# Document Image Analysis

Quantized version of Qwen2.5-VL-7B-Instruct, supporting vision-text input and text output, with weights quantized to INT4 and activations to FP16.

PaliGemma 2 is an upgraded vision-language model released by Google, combining the capabilities of Gemma 2 and SigLIP vision models, supporting multilingual vision-language tasks.

A fine-tuned image-to-text generation model based on PaliGemma 224x224 version, specializing in generating detailed descriptions for artistic images