# Multimodal instruction fine-tuning

A visual question answering model based on the Qwen2.5 architecture, focusing on Vietnamese scenarios and supporting the answering of image-related questions.

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 Korean automatic speech recognition (ASR) and speech translation (AST) model fine-tuned based on microsoft/Phi-4-multimodal-instruct, demonstrating excellent performance on the zeroth-korean and fleurs datasets.

A multimodal large language model fine-tuned based on Pixtral-12B-2409, specializing in generating rich image descriptions

This is a multimodal model based on Llama-3.2-11B-Vision-Instruct, which supports image and text input and generates text output.

xGen-MM is a series of the latest foundational large language models (LMMs) developed by Salesforce AI Research. It is improved on the basis of the BLIP series and incorporates enhanced features, with more powerful foundational capabilities.

ViP-LLaVA is an open-source multimodal chatbot, fine-tuned on LLaMA/Vicuna with image and region-level instruction data.