# Multimodal Text Generation

Vintern-1B-v3_5 is a 1-billion-parameter vision-language model supporting image-text generation tasks.

This is a vision-enhanced version based on Mistral-Small-3.1-24B-Instruct-2503, supporting image-to-text generation tasks.

Gemma 3 4B parameter model optimized with OpenVINO, supporting text-to-text and visual-text inference

Gemma 3 is a lightweight open-source model series launched by Google, built on Gemini technology, supporting multimodal input and text output.

Gemma is a family of lightweight, cutting-edge open models from Google, built on the same research and technology as the Gemini models. The 1B version is a pretrained base model in GGUF format with Quantization-Aware Training (QAT).

A fine-tuned version of the Qwen2-VL-7B model, trained using Unsloth and Huggingface TRL library, achieving 2x inference speed improvement.

Llama 2 is a series of open-source large language models developed by Meta, supporting various natural language processing tasks.

ko-deplot is a Korean visual question answering model based on Google's Pix2Struct architecture, fine-tuned from the Deplot model, supporting chart image question-answering tasks in Korean and English.