# Multimodal Large Model

An improved vision-language model based on Qwen2.5-VL-72B-Instruct, excelling in multiple visual reasoning benchmarks

A visual question answering model fine-tuned based on InternVL3-1B and Vintern-1B-v3_5, supporting Vietnamese, suitable for image content understanding and question-answering tasks.

EMOVA is an end-to-end omni-modal large language model that supports visual, auditory, and speech functions, capable of generating text and speech responses with emotional control.

InternVL3 is an advanced series of multimodal large language models, demonstrating exceptional multimodal perception and reasoning capabilities, supporting image, video, and text inputs.

InternVL3-78B is an advanced multimodal large language model developed by OpenGVLab, demonstrating exceptional comprehensive performance. Compared to its predecessor InternVL 2.5, it possesses stronger multimodal perception and reasoning capabilities, extending its abilities to new domains such as tool usage, GUI agents, industrial image analysis, and 3D visual perception.

A 4-bit GPTQ quantized version of the Qwen2.5-Omni-7B model, supporting multilingual and multimodal tasks.

InternVideo2.5 is a video multimodal large language model (MLLM) enhanced by long and rich context (LRC) modeling, built upon InternVL2.5.

InternVideo2.5 is a video multimodal large language model enhanced by Long and Rich Context (LRC) modeling, built upon InternVL2.5. It significantly improves existing MLLM models by enhancing the ability to perceive fine-grained details and capture long-term temporal structures.

mPLUG-Owl3 is an advanced multimodal large language model that focuses on solving the problem of long image sequence understanding. It significantly improves the processing speed and sequence length support through the hyper attention mechanism.

A large-scale vision-language model developed by Japan's National Institute of Informatics, supporting Japanese and English with strong image understanding and text generation capabilities.

An instruction-fine-tuned version based on the Pixtral-12B-2409 multimodal large language model, capable of generating richer detail descriptions for given images

mPLUG-DocOwl2 is an OCR-free multimodal large language model for multi-page document understanding, efficiently encoding document content via a high-resolution document compressor.

ChartMoE is a multimodal large language model based on InternLM-XComposer2, featuring a mixture of experts connector with advanced chart capabilities.

Kangaroo is a powerful multimodal large language model specifically designed for long video understanding, supporting bilingual dialogue (Chinese-English) and long video inputs.

InternLM-XComposer2 is a vision-language large model developed based on InternLM2, featuring outstanding image-text understanding and creation capabilities.