# JSON Structured Output

QwenGuard is a visual security protection model capable of evaluating images based on provided security policies, outputting safety ratings, safety categories, and evaluation rationale.

QwenGuard-v1.2-3B is a visual security protection model developed based on Qwen/Qwen2.5-VL-3B-Instruct, designed for assessing the safety of image content.

Cephalo-Gemma-3-4b is a cross-modal vision-language model focused on biomimetic material analysis and design.

A Korean large language model fine-tuned based on Qwen2.5-14B, specializing in RAG (Retrieval-Augmented Generation) tasks, capable of generating structured responses with source citations.

A text-to-graph information extraction model based on Qwen-2.5-0.5B, jointly trained through reinforcement learning (GRPO) and supervised learning.

LlavaGuard is a safety evaluation guardian based on vision-language models, primarily used for safety classification and violation detection of image content.

LlavaGuard is a safety assessment system based on a vision-language model, primarily used for safety classification and compliance checks of image content.

LlavaGuard is a dataset safety evaluation and assurance framework based on visual-language models, primarily used for content safety evaluation.

This model is a proposition segmentation model based on Flan-T5-Large, designed to decompose text content into independent propositional units.