Qwen2 7B Instruct, and the product first shipped in 2024.
Latest indexed changes and source events
Alibaba-NLP/gte-Qwen2-7B-instruct verified by the PulseGate indexer
Other apps tracked under the same category.
