Deepset Mxbai Embed De Large is a text embedding model hosted on Hugging Face under the identifier mixedbread-ai/deepset-mxbai-embed-de-large-v1. It belongs to the class of foundation models and performs the feature-extraction task. The model generates dense vector representations from German-language text input and is intended for use in semantic similarity, retrieval, and related applications where language-specific embeddings are required.
It is delivered as an open model on the Hugging Face platform. Inference is available through Hugging Face inference providers, with the current status listed as live for the feature-extraction task. The model uses a tokenizer configuration that defines specific tokens including a beginning-of-sequence token, end-of-sequence token, mask token, padding token, separator token, and unknown token. Downloads of the model have reached over three million in total.
The model page was created on 12 July 2024. It is provided within the broader Hugging Face ecosystem that supports open-source and open-science efforts in artificial intelligence.
Deepset Mxbai Embed De Large sits in PulseGate's Foundation models & chat category. It focuses on creating high-quality vector embeddings for German text to power semantic search and RAG applications. It is built as an open-source project for developers. Deepset Mxbai Embed De Large is open source under the Open Source license. The product ships for the command line, embeddable surfaces, and API.
It is developed by mixedbread.ai, and the product first shipped in 2024. Key capabilities include german embeddings, feature extraction, and semantic search.
Latest indexed changes and source events
mixedbread-ai/deepset-mxbai-embed-de-large-v1 verified by the PulseGate indexer
