# Multimodal Instruction Following

Dimple is the first discrete diffusion multimodal large language model (DMLLM) that combines autoregressive and diffusion training paradigms. After training on the same dataset as LLaVA-NEXT, it outperforms LLaVA-NEXT-7B by 3.9%.

Qwen2.5-VL-72B-Instruct is a 72B-parameter multimodal large model that supports vision-language tasks, capable of understanding and generating text related to images.

MLX format model converted from SmolVLM2-500M-Video-Instruct, supporting video-to-text tasks

A fine-tuned multimodal model based on unsloth/Llama-3.2-11B-Vision-Instruct, optimized for vision-language tasks and enhanced instruction-following capabilities, achieving 2x training acceleration through the Unsloth framework

A Turkish visual-language model specifically designed for multimodal visual instruction-following tasks, capable of processing both visual (image) and text inputs to understand and execute instructions provided in Turkish.

LLaVa is an open-source multimodal chatbot, fine-tuned on GPT-generated multimodal instruction-following data based on LLaMA/Vicuna, specifically optimized for chat/instruction-following as a multimodal version of LLM.

LLaRA is an open-source visual motion strategy model, fine-tuned from LLaVA-7b-v1.5 on instruction-following data and auxiliary datasets, primarily used for robotics research.

DenseConnector is an open-source chatbot, fine-tuned based on LLaMA/Vicuna and trained using GPT-generated multimodal instruction-following data.

LLaVA is an open-source multimodal chatbot, fine-tuned on large language models using multimodal instruction-following data.

LLaVA is an open-source multimodal chatbot, fine-tuned based on a large language model, supporting interactions with both images and text.

LLaVA is a multimodal large model that achieves general-purpose visual assistant capabilities by connecting a visual encoder with a large language model

A vision-language instruction-following model capable of generating Japanese descriptions for input images and optionally processing input text (e.g., questions).

LLaVA is an open-source multimodal chatbot, fine-tuned based on LLaMA/Vicuna and trained with GPT-generated multimodal instruction-following data.

LLaVA is an open-source multimodal chatbot, fine-tuned based on LLaMA/Vicuna, supporting image-text interaction.

SpeechGPT is a large language model with intrinsic cross-modal dialogue capabilities, capable of perceiving and generating multimodal content, supporting interaction via speech and text.

SpeechGPT is a large language model with intrinsic cross-modal dialogue capabilities, capable of perceiving and generating multimodal content based on human instructions.

InstructBLIP-Vicuna-7B is a vision-language model based on Vicuna-7B, supporting image-to-text conversion tasks.

LLaVA is an open-source multimodal chatbot, fine-tuned based on LLaMA/Vicuna and trained with GPT-generated multimodal instruction-following data.

LLaVA is an open-source chatbot fine-tuned with GPT-generated multimodal instruction-following data based on LLaMA/Vicuna

LLaVA is an open-source chatbot fine-tuned with GPT-generated multimodal instruction-following data based on LLaMA/Vicuna, supporting visual and language multimodal interactions.

LLaVA is an open-source chatbot fine-tuned with GPT-generated multimodal instruction-following data based on LLaMA/Vicuna, belonging to a Transformer-based autoregressive language model.