luodi-7
/

internvl_memeloc_stage1

Model card Files Files and versions

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

模型介绍

微调internvl2_5-4B
希望能微调模型根据一串meme文字和meme底图学会输出【文字框位置+对应位置填的文字】
参考之前internvl微调visual grounding任务,检测抽象对话框，考虑框中放什么。
当前任务Writable text area[[xmin，ymin, xmax, ymax]]

测试结果

avg_iou=0.3192
avg_similarity=0.9698

Downloads last month: 9

Safetensors

Model size

4B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support