moca-embed/MoCa-Qwen25VL-7B
Zero-Shot Image Classification
•
8B
•
Updated
•
86
•
1
None defined yet.
Welcome to MoCa-Embed! 👋
This is the organization of MoCa, which refers to Modality-aware Continual Pre-training for multimodal embedding models. In this organization, we release code, data and model checkpoints for MoCa embeddings.
🏠 Homepage | 💻 Code | 🤖 MoCa-Qwen25VL-7B | 🤖 MoCa-Qwen25VL-3B | 📚 Datasets | 📄 Paper