# Image Text Generation

This is the quantized version of the pixtral-12b model, quantized using llama.cpp, supporting image-text-to-text tasks.

ViTucano is the first natively Portuguese pre-trained visual assistant, combining visual understanding and language capabilities, suitable for multimodal tasks such as image captioning and visual question answering.

GIT is a Transformer decoder-based vision-language model trained with CLIP image tokens and text token conditioning, suitable for tasks like image captioning and visual question answering.