From the source
Hugging Face and LlamaIndex release vdr-2b-multi-v1, a multilingual embedding model for visual document retrieval, along with its English-only variant vdr-2b-v1 and an open-source dataset vdr-multilingual-train.
From the source
We present vdr-2b-multi-v1, the best multilingual embedding model for visual document retrieval. We also release its English-only twin vdr-2b-v1 and open-source the new vdr-multilingual-train dataset.
huggingface.co
