# Multimodal large model

Heron-NVILA-Lite-33B is a vision-language model based on the NVILA-Lite architecture, specifically trained for Japanese, and supports multimodal tasks in both Japanese and English.

InternVL3-2B is a multimodal large language model implemented based on the Hugging Face Transformers library. It performs excellently in multimodal tasks such as image, video, and text processing, supporting multiple input methods and efficient batch inference.

A vision-language model designed specifically for Arabic optical character recognition (OCR), capable of directly recognizing Arabic text in images.

InternLM-XComposer2.5-OL is a comprehensive multimodal system supporting long-term streaming video and audio interaction.

XGen-MM is the latest multimodal large model series developed by Salesforce AI Research. Based on the successful design of BLIP, it achieves a more powerful and superior model architecture through fundamental enhancements.

A vision-language large model based on InternLM2 with outstanding image-text understanding and creation capabilities