Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs
Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs
Some questions about Pink-G
stage2_with_object365.sh
Some Question About MMbench Prompt
Fine-tuning settings on the refcoco dataset
How does the coordinates were processed?
stage2.sh
About VQAv2 and COCO2014
Considering LLAMA 3 or LLAMA 3.1 as base model
About inference.ipynb
stage1 checkpoint