Yesheng Liu

No such file(textvqa_val.jsonl) when evaluating textvqa

1

When I follow the method in "how_to_evaluate_internvl_chat_1_5.md" , I found that there is no such file in your repo data release. 404 page not found when run: wget https://github.com/OpenGVLab/InternVL/releases/download/data/textvqa_val.jsonl

I want to know how you create QA from collected data? What is the whole pipeline? I do not see any appendix in your released paper.

When I try to evaluate Ola model on MMMU with such command: `python run.py --model ola --data MMMU_DEV_VAL` I encounter this error when loading speech model: ``` [2025-04-09 06:46:03] ERROR...

feature: add model path argument

2

when using t2v_metrics as a package, `import t2v_metrics clip_flant5_score = t2v_metrics.VQAScore(model='clip-flant5-xxl') # our recommended scoring model ` the model path can not be specified directly. Instead, this argument is a...

How to utilize to image in labels directory?

2

It seems that all image in the labels directory is all black. I want to know how to use them.