# For Academic Research Only

VARCO-VISION-14B is a powerful English-Korean visual language model that supports image and text input to generate text output, equipped with localization, referencing, and OCR capabilities.

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

This is a FLAN-T5 model trained on the arXiv math QA dataset, specializing in mathematical problem-solving tasks, but the output is unreliable and intended for research purposes only.

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.

LLaMA-13b is a 13 billion parameter large language model released by Meta, subject to a non-commercial use license agreement.