metadata
license: apache-2.0
datasets:
- Michael4933/MGrounding-630k
- lmms-lab/M4-Instruct-Data
- lmms-lab/LLaVA-OneVision-Data
language:
- en
metrics:
- accuracy
base_model:
- Qwen/Qwen2-VL-7B-Instruct
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models