# ColBERT Strategy

A multilingual visual retrieval model based on Qwen2.5-VL-7B-Instruct using the ColBERT strategy, ranked first in the Vidore benchmark

A visual retrieval model based on Qwen2-VL-2B-Instruct and ColBERT strategy, capable of generating multi-vector representations for text and images

ColQwen2.5 is a visual retrieval model based on Qwen2.5-VL-3B-Instruct and the ColBERT strategy, focusing on efficiently indexing documents through visual features.

A visual retrieval model based on SmolVLM-Instruct-500M and the ColBERT strategy, capable of efficiently indexing documents through visual features

ColPali is a visual retrieval model based on PaliGemma-3B and the ColBERT strategy, designed for efficient document indexing through visual features

A visual retrieval model based on SmolVLM-Instruct and ColBERT strategy, capable of efficiently indexing documents through visual features

ColPali is a visual retrieval model based on PaliGemma-3B and ColBERT strategy, designed for efficient indexing of document visual features

ColQwen2 is a visual retrieval model based on Qwen2-VL-2B-Instruct and the ColBERT strategy, designed for efficient indexing of document visual features.

ColPali is a vision-language model based on PaliGemma-3B and the ColBERT strategy, designed for efficient document indexing from visual features.

ColPali is a visual retrieval model based on PaliGemma-3B and ColBERT strategy, designed for efficient document indexing from visual features.