Qingni Wang
Qingni Wang
I need this too! Do u know how to evaluate on large-scale dataset now?
Me,too.Any updates?
metoo,anybody know?
> Hi @Michael4933, I use the huggingface link you suggested, but still get .satetensors files. Did you use the llama parameters from https://huggingface.co/yahma/llama-7b-hf/tree/main to generate bin files? Thank you! hi,...
> Now I have figured it out. It is very likely that the llama weights you select is not appropriate. My former attempt failed at choose a incorrect .pth file...
> The current model is not trained on joint multimodal data, so it may not perform well at the test time. But I see you run the test on Music-AVQA...
> Well, since we didn't train the model on exact pair data, the comparability might not satisfy your expectation at this time. > > Thanks for your attention. But I...
Me,too.Any updates?
> [@JjjFangg](https://github.com/JjjFangg) Hi, thanks for your reply. Did you mean max pixel = 16384_28_28, which is the default value for Qwen2.5VL? Hi, I want to know if you can reproduce...