# Multimodal QA

A vision-language model based on ViLT architecture, fine-tuned specifically for GQA visual reasoning tasks

This is a multimodal model based on Qwen2.5-VL-7B-Instruct, supporting visual question answering tasks, converted to MLX format for efficient operation on Apple chips.

VL-Rethinker-7B-8bit is a multimodal model based on Qwen2.5-VL-7B-Instruct, supporting visual question answering tasks.

TinyLLaVA-Video is a video understanding model based on Qwen2.5-3B and siglip-so400m-patch14-384, utilizing a grouped resampler for video frame processing

A multimodal model built on UMT-L and Qwen2-7B, supporting long video understanding with only 16 tokens per frame and an extended context window of 128k.

A vision-language model based on Microsoft's Phi-1.5 architecture, combined with CLIP for image processing capabilities

Idefics3 is an open-source multimodal model capable of processing arbitrary sequences of image and text inputs to generate text outputs. It shows significant improvements in OCR, document understanding, and visual reasoning.

Idefics2 is an open-source multimodal model capable of accepting arbitrary sequences of image and text inputs to generate text outputs. It shows significant improvements in OCR, document understanding, and visual reasoning.

Llava-Phi2 is a multimodal implementation based on Phi2, combining vision and language processing capabilities, suitable for image-text-to-text tasks.

VideoBLIP is an enhanced version of BLIP-2 capable of processing video data, using OPT-2.7b as the language model backbone.