# Multimodal instruction understanding

Mistral-Small-3.2-24B-Instruct-2506 is an image-text-to-text model that performs excellently in model quantization and shows significant improvements in instruction following, reducing repetition errors, and function calls.

A multilingual audio-to-text model based on Llama-3.1-8B-Instruct, supporting processing of over 40 languages

Qwen2.5-VL-32B-Instruct is a 32B-parameter multimodal vision-language model that supports joint understanding and generation tasks for images and text.

Qwen2-VL-2B-Instruct is a multimodal vision-language model that supports image-text-to-text tasks.

InstructCLIP is an instruction-guided image editing model improved through contrastive learning-based automatic data optimization. It combines CLIP and Stable Diffusion technologies to edit images based on textual instructions.

Phi-4-multimodal-instruct is a lightweight open-source multimodal foundation model that integrates language, vision, and speech research and datasets from Phi-3.5 and 4.0 models. It supports text, image, and audio inputs to generate text outputs, with a context length of 128K tokens.

ONNX version of the Phi-4 multimodal model, quantized to int4 precision with accelerated inference via ONNX Runtime, supporting text, image, and audio inputs.

Llama-3.2-11B-Vision-Instruct is a multilingual vision-language model that can be used for image-text to text conversion tasks.

The first vision-language model supporting Traditional Chinese instruction input (1.2B parameters), compatible with Transformers library, quick to load and easy to fine-tune

Octo Small is a diffusion policy model for robot control, based on Transformer architecture, capable of predicting robot actions from visual inputs and language instructions.