# Visual language understanding

Gemma 3 is a lightweight, advanced open model series from Google, built on the same research and technology used to create Gemini models. This model is multimodal, capable of processing both text and image inputs to generate text outputs.

VL-Rethinker-7B 4-bit MLX Quantized Version is a quantized variant of the TIGER-Lab/VL-Rethinker-7B model, optimized for Apple devices and supporting visual question-answering tasks.

Qwen2.5-VL-32B-Instruct is a multimodal vision-language model with a parameter scale of 32B, supporting image understanding and text generation tasks.

A visual language model for classifying offensive emojis in the Singapore context, fine-tuned based on Qwen2-VL-7B-Instruct

The Mulberry model is a step-by-step reasoning-based model trained on the Mulberry - 260K SFT dataset generated through collective knowledge search.

The Magician is the first multi-modal large language model with free-form multi-image localization capabilities, achieving precise localization in complex multi-image scenarios and outperforming models with a scale of 70B in performance.

An open-source chatbot model trained by fine-tuning the entire model on open-source data, which can be used for research on multimodal models and chatbots.

Qwen2-VL-7B-Instruct is a multimodal vision-language model that supports the joint understanding and generation of images and text.

GLM-Edge-V-5B is a 5-billion-parameter multimodal model that supports image and text inputs, capable of performing image understanding and text generation tasks.