--- base_model: - Qwen/Qwen2.5-7B-Instruct --- # AllSparkv2: A Language-centric Progressive Omni-modal Learning Framework [Run Shao](https://scholar.google.com/citations?user=j3fct8MAAAAJ&hl=en&oi=ao), and [Haifeng Li](https://scholar.google.com/citations?user=51p_SJAAAAAJ&hl=en). **School of Geosciences and Info-physics, Central South University**

## Introduction AllSparkv2 is a progressive multimodal learning framework that decouples cross-modal general knowledge from modality-specific knowledge at both the architecture and training strategy levels. Inspired by Piaget's Theory of Cognitive Development, AllSparkv2 introduces the Modal Mixture of Experts (M-MoE) architecture, where dedicated experts handle different modalities to decouple the parameter space, and new modality experts inherit cross-modal general knowledge by initializing from existing ones. In training, a hierarchical modality learning strategy is implemented, starting with vision as the initial modality, followed by point clouds as the successive modality. AllSparkv2 undergoes full-parameter training on vision for powerful cross-modal general knowledge, while only modality-specific experts are trained for point clouds, preserving existing knowledge. Experimental results demonstrate that AllSparkv2 can progressively integrate new modalities while preventing catastrophic forgetting and enhancing cross-modal performance. ## Note We provide this model in four different sizes: 0.5B, 1B, 3B, and 7B. You can find them at the following links: - 0.5B model: [[Link](https://huggingface.co/ShaoRun/AllSparkv2-0.5B-V-P)] - 1.5B model: [[Link](https://huggingface.co/ShaoRun/AllSparkv2-1.5B-V-P)] - 3B model: [[Link](https://huggingface.co/ShaoRun/AllSparkv2-3B-V-P)] - 7B model: [[Link](https://huggingface.co/ShaoRun/AllSparkv2-7B-V-P)] If you're using AllSparkv2 in your research or applications, please cite using this BibTeX: ```bibtex ``` ## License This repository is under [BSD 3-Clause License](LICENSE.md).