# Multimodal instruction following

Mistral-Small-3.2-24B-Instruct-2506 is an image-text-to-text model and an updated version of Mistral-Small-3.1-24B-Instruct-2503, with improvements in instruction following, reducing repetition errors, and function calls.

An 8B-parameter large language model developed by the Qwen team, supporting ultra-long context and multilingual processing

4-bit quantized version based on meta-llama/Llama-3.2-11B-Vision-Instruct, supporting image understanding and text generation tasks

MQT-LLaVA is an open-source multimodal chatbot model based on the Transformer architecture. It is trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction data.

LLaMA-VID is an open-source multimodal chatbot fine-tuned from LLaMA/Vicuna, supporting hours-long video processing through extended context tokens.

BakLLaVA-1 is a multimodal model based on Mistral 7B and enhanced with the LLaVA 1.5 architecture, outperforming Llama 2 13B on multiple benchmarks.